模型价格目录模型成本，
模型成本，
不再靠猜。
比较 2940 条有来源的模型价格记录。所有数字均为带日期的静态快照，可自行核验。
| 模型 | 来源 / 更新 | 输入 / 百万 | 输出 / 百万 | 上下文 | Tokenizer |
|---|---|---|---|---|---|
| ai21.j2 mid v1ai21.j2-mid-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $12.50 | $12.50 | 8,191 tokens | 估算o200k_base |
| ai21.j2 ultra v1ai21.j2-ultra-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $18.80 | $18.80 | 8,191 tokens | 估算o200k_base |
| ai21.jamba 1 5 large v1:0ai21.jamba-1-5-large-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 256,000 tokens | 估算o200k_base |
| ai21.jamba 1 5 mini v1:0ai21.jamba-1-5-mini-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 256,000 tokens | 估算o200k_base |
| ai21.jamba instruct v1:0ai21.jamba-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.70 | 70,000 tokens | 估算o200k_base |
| agnes 2.5 flashaihubmix/agnes-2.5-flash · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.15 | 512,000 tokens | 估算o200k_base |
| agnes 2.5 proaihubmix/agnes-2.5-pro · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.45 | $0.90 | 1,000,000 tokens | 估算o200k_base |
| cc glm 5.1aihubmix/cc-glm-5.1 · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.22 | 200,000 tokens | 估算o200k_base |
| Claude fable 5aihubmix/claude-fable-5 · aihubmix | LiteLLM ↗2026-10-25 UTC | $11.00 | $55.00 | 1,000,000 tokens | 估算o200k_base |
| Claude haiku 4 5aihubmix/claude-haiku-4-5 · aihubmix | LiteLLM ↗2026-10-25 UTC | $1.10 | $5.50 | 200,000 tokens | 估算o200k_base |
| Claude opus 4 8 thinkaihubmix/claude-opus-4-8-think · aihubmix | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5aihubmix/claude-opus-5 · aihubmix | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 5aihubmix/claude-sonnet-5 · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| coding glm 5.3aihubmix/coding-glm-5.3 · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.22 | 1,048,576 tokens | 估算o200k_base |
| coding kimi k3aihubmix/coding-kimi-k3 · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.44 | $1.61333 | 1,048,576 tokens | 估算o200k_base |
| coding xiaomi mimo v2.5aihubmix/coding-xiaomi-mimo-v2.5 · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.16 | 1,048,576 tokens | 估算o200k_base |
| coding xiaomi mimo v2.5 proaihubmix/coding-xiaomi-mimo-v2.5-pro · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 1,048,576 tokens | 估算o200k_base |
| command a plus 05 2026aihubmix/command-a-plus-05-2026 · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| DeepSeek v4 flashaihubmix/deepseek-v4-flash · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.142 | $0.284 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 proaihubmix/deepseek-v4-pro · aihubmix | LiteLLM ↗2026-10-25 UTC | $1.69 | $3.38 | 1,000,000 tokens | 估算o200k_base |
| doubao seed 2 0 code previewaihubmix/doubao-seed-2-0-code-preview · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.4822 | $2.411 | 256,000 tokens | 估算o200k_base |
| doubao seed 2 0 lite 260428aihubmix/doubao-seed-2-0-lite-260428 · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.09041 | $0.54246 | 256,000 tokens | 估算o200k_base |
| doubao seed 2 0 miniaihubmix/doubao-seed-2-0-mini · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.030136 | $0.30136 | 256,000 tokens | 估算o200k_base |
| doubao seed 2 0 proaihubmix/doubao-seed-2-0-pro · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.4822 | $2.411 | 256,000 tokens | 估算o200k_base |
| doubao seed 2 1 turboaihubmix/doubao-seed-2-1-turbo · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.46475 | $2.32375 | 256,000 tokens | 估算o200k_base |
| ernie 5.1aihubmix/ernie-5.1 · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.5634 | $2.5353 | 119,000 tokens | 估算o200k_base |
| Gemini 3 flash previewaihubmix/gemini-3-flash-preview · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.50 | $3.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3 flash preview searchaihubmix/gemini-3-flash-preview-search · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.50 | $3.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 pro previewaihubmix/gemini-3.1-pro-preview · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 pro preview customtoolsaihubmix/gemini-3.1-pro-preview-customtools · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.5 flash liteaihubmix/gemini-3.5-flash-lite · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.499999 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.7 flashaihubmix/gemini-3.7-flash · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,048,576 tokens | 估算o200k_base |
| gemma 4 26b a4b itaihubmix/gemma-4-26b-a4b-it · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.39998 | 262,144 tokens | 估算o200k_base |
| gemma 4 31b itaihubmix/gemma-4-31b-it · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.39998 | 262,144 tokens | 估算o200k_base |
| glm 5.2 fast previewaihubmix/glm-5.2-fast-preview · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.254 | $7.889 | 1,000,000 tokens | 估算o200k_base |
| glm 5.3aihubmix/glm-5.3 · aihubmix | LiteLLM ↗2026-10-25 UTC | $1.1268 | $3.9438 | 1,048,576 tokens | 估算o200k_base |
| glm 5.3 flashaihubmix/glm-5.3-flash · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.11268 | $0.39438 | 1,048,576 tokens | 估算o200k_base |
| glm 5v turboaihubmix/glm-5v-turbo · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.7042 | $3.09848 | 200,000 tokens | 估算o200k_base |
| GPT 5.3 codexaihubmix/gpt-5.3-codex · aihubmix | LiteLLM ↗2026-10-25 UTC | $1.75 | $14.00 | 400,000 tokens | 估算o200k_base |
| GPT 5.4 highaihubmix/gpt-5.4-high · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.50 | $15.00 | 1,050,000 tokens | 估算o200k_base |
| GPT 5.4 lowaihubmix/gpt-5.4-low · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.50 | $15.00 | 1,050,000 tokens | 估算o200k_base |
| GPT 5.4 miniaihubmix/gpt-5.4-mini · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.75 | $4.50 | 400,000 tokens | 估算o200k_base |
| GPT 5.4 nanoaihubmix/gpt-5.4-nano · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.25 | 400,000 tokens | 估算o200k_base |
| GPT 5.5aihubmix/gpt-5.5 · aihubmix | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 1,050,000 tokens | 估算o200k_base |
| GPT 5.5 proaihubmix/gpt-5.5-pro · aihubmix | LiteLLM ↗2026-10-25 UTC | $30.00 | $180.00 | 1,050,000 tokens | 估算o200k_base |
| GPT 5.6 lunaaihubmix/gpt-5.6-luna · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.20 | 1,050,000 tokens | 估算o200k_base |
| GPT 5.6 sol discaihubmix/gpt-5.6-sol-disc · aihubmix | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 1,050,000 tokens | 估算o200k_base |
| GPT 5.6 terraaihubmix/gpt-5.6-terra · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,050,000 tokens | 估算o200k_base |
| GPT chat latestaihubmix/gpt-chat-latest · aihubmix | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 400,000 tokens | 估算o200k_base |
| grok 4 20 non reasoningaihubmix/grok-4-20-non-reasoning · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 1,000,000 tokens | 估算o200k_base |
| grok 4 20 reasoningaihubmix/grok-4-20-reasoning · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 1,000,000 tokens | 估算o200k_base |
| grok 4.6aihubmix/grok-4.6 · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 500,000 tokens | 估算o200k_base |
| grok build 0.1aihubmix/grok-build-0.1 · aihubmix | LiteLLM ↗2026-10-25 UTC | $1.00 | $2.00 | 256,000 tokens | 估算o200k_base |
| hy3aihubmix/hy3 · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.1562 | $0.6248 | 256,000 tokens | 估算o200k_base |
| hy4 previewaihubmix/hy4-preview · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.845 | $2.535 | 1,048,576 tokens | 估算o200k_base |
| kimi k2.6aihubmix/kimi-k2.6 · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.95 | $3.9995 | 262,144 tokens | 估算o200k_base |
| kimi k2.7 code highspeedaihubmix/kimi-k2.7-code-highspeed · aihubmix | LiteLLM ↗2026-10-25 UTC | $1.90 | $7.999 | 262,144 tokens | 估算o200k_base |
| kimi k3aihubmix/kimi-k3 · aihubmix | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,048,576 tokens | 估算o200k_base |
| longcat 2.0aihubmix/longcat-2.0 · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.7746 | $3.0984 | 1,000,000 tokens | 估算o200k_base |
| mai thinking 1aihubmix/mai-thinking-1 · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 256,000 tokens | 估算o200k_base |
| mimo v2 omniaihubmix/mimo-v2-omni · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.44 | $2.20 | 256,000 tokens | 估算o200k_base |
| mimo v2 proaihubmix/mimo-v2-pro · aihubmix | LiteLLM ↗2026-10-25 UTC | $1.10 | $3.30 | 1,000,000 tokens | 估算o200k_base |
| minimax m2.7aihubmix/minimax-m2.7 · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.2958 | $1.1832 | 204,800 tokens | 估算o200k_base |
| minimax m3aihubmix/minimax-m3 · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.288 | $1.152 | 1,000,000 tokens | 估算o200k_base |
| muse spark 1.2aihubmix/muse-spark-1.2 · aihubmix | LiteLLM ↗2026-10-25 UTC | $1.375 | $4.675 | 1,048,576 tokens | 估算o200k_base |
| qwen3 coder nextaihubmix/qwen3-coder-next · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.137 | $0.548 | 262,144 tokens | 估算o200k_base |
| qwen3.5 122b a10baihubmix/qwen3.5-122b-a10b · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.1126 | $0.9008 | 262,144 tokens | 估算o200k_base |
| qwen3.5 397b a17baihubmix/qwen3.5-397b-a17b · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.1644 | $0.9864 | 262,144 tokens | 估算o200k_base |
| qwen3.6 27baihubmix/qwen3.6-27b · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.422 | $2.532 | 262,144 tokens | 估算o200k_base |
| qwen3.6 35b a3baihubmix/qwen3.6-35b-a3b · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.254 | $1.524 | 262,144 tokens | 估算o200k_base |
| qwen3.6 max previewaihubmix/qwen3.6-max-preview · aihubmix | LiteLLM ↗2026-10-25 UTC | $1.268 | $7.608 | 262,144 tokens | 估算o200k_base |
| qwen3.7 plusaihubmix/qwen3.7-plus · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.282 | $1.128 | 1,000,000 tokens | 估算o200k_base |
| qwen3.8 2.4t a95baihubmix/qwen3.8-2.4t-a95b · aihubmix | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 1,000,000 tokens | 估算o200k_base |
| qwen3.8 flashaihubmix/qwen3.8-flash · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.1126 | $0.380025 | 1,000,000 tokens | 估算o200k_base |
| qwen3.8 maxaihubmix/qwen3.8-max · aihubmix | LiteLLM ↗2026-10-25 UTC | $1.69 | $5.07 | 1,000,000 tokens | 估算o200k_base |
| step 3.7 flashaihubmix/step-3.7-flash · aihubmix | LiteLLM ↗2026-10-25 UTC | $0.22 | $1.32 | 256,000 tokens | 估算o200k_base |
| nova lite v1amazon-nova/nova-lite-v1 · amazon_nova | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.24 | 300,000 tokens | 估算o200k_base |
| nova micro v1amazon-nova/nova-micro-v1 · amazon_nova | LiteLLM ↗2026-10-25 UTC | $0.035 | $0.14 | 128,000 tokens | 估算o200k_base |
| nova premier v1amazon-nova/nova-premier-v1 · amazon_nova | LiteLLM ↗2026-10-25 UTC | $2.50 | $12.50 | 1,000,000 tokens | 估算o200k_base |
| nova pro v1amazon-nova/nova-pro-v1 · amazon_nova | LiteLLM ↗2026-10-25 UTC | $0.80 | $3.20 | 300,000 tokens | 估算o200k_base |
| amazon.nova 2 lite v1:0amazon.nova-2-lite-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| amazon.nova 2 pro preview 20251202 v1:0amazon.nova-2-pro-preview-20251202-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| amazon.nova lite v1:0amazon.nova-lite-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.24 | 300,000 tokens | 估算o200k_base |
| amazon.nova micro v1:0amazon.nova-micro-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.035 | $0.14 | 128,000 tokens | 估算o200k_base |
| amazon.nova premier v1:0amazon.nova-premier-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.50 | $12.50 | 1,000,000 tokens | 估算o200k_base |
| amazon.nova pro v1:0amazon.nova-pro-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.80 | $3.20 | 300,000 tokens | 估算o200k_base |
| amazon.titan text express v1amazon.titan-text-express-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 42,000 tokens | 估算o200k_base |
| amazon.titan text lite v1amazon.titan-text-lite-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.20 | 42,000 tokens | 估算o200k_base |
| amazon.titan text premier v1:0amazon.titan-text-premier-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 42,000 tokens | 估算o200k_base |
| anthropic.Claude 3 5 haiku 20241022 v1:0anthropic.claude-3-5-haiku-20241022-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.80 | $4.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude 3 5 sonnet 20240620 v1:0anthropic.claude-3-5-sonnet-20240620-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude 3 5 sonnet 20241022 v2:0anthropic.claude-3-5-sonnet-20241022-v2:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude 3 7 sonnet 20240620 v1:0anthropic.claude-3-7-sonnet-20240620-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.60 | $18.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude 3 7 sonnet 20250219 v1:0anthropic.claude-3-7-sonnet-20250219-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude 3 opus 20240229 v1:0anthropic.claude-3-opus-20240229-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude fable 5anthropic.claude-fable-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude fable 5 1anthropic.claude-fable-5-1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude haiku 4 5 20251001 v1:0anthropic.claude-haiku-4-5-20251001-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude haiku 4 5@20251001anthropic.claude-haiku-4-5@20251001 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude haiku 5 5anthropic.claude-haiku-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude instant v1anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.80 | $2.40 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude mythos 5 1anthropic.claude-mythos-5-1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude mythos previewanthropic.claude-mythos-preview · bedrock | LiteLLM ↗2026-10-25 UTC | $27.50 | $137.50 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 4 1 20250805 v1:0anthropic.claude-opus-4-1-20250805-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude opus 4 20250514 v1:0anthropic.claude-opus-4-20250514-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude opus 4 5 20251101 v1:0anthropic.claude-opus-4-5-20251101-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude opus 4 6 v1anthropic.claude-opus-4-6-v1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 4 7anthropic.claude-opus-4-7 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 4 8anthropic.claude-opus-4-8 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 5anthropic.claude-opus-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 5 5anthropic.claude-opus-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 4 20250514 v1:0anthropic.claude-sonnet-4-20250514-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 4 5 20250929 v1:0anthropic.claude-sonnet-4-5-20250929-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 4 6anthropic.claude-sonnet-4-6 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 5anthropic.claude-sonnet-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 5 5anthropic.claude-sonnet-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude v1anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $8.00 | $24.00 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | $8.00 | $24.00 | 100,000 tokens | 估算o200k_base |
| CodeLlama 34b Instruct hfanyscale/codellama/CodeLlama-34b-Instruct-hf · anyscale | LiteLLM ↗2026-10-25 UTC | $1.00 | $1.00 | 4,096 tokens | 估算o200k_base |
| CodeLlama 70b Instruct hfanyscale/codellama/CodeLlama-70b-Instruct-hf · anyscale | LiteLLM ↗2026-10-25 UTC | $1.00 | $1.00 | 4,096 tokens | 估算o200k_base |
| gemma 7b itanyscale/google/gemma-7b-it · anyscale | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 8,192 tokens | 估算o200k_base |
| zephyr 7b betaanyscale/HuggingFaceH4/zephyr-7b-beta · anyscale | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 16,384 tokens | 估算o200k_base |
| Llama 2 13b chat hfanyscale/meta-llama/Llama-2-13b-chat-hf · anyscale | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.25 | 4,096 tokens | 估算o200k_base |
| Llama 2 70b chat hfanyscale/meta-llama/Llama-2-70b-chat-hf · anyscale | LiteLLM ↗2026-10-25 UTC | $1.00 | $1.00 | 4,096 tokens | 估算o200k_base |
| Llama 2 7b chat hfanyscale/meta-llama/Llama-2-7b-chat-hf · anyscale | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 4,096 tokens | 估算o200k_base |
| Meta Llama 3 70B Instructanyscale/meta-llama/Meta-Llama-3-70B-Instruct · anyscale | LiteLLM ↗2026-10-25 UTC | $1.00 | $1.00 | 8,192 tokens | 估算o200k_base |
| Meta Llama 3 8B Instructanyscale/meta-llama/Meta-Llama-3-8B-Instruct · anyscale | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 8,192 tokens | 估算o200k_base |
| Mistral 7B Instruct v0.1anyscale/mistralai/Mistral-7B-Instruct-v0.1 · anyscale | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 16,384 tokens | 估算o200k_base |
| Mixtral 8x22B Instruct v0.1anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1 · anyscale | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 65,536 tokens | 估算o200k_base |
| Mixtral 8x7B Instruct v0.1anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1 · anyscale | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 16,384 tokens | 估算o200k_base |
| apac.amazon.nova 2 lite v1:0apac.amazon.nova-2-lite-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.396 | $3.311 | 1,000,000 tokens | 估算o200k_base |
| apac.amazon.nova 2 pro preview 20251202 v1:0apac.amazon.nova-2-pro-preview-20251202-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.375 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| apac.amazon.nova lite v1:0apac.amazon.nova-lite-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.063 | $0.252 | 300,000 tokens | 估算o200k_base |
| apac.amazon.nova micro v1:0apac.amazon.nova-micro-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.037 | $0.148 | 128,000 tokens | 估算o200k_base |
| apac.amazon.nova pro v1:0apac.amazon.nova-pro-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.84 | $3.36 | 300,000 tokens | 估算o200k_base |
| apac.anthropic.Claude fable 5apac.anthropic.claude-fable-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $11.00 | $55.00 | 1,000,000 tokens | 估算o200k_base |
| apac.anthropic.Claude haiku 4 5 20251001 v1:0apac.anthropic.claude-haiku-4-5-20251001-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.10 | $5.50 | 200,000 tokens | 估算o200k_base |
| apac.anthropic.Claude haiku 5 5apac.anthropic.claude-haiku-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.11 | $0.55 | 1,000,000 tokens | 估算o200k_base |
| apac.anthropic.Claude mythos previewapac.anthropic.claude-mythos-preview · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $27.50 | $137.50 | 1,000,000 tokens | 估算o200k_base |
| apac.anthropic.Claude opus 4 7apac.anthropic.claude-opus-4-7 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| apac.anthropic.Claude opus 4 8apac.anthropic.claude-opus-4-8 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| apac.anthropic.Claude opus 5apac.anthropic.claude-opus-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| apac.anthropic.Claude opus 5 5apac.anthropic.claude-opus-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $4.40 | $22.00 | 1,000,000 tokens | 估算o200k_base |
| apac.anthropic.Claude sonnet 4 20250514 v1:0apac.anthropic.claude-sonnet-4-20250514-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| apac.anthropic.Claude sonnet 4 6apac.anthropic.claude-sonnet-4-6 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 1,000,000 tokens | 估算o200k_base |
| apac.anthropic.Claude sonnet 5apac.anthropic.claude-sonnet-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| apac.anthropic.Claude sonnet 5 5apac.anthropic.claude-sonnet-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| au.anthropic.Claude fable 5au.anthropic.claude-fable-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $11.00 | $55.00 | 1,000,000 tokens | 估算o200k_base |
| au.anthropic.Claude haiku 4 5 20251001 v1:0au.anthropic.claude-haiku-4-5-20251001-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.10 | $5.50 | 200,000 tokens | 估算o200k_base |
| au.anthropic.Claude haiku 5 5au.anthropic.claude-haiku-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.11 | $0.55 | 1,000,000 tokens | 估算o200k_base |
| au.anthropic.Claude mythos previewau.anthropic.claude-mythos-preview · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $27.50 | $137.50 | 1,000,000 tokens | 估算o200k_base |
| au.anthropic.Claude opus 4 6 v1au.anthropic.claude-opus-4-6-v1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| au.anthropic.Claude opus 4 7au.anthropic.claude-opus-4-7 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| au.anthropic.Claude opus 4 8au.anthropic.claude-opus-4-8 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| au.anthropic.Claude opus 5au.anthropic.claude-opus-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| au.anthropic.Claude opus 5 5au.anthropic.claude-opus-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $4.40 | $22.00 | 1,000,000 tokens | 估算o200k_base |
| au.anthropic.Claude sonnet 4 5 20250929 v1:0au.anthropic.claude-sonnet-4-5-20250929-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 200,000 tokens | 估算o200k_base |
| au.anthropic.Claude sonnet 4 6au.anthropic.claude-sonnet-4-6 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 1,000,000 tokens | 估算o200k_base |
| au.anthropic.Claude sonnet 5au.anthropic.claude-sonnet-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| au.anthropic.Claude sonnet 5 5au.anthropic.claude-sonnet-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| Claude fable 5azure_ai/claude-fable-5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude fable 5 1azure_ai/claude-fable-5-1 · azure_ai | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude haiku 4 5azure_ai/claude-haiku-4-5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| Claude haiku 5 5azure_ai/claude-haiku-5-5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 5azure_ai/claude-opus-4-5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 4 6azure_ai/claude-opus-4-6 · azure_ai | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 7azure_ai/claude-opus-4-7 · azure_ai | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 8azure_ai/claude-opus-4-8 · azure_ai | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5azure_ai/claude-opus-5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5 5azure_ai/claude-opus-5-5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5 5 fastazure_ai/claude-opus-5-5-fast · azure_ai | LiteLLM ↗2026-10-25 UTC | $8.00 | $40.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 4 5azure_ai/claude-sonnet-4-5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 4 6azure_ai/claude-sonnet-4-6 · azure_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 5azure_ai/claude-sonnet-5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 5 5azure_ai/claude-sonnet-5-5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| Codestral 2501azure_ai/Codestral-2501 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.90 | 256,000 tokens | 估算o200k_base |
| cohere command aazure_ai/cohere-command-a · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 131,072 tokens | 估算o200k_base |
| Cohere command a plus 05 2026azure_ai/Cohere-command-a-plus-05-2026 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.80 | $3.20 | 128,000 tokens | 估算o200k_base |
| DeepSeek v3azure_ai/deepseek-v3 · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.14 | $4.56 | 128,000 tokens | 估算o200k_base |
| DeepSeek v3.2azure_ai/deepseek-v3.2 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.58 | $1.68 | 128,000 tokens | 估算o200k_base |
| DeepSeek v3.2 specialeazure_ai/deepseek-v3.2-speciale · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.58 | $1.68 | 128,000 tokens | 估算o200k_base |
| DeepSeek v4 flashazure_ai/deepseek-v4-flash · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.19 | $0.51 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek V4 Flash 0731azure_ai/DeepSeek-V4-Flash-0731 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.44 | $1.32 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 proazure_ai/deepseek-v4-pro · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.74 | $3.48 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4.1 flashazure_ai/deepseek-v4.1-flash · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| FW DeepSeek V3.2azure_ai/FW-DeepSeek-V3.2 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.62 | $1.85 | 163,840 tokens | 估算o200k_base |
| FW DeepSeek V4 Flashazure_ai/FW-DeepSeek-V4-Flash · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.31 | 1,000,000 tokens | 估算o200k_base |
| FW DeepSeek V4 Proazure_ai/FW-DeepSeek-V4-Pro · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.925 | $3.828 | 1,000,000 tokens | 估算o200k_base |
| FW DeepSeek V4.1 Flashazure_ai/FW-DeepSeek-V4.1-Flash · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.375 | $1.50 | 1,000,000 tokens | 估算o200k_base |
| FW GLM 5azure_ai/FW-GLM-5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.10 | $3.52 | 200,000 tokens | 估算o200k_base |
| FW GLM 5.1azure_ai/FW-GLM-5.1 · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.54 | $4.84 | 202,800 tokens | 估算o200k_base |
| FW GLM 5.2azure_ai/FW-GLM-5.2 · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.54 | $4.84 | 1,048,576 tokens | 估算o200k_base |
| FW GLM 5.2 Fastazure_ai/FW-GLM-5.2-Fast · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.31 | $7.26 | 1,048,576 tokens | 估算o200k_base |
| FW GLM 5.3azure_ai/FW-GLM-5.3 · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.75 | $5.50 | 1,048,576 tokens | 估算o200k_base |
| FW GLM 5.3 Flashazure_ai/FW-GLM-5.3-Flash · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.188 | $0.625 | 1,048,576 tokens | 估算o200k_base |
| FW GPT OSS 120Bazure_ai/FW-GPT-OSS-120B · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.165 | $0.66 | 131,072 tokens | 估算o200k_base |
| FW Inklingazure_ai/FW-Inkling · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.46 | 1,048,576 tokens | 估算o200k_base |
| FW Kimi K2.5azure_ai/FW-Kimi-K2.5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.66 | $3.30 | 262,144 tokens | 估算o200k_base |
| FW Kimi K2.6azure_ai/FW-Kimi-K2.6 · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.045 | $4.40 | 262,144 tokens | 估算o200k_base |
| FW Kimi K2.7 Codeazure_ai/FW-Kimi-K2.7-Code · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.05 | $4.40 | 262,144 tokens | 估算o200k_base |
| FW Kimi K3azure_ai/FW-Kimi-K3 · azure_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,048,576 tokens | 估算o200k_base |
| FW MiniMax M2.5azure_ai/FW-MiniMax-M2.5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.33 | $1.32 | 1,000,000 tokens | 估算o200k_base |
| FW MiniMax M3azure_ai/FW-MiniMax-M3 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.33 | $1.32 | 512,000 tokens | 估算o200k_base |
| FW Nemotron 3 Ultra NVFP4azure_ai/FW-Nemotron-3-Ultra-NVFP4 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.66 | $2.64 | 262,144 tokens | 估算o200k_base |
| FW Nemotron Lightning 3.5 30B A3Bazure_ai/FW-Nemotron-Lightning-3.5-30B-A3B · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.22 | 262,144 tokens | 估算o200k_base |
| GPT 5.4azure_ai/gpt-5.4 · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.50 | $15.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.4 2026 03 05azure_ai/gpt-5.4-2026-03-05 · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.50 | $15.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.4 miniazure_ai/gpt-5.4-mini · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.75 | $4.50 | 272,000 tokens | 估算o200k_base |
| GPT 5.4 mini 2026 03 17azure_ai/gpt-5.4-mini-2026-03-17 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.75 | $4.50 | 272,000 tokens | 估算o200k_base |
| GPT 5.4 nanoazure_ai/gpt-5.4-nano · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.25 | 272,000 tokens | 估算o200k_base |
| GPT 5.4 nano 2026 03 17azure_ai/gpt-5.4-nano-2026-03-17 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.25 | 272,000 tokens | 估算o200k_base |
| GPT 5.5azure_ai/gpt-5.5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.5 2026 04 23azure_ai/gpt-5.5-2026-04-23 · azure_ai | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.5 2026 04 24azure_ai/gpt-5.5-2026-04-24 · azure_ai | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 922,000 tokens | 估算o200k_base |
| GPT 6 astraazure_ai/gpt-6-astra · azure_ai | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 922,000 tokens | 估算o200k_base |
| GPT 6 lunaazure_ai/gpt-6-luna · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 922,000 tokens | 估算o200k_base |
| GPT 6 solazure_ai/gpt-6-sol · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 922,000 tokens | 估算o200k_base |
| GPT 6.1 solazure_ai/gpt-6.1-sol · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 922,000 tokens | 估算o200k_base |
| GPT chat latestazure_ai/gpt-chat-latest · azure_ai | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 128,000 tokens | 估算o200k_base |
| GPT oss 120bazure_ai/gpt-oss-120b · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| grok 4azure_ai/grok-4 · azure_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 262,000 tokens | 估算o200k_base |
| grok 4 1 fast non reasoningazure_ai/grok-4-1-fast-non-reasoning · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.50 | 128,000 tokens | 估算o200k_base |
| grok 4 1 fast reasoningazure_ai/grok-4-1-fast-reasoning · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.50 | 128,000 tokens | 估算o200k_base |
| grok 4 20 non reasoningazure_ai/grok-4-20-non-reasoning · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 262,000 tokens | 估算o200k_base |
| grok 4 20 reasoningazure_ai/grok-4-20-reasoning · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 262,000 tokens | 估算o200k_base |
| grok 4.3azure_ai/grok-4.3 · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 200,000 tokens | 估算o200k_base |
| grok 4.6azure_ai/grok-4.6 · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 200,000 tokens | 估算o200k_base |
| grok 4.7azure_ai/grok-4.7 · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 500,000 tokens | 估算o200k_base |
| grok code fast 1azure_ai/grok-code-fast-1 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.50 | 256,000 tokens | 估算o200k_base |
| jais 30b chatazure_ai/jais-30b-chat · azure_ai | LiteLLM ↗2026-10-25 UTC | $3,200.00 | $9,710.00 | 8,192 tokens | 估算o200k_base |
| jamba instructazure_ai/jamba-instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.70 | 70,000 tokens | 估算o200k_base |
| kimi k2 thinkingazure_ai/kimi-k2-thinking · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 262,144 tokens | 估算o200k_base |
| kimi k2.5azure_ai/kimi-k2.5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.00 | 262,144 tokens | 估算o200k_base |
| kimi k2.6azure_ai/kimi-k2.6 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| kimi k2.7 codeazure_ai/kimi-k2.7-code · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| Llama 3.3 70B Instructazure_ai/Llama-3.3-70B-Instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.71 | $0.71 | 128,000 tokens | 估算o200k_base |
| Llama 4 Maverick 17B 128E Instruct FP8azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.00 | 1,000,000 tokens | 估算o200k_base |
| Llama 4 Scout 17B 16E Instructazure_ai/Llama-4-Scout-17B-16E-Instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.78 | 10,000,000 tokens | 估算o200k_base |
| MAI Code 1.1 Flashazure_ai/MAI-Code-1.1-Flash · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.20 | 256,000 tokens | 估算o200k_base |
| MAI Cyber 1 Flashazure_ai/MAI-Cyber-1-Flash · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.50 | 256,000 tokens | 估算o200k_base |
| MAI DS R1azure_ai/MAI-DS-R1 · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.35 | $5.40 | 128,000 tokens | 估算o200k_base |
| MAI Thinking 1azure_ai/MAI-Thinking-1 · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 256,000 tokens | 估算o200k_base |
| Meta Llama 3 70B Instructazure_ai/Meta-Llama-3-70B-Instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.10 | $0.37 | 8,192 tokens | 估算o200k_base |
| Meta Llama 3.1 70B Instructazure_ai/Meta-Llama-3.1-70B-Instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.68 | $3.54 | 128,000 tokens | 估算o200k_base |
| ministral 3bazure_ai/ministral-3b · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.04 | 128,000 tokens | 估算o200k_base |
| Mistral largeazure_ai/mistral-large · azure_ai | LiteLLM ↗2026-10-25 UTC | $4.00 | $12.00 | 32,000 tokens | 估算o200k_base |
| Mistral large 2407azure_ai/mistral-large-2407 · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| Mistral large 3azure_ai/mistral-large-3 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 256,000 tokens | 估算o200k_base |
| Mistral large latestazure_ai/mistral-large-latest · azure_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| Mistral medium 2505azure_ai/mistral-medium-2505 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.40 | $2.00 | 131,072 tokens | 估算o200k_base |
| Mistral medium 3 5azure_ai/mistral-medium-3-5 · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 128,000 tokens | 估算o200k_base |
| Mistral nemoazure_ai/mistral-nemo · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 131,072 tokens | 估算o200k_base |
| Mistral smallazure_ai/mistral-small · azure_ai | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.00 | 32,000 tokens | 估算o200k_base |
| Mistral small 2503azure_ai/mistral-small-2503 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 128,000 tokens | 估算o200k_base |
| model routerazure_ai/model_router · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.00 | 200,000 tokens | 估算o200k_base |
| model routerazure_ai/model-router · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.00 | 200,000 tokens | 估算o200k_base |
| Phi 3 medium 128k instructazure_ai/Phi-3-medium-128k-instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.17 | $0.68 | 128,000 tokens | 估算o200k_base |
| Phi 3 medium 4k instructazure_ai/Phi-3-medium-4k-instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.17 | $0.68 | 4,096 tokens | 估算o200k_base |
| Phi 3 mini 128k instructazure_ai/Phi-3-mini-128k-instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.52 | 128,000 tokens | 估算o200k_base |
| Phi 3 mini 4k instructazure_ai/Phi-3-mini-4k-instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.52 | 4,096 tokens | 估算o200k_base |
| Phi 3 small 128k instructazure_ai/Phi-3-small-128k-instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| Phi 3 small 8k instructazure_ai/Phi-3-small-8k-instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 8,192 tokens | 估算o200k_base |
| Phi 3.5 mini instructazure_ai/Phi-3.5-mini-instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.52 | 128,000 tokens | 估算o200k_base |
| Phi 3.5 MoE instructazure_ai/Phi-3.5-MoE-instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.16 | $0.64 | 128,000 tokens | 估算o200k_base |
| Phi 3.5 vision instructazure_ai/Phi-3.5-vision-instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.52 | 128,000 tokens | 估算o200k_base |
| Phi 4azure_ai/Phi-4 · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.125 | $0.50 | 16,384 tokens | 估算o200k_base |
| Phi 4 mini instructazure_ai/Phi-4-mini-instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.075 | $0.30 | 131,072 tokens | 估算o200k_base |
| Phi 4 mini reasoningazure_ai/Phi-4-mini-reasoning · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.075 | $0.30 | 131,072 tokens | 估算o200k_base |
| Phi 4 multimodal instructazure_ai/Phi-4-multimodal-instruct · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.32 | 131,072 tokens | 估算o200k_base |
| Phi 4 reasoningazure_ai/Phi-4-reasoning · azure_ai | LiteLLM ↗2026-10-25 UTC | $0.125 | $0.50 | 32,768 tokens | 估算o200k_base |
| GPT 6.1 solazure/apac/gpt-6.1-sol · azure | LiteLLM ↗2026-10-25 UTC | $2.40 | $12.00 | 922,000 tokens | 估算o200k_base |
| chat latestazure/chat-latest · azure | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 272,000 tokens | 估算o200k_base |
| command r plusazure/command-r-plus · azure | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 128,000 tokens | 估算o200k_base |
| computer use previewazure/computer-use-preview · azure | LiteLLM ↗2026-10-25 UTC | $3.00 | $12.00 | 8,192 tokens | 估算o200k_base |
| GPT 4oazure/eu/gpt-4o · azure | LiteLLM ↗2026-10-25 UTC | $2.75 | $11.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 05 13azure/eu/gpt-4o-2024-05-13 · azure | LiteLLM ↗2026-10-25 UTC | $5.50 | $16.50 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 08 06azure/eu/gpt-4o-2024-08-06 · azure | LiteLLM ↗2026-10-25 UTC | $2.75 | $11.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 11 20azure/eu/gpt-4o-2024-11-20 · azure | LiteLLM ↗2026-10-25 UTC | $2.75 | $11.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o miniazure/eu/gpt-4o-mini · azure | LiteLLM ↗2026-10-25 UTC | $0.165 | $0.66 | 128,000 tokens | 估算o200k_base |
| GPT 4o mini 2024 07 18azure/eu/gpt-4o-mini-2024-07-18 · azure | LiteLLM ↗2026-10-25 UTC | $0.165 | $0.66 | 128,000 tokens | 估算o200k_base |
| GPT 5 2025 08 07azure/eu/gpt-5-2025-08-07 · azure | LiteLLM ↗2026-10-25 UTC | $1.375 | $11.00 | 272,000 tokens | 估算o200k_base |
| GPT 5 mini 2025 08 07azure/eu/gpt-5-mini-2025-08-07 · azure | LiteLLM ↗2026-10-25 UTC | $0.275 | $2.20 | 272,000 tokens | 估算o200k_base |
| GPT 5 nano 2025 08 07azure/eu/gpt-5-nano-2025-08-07 · azure | LiteLLM ↗2026-10-25 UTC | $0.055 | $0.44 | 272,000 tokens | 估算o200k_base |
| GPT 5.1azure/eu/gpt-5.1 · azure | LiteLLM ↗2026-10-25 UTC | $1.375 | $11.00 | 272,000 tokens | 估算o200k_base |
| GPT 5.1 chatazure/eu/gpt-5.1-chat · azure | LiteLLM ↗2026-10-25 UTC | $1.375 | $11.00 | 111,616 tokens | 估算o200k_base |
| GPT 5.2 chatazure/eu/gpt-5.2-chat · azure | LiteLLM ↗2026-10-25 UTC | $1.925 | $15.40 | 111,616 tokens | 估算o200k_base |
| GPT 5.3 chatazure/eu/gpt-5.3-chat · azure | LiteLLM ↗2026-10-25 UTC | $1.925 | $15.40 | 111,616 tokens | 估算o200k_base |
| GPT 5.4azure/eu/gpt-5.4 · azure | LiteLLM ↗2026-10-25 UTC | $2.75 | $16.50 | 922,000 tokens | 估算o200k_base |
| GPT 5.4 2026 03 05azure/eu/gpt-5.4-2026-03-05 · azure | LiteLLM ↗2026-10-25 UTC | $2.75 | $16.50 | 922,000 tokens | 估算o200k_base |
| GPT 5.5azure/eu/gpt-5.5 · azure | LiteLLM ↗2026-10-25 UTC | $5.50 | $33.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.5 2026 04 23azure/eu/gpt-5.5-2026-04-23 · azure | LiteLLM ↗2026-10-25 UTC | $5.50 | $33.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.5 2026 04 24azure/eu/gpt-5.5-2026-04-24 · azure | LiteLLM ↗2026-10-25 UTC | $5.50 | $33.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6azure/eu/gpt-5.6 · azure | LiteLLM ↗2026-10-25 UTC | $4.40 | $22.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 lunaazure/eu/gpt-5.6-luna · azure | LiteLLM ↗2026-10-25 UTC | $0.22 | $1.32 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 solazure/eu/gpt-5.6-sol · azure | LiteLLM ↗2026-10-25 UTC | $4.40 | $22.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 terraazure/eu/gpt-5.6-terra · azure | LiteLLM ↗2026-10-25 UTC | $2.20 | $13.20 | 922,000 tokens | 估算o200k_base |
| GPT 6 astraazure/eu/gpt-6-astra · azure | LiteLLM ↗2026-10-25 UTC | $12.00 | $60.00 | 922,000 tokens | 估算o200k_base |
| GPT 6 lunaazure/eu/gpt-6-luna · azure | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.60 | 922,000 tokens | 估算o200k_base |
| GPT 6 solazure/eu/gpt-6-sol · azure | LiteLLM ↗2026-10-25 UTC | $2.40 | $12.00 | 922,000 tokens | 估算o200k_base |
| GPT 6.1 solazure/eu/gpt-6.1-sol · azure | LiteLLM ↗2026-10-25 UTC | $2.40 | $12.00 | 922,000 tokens | 估算o200k_base |
| o1azure/eu/o1 · azure | LiteLLM ↗2026-10-25 UTC | $16.50 | $66.00 | 200,000 tokens | 估算o200k_base |
| o1 2024 12 17azure/eu/o1-2024-12-17 · azure | LiteLLM ↗2026-10-25 UTC | $16.50 | $66.00 | 200,000 tokens | 估算o200k_base |
| o1 mini 2024 09 12azure/eu/o1-mini-2024-09-12 · azure | LiteLLM ↗2026-10-25 UTC | $1.21 | $4.84 | 128,000 tokens | 估算o200k_base |
| o1 previewazure/eu/o1-preview · azure | LiteLLM ↗2026-10-25 UTC | $16.50 | $66.00 | 128,000 tokens | 估算o200k_base |
| o3azure/eu/o3 · azure | LiteLLM ↗2026-10-25 UTC | $2.20 | $8.80 | 200,000 tokens | 估算o200k_base |
| o3 2025 04 16azure/eu/o3-2025-04-16 · azure | LiteLLM ↗2026-10-25 UTC | $2.20 | $8.80 | 200,000 tokens | 估算o200k_base |
| o3 miniazure/eu/o3-mini · azure | LiteLLM ↗2026-10-25 UTC | $1.21 | $4.84 | 200,000 tokens | 估算o200k_base |
| o3 mini 2025 01 31azure/eu/o3-mini-2025-01-31 · azure | LiteLLM ↗2026-10-25 UTC | $1.21 | $4.84 | 200,000 tokens | 估算o200k_base |
| o4 miniazure/eu/o4-mini · azure | LiteLLM ↗2026-10-25 UTC | $1.21 | $4.84 | 200,000 tokens | 估算o200k_base |
| o4 mini 2025 04 16azure/eu/o4-mini-2025-04-16 · azure | LiteLLM ↗2026-10-25 UTC | $1.21 | $4.84 | 200,000 tokens | 估算o200k_base |
| GPT 4o 2024 08 06azure/global-standard/gpt-4o-2024-08-06 · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 11 20azure/global-standard/gpt-4o-2024-11-20 · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o miniazure/global-standard/gpt-4o-mini · azure | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 08 06azure/global/gpt-4o-2024-08-06 · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 11 20azure/global/gpt-4o-2024-11-20 · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 5.1azure/global/gpt-5.1 · azure | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 272,000 tokens | 估算o200k_base |
| GPT 3.5 turboazure/gpt-3.5-turbo · azure | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 4,097 tokens | 估算o200k_base |
| GPT 35 turboazure/gpt-35-turbo · azure | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 4,097 tokens | 估算o200k_base |
| GPT 35 turbo 16kazure/gpt-35-turbo-16k · azure | LiteLLM ↗2026-10-25 UTC | $3.00 | $4.00 | 16,385 tokens | 估算o200k_base |
| GPT 35 turbo 16k 0613azure/gpt-35-turbo-16k-0613 · azure | LiteLLM ↗2026-10-25 UTC | $3.00 | $4.00 | 16,385 tokens | 估算o200k_base |
| GPT 4azure/gpt-4 · azure | LiteLLM ↗2026-10-25 UTC | $30.00 | $60.00 | 8,192 tokens | 估算o200k_base |
| GPT 4 0125 previewazure/gpt-4-0125-preview · azure | LiteLLM ↗2026-10-25 UTC | $10.00 | $30.00 | 128,000 tokens | 估算o200k_base |
| GPT 4 0613azure/gpt-4-0613 · azure | LiteLLM ↗2026-10-25 UTC | $30.00 | $60.00 | 8,192 tokens | 估算o200k_base |
| GPT 4 1106 previewazure/gpt-4-1106-preview · azure | LiteLLM ↗2026-10-25 UTC | $10.00 | $30.00 | 128,000 tokens | 估算o200k_base |
| GPT 4 32kazure/gpt-4-32k · azure | LiteLLM ↗2026-10-25 UTC | $60.00 | $120.00 | 32,768 tokens | 估算o200k_base |
| GPT 4 32k 0613azure/gpt-4-32k-0613 · azure | LiteLLM ↗2026-10-25 UTC | $60.00 | $120.00 | 32,768 tokens | 估算o200k_base |
| GPT 4 turboazure/gpt-4-turbo · azure | LiteLLM ↗2026-10-25 UTC | $11.00 | $33.00 | 128,000 tokens | 估算o200k_base |
| GPT 4 turbo 2024 04 09azure/gpt-4-turbo-2024-04-09 · azure | LiteLLM ↗2026-10-25 UTC | $11.00 | $33.00 | 128,000 tokens | 估算o200k_base |
| GPT 4 turbo vision previewazure/gpt-4-turbo-vision-preview · azure | LiteLLM ↗2026-10-25 UTC | $11.00 | $33.00 | 128,000 tokens | 估算o200k_base |
| GPT 4.1azure/gpt-4.1 · azure | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 1,047,576 tokens | 估算o200k_base |
| GPT 4.1 2025 04 14azure/gpt-4.1-2025-04-14 · azure | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 1,047,576 tokens | 估算o200k_base |
| GPT 4.1 miniazure/gpt-4.1-mini · azure | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 1,047,576 tokens | 估算o200k_base |
| GPT 4.1 mini 2025 04 14azure/gpt-4.1-mini-2025-04-14 · azure | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 1,047,576 tokens | 估算o200k_base |
| GPT 4.1 nanoazure/gpt-4.1-nano · azure | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 1,047,576 tokens | 估算o200k_base |
| GPT 4.1 nano 2025 04 14azure/gpt-4.1-nano-2025-04-14 · azure | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 1,047,576 tokens | 估算o200k_base |
| GPT 4.5 previewazure/gpt-4.5-preview · azure | LiteLLM ↗2026-10-25 UTC | $75.00 | $150.00 | 128,000 tokens | 估算o200k_base |
| GPT 4oazure/gpt-4o · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 05 13azure/gpt-4o-2024-05-13 · azure | LiteLLM ↗2026-10-25 UTC | $5.00 | $15.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 08 06azure/gpt-4o-2024-08-06 · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 11 20azure/gpt-4o-2024-11-20 · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o audio preview 2024 12 17azure/gpt-4o-audio-preview-2024-12-17 · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o miniazure/gpt-4o-mini · azure | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| GPT 4o mini 2024 07 18azure/gpt-4o-mini-2024-07-18 · azure | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| GPT 4o mini audio preview 2024 12 17azure/gpt-4o-mini-audio-preview-2024-12-17 · azure | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| GPT 5azure/gpt-5 · azure | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 272,000 tokens | 估算o200k_base |
| GPT 5 2025 08 07azure/gpt-5-2025-08-07 · azure | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 272,000 tokens | 估算o200k_base |
| GPT 5 chatazure/gpt-5-chat · azure | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 5 miniazure/gpt-5-mini · azure | LiteLLM ↗2026-10-25 UTC | $0.25 | $2.00 | 272,000 tokens | 估算o200k_base |
| GPT 5 mini 2025 08 07azure/gpt-5-mini-2025-08-07 · azure | LiteLLM ↗2026-10-25 UTC | $0.25 | $2.00 | 272,000 tokens | 估算o200k_base |
| GPT 5 nanoazure/gpt-5-nano · azure | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.40 | 272,000 tokens | 估算o200k_base |
| GPT 5 nano 2025 08 07azure/gpt-5-nano-2025-08-07 · azure | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.40 | 272,000 tokens | 估算o200k_base |
| GPT 5.1azure/gpt-5.1 · azure | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 272,000 tokens | 估算o200k_base |
| GPT 5.1 2025 11 13azure/gpt-5.1-2025-11-13 · azure | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 272,000 tokens | 估算o200k_base |
| GPT 5.1 chatazure/gpt-5.1-chat · azure | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 111,616 tokens | 估算o200k_base |
| GPT 5.2azure/gpt-5.2 · azure | LiteLLM ↗2026-10-25 UTC | $1.75 | $14.00 | 272,000 tokens | 估算o200k_base |
| GPT 5.2 2025 12 11azure/gpt-5.2-2025-12-11 · azure | LiteLLM ↗2026-10-25 UTC | $1.75 | $14.00 | 272,000 tokens | 估算o200k_base |
| GPT 5.2 chatazure/gpt-5.2-chat · azure | LiteLLM ↗2026-10-25 UTC | $1.75 | $14.00 | 111,616 tokens | 估算o200k_base |
| GPT 5.3 chatazure/gpt-5.3-chat · azure | LiteLLM ↗2026-10-25 UTC | $1.75 | $14.00 | 111,616 tokens | 估算o200k_base |
| GPT 5.4azure/gpt-5.4 · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $15.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.4 2026 03 05azure/gpt-5.4-2026-03-05 · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $15.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.4 miniazure/gpt-5.4-mini · azure | LiteLLM ↗2026-10-25 UTC | $0.75 | $4.50 | 272,000 tokens | 估算o200k_base |
| GPT 5.4 mini 2026 03 17azure/gpt-5.4-mini-2026-03-17 · azure | LiteLLM ↗2026-10-25 UTC | $0.75 | $4.50 | 272,000 tokens | 估算o200k_base |
| GPT 5.4 nanoazure/gpt-5.4-nano · azure | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.25 | 272,000 tokens | 估算o200k_base |
| GPT 5.4 nano 2026 03 17azure/gpt-5.4-nano-2026-03-17 · azure | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.25 | 272,000 tokens | 估算o200k_base |
| GPT 5.5azure/gpt-5.5 · azure | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.5 2026 04 23azure/gpt-5.5-2026-04-23 · azure | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.5 2026 04 24azure/gpt-5.5-2026-04-24 · azure | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6azure/gpt-5.6 · azure | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 lunaazure/gpt-5.6-luna · azure | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.20 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 luna 2026 07 09azure/gpt-5.6-luna-2026-07-09 · azure | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.20 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 solazure/gpt-5.6-sol · azure | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 sol 2026 07 09azure/gpt-5.6-sol-2026-07-09 · azure | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 terraazure/gpt-5.6-terra · azure | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 terra 2026 07 09azure/gpt-5.6-terra-2026-07-09 · azure | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 922,000 tokens | 估算o200k_base |
| GPT 6 astraazure/gpt-6-astra · azure | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 922,000 tokens | 估算o200k_base |
| GPT 6 astra 2026 09 03azure/gpt-6-astra-2026-09-03 · azure | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 922,000 tokens | 估算o200k_base |
| GPT 6 lunaazure/gpt-6-luna · azure | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 922,000 tokens | 估算o200k_base |
| GPT 6 luna 2026 09 22azure/gpt-6-luna-2026-09-22 · azure | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 922,000 tokens | 估算o200k_base |
| GPT 6 solazure/gpt-6-sol · azure | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 922,000 tokens | 估算o200k_base |
| GPT 6 sol 2026 09 22azure/gpt-6-sol-2026-09-22 · azure | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 922,000 tokens | 估算o200k_base |
| GPT 6.1 solazure/gpt-6.1-sol · azure | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 922,000 tokens | 估算o200k_base |
| GPT 6.1 sol 2026 09 29azure/gpt-6.1-sol-2026-09-29 · azure | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 922,000 tokens | 估算o200k_base |
| GPT audioazure/gpt-audio · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT audio 1.5azure/gpt-audio-1.5 · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT audio 1.5 2026 02 23azure/gpt-audio-1.5-2026-02-23 · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT audio 2025 08 28azure/gpt-audio-2025-08-28 · azure | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT audio miniazure/gpt-audio-mini · azure | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 128,000 tokens | 估算o200k_base |
| GPT audio mini 2025 10 06azure/gpt-audio-mini-2025-10-06 · azure | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 128,000 tokens | 估算o200k_base |
| GPT chat latestazure/gpt-chat-latest · azure | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 128,000 tokens | 估算o200k_base |
| Mistral large 2402azure/mistral-large-2402 · azure | LiteLLM ↗2026-10-25 UTC | $8.00 | $24.00 | 32,000 tokens | 估算o200k_base |
| Mistral large latestazure/mistral-large-latest · azure | LiteLLM ↗2026-10-25 UTC | $8.00 | $24.00 | 32,000 tokens | 估算o200k_base |
| model routerazure/model-router · azure | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.00 | 200,000 tokens | 估算o200k_base |
| o1azure/o1 · azure | LiteLLM ↗2026-10-25 UTC | $15.00 | $60.00 | 200,000 tokens | 估算o200k_base |
| o1 2024 12 17azure/o1-2024-12-17 · azure | LiteLLM ↗2026-10-25 UTC | $15.00 | $60.00 | 200,000 tokens | 估算o200k_base |
| o1 miniazure/o1-mini · azure | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 128,000 tokens | 估算o200k_base |
| o1 mini 2024 09 12azure/o1-mini-2024-09-12 · azure | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 128,000 tokens | 估算o200k_base |
| o3azure/o3 · azure | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 200,000 tokens | 估算o200k_base |
| o3 2025 04 16azure/o3-2025-04-16 · azure | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 200,000 tokens | 估算o200k_base |
| o3 miniazure/o3-mini · azure | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 200,000 tokens | 估算o200k_base |
| o3 mini 2025 01 31azure/o3-mini-2025-01-31 · azure | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 200,000 tokens | 估算o200k_base |
| o4 miniazure/o4-mini · azure | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 200,000 tokens | 估算o200k_base |
| o4 mini 2025 04 16azure/o4-mini-2025-04-16 · azure | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 200,000 tokens | 估算o200k_base |
| GPT 5.1azure/us-gov/gpt-5.1 · azure | LiteLLM ↗2026-10-25 UTC | $1.71875 | $13.75 | 272,000 tokens | 估算o200k_base |
| o3 miniazure/us-gov/o3-mini · azure | LiteLLM ↗2026-10-25 UTC | $1.513 | $6.05 | 200,000 tokens | 估算o200k_base |
| GPT 4.1 2025 04 14azure/us/gpt-4.1-2025-04-14 · azure | LiteLLM ↗2026-10-25 UTC | $2.20 | $8.80 | 1,047,576 tokens | 估算o200k_base |
| GPT 4.1 mini 2025 04 14azure/us/gpt-4.1-mini-2025-04-14 · azure | LiteLLM ↗2026-10-25 UTC | $0.44 | $1.76 | 1,047,576 tokens | 估算o200k_base |
| GPT 4.1 nano 2025 04 14azure/us/gpt-4.1-nano-2025-04-14 · azure | LiteLLM ↗2026-10-25 UTC | $0.11 | $0.44 | 1,047,576 tokens | 估算o200k_base |
| GPT 4oazure/us/gpt-4o · azure | LiteLLM ↗2026-10-25 UTC | $2.75 | $11.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 05 13azure/us/gpt-4o-2024-05-13 · azure | LiteLLM ↗2026-10-25 UTC | $5.50 | $16.50 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 08 06azure/us/gpt-4o-2024-08-06 · azure | LiteLLM ↗2026-10-25 UTC | $2.75 | $11.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 11 20azure/us/gpt-4o-2024-11-20 · azure | LiteLLM ↗2026-10-25 UTC | $2.75 | $11.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o miniazure/us/gpt-4o-mini · azure | LiteLLM ↗2026-10-25 UTC | $0.165 | $0.66 | 128,000 tokens | 估算o200k_base |
| GPT 4o mini 2024 07 18azure/us/gpt-4o-mini-2024-07-18 · azure | LiteLLM ↗2026-10-25 UTC | $0.165 | $0.66 | 128,000 tokens | 估算o200k_base |
| GPT 5 2025 08 07azure/us/gpt-5-2025-08-07 · azure | LiteLLM ↗2026-10-25 UTC | $1.375 | $11.00 | 272,000 tokens | 估算o200k_base |
| GPT 5 mini 2025 08 07azure/us/gpt-5-mini-2025-08-07 · azure | LiteLLM ↗2026-10-25 UTC | $0.275 | $2.20 | 272,000 tokens | 估算o200k_base |
| GPT 5 nano 2025 08 07azure/us/gpt-5-nano-2025-08-07 · azure | LiteLLM ↗2026-10-25 UTC | $0.055 | $0.44 | 272,000 tokens | 估算o200k_base |
| GPT 5.1azure/us/gpt-5.1 · azure | LiteLLM ↗2026-10-25 UTC | $1.375 | $11.00 | 272,000 tokens | 估算o200k_base |
| GPT 5.1 chatazure/us/gpt-5.1-chat · azure | LiteLLM ↗2026-10-25 UTC | $1.375 | $11.00 | 111,616 tokens | 估算o200k_base |
| GPT 5.2 chatazure/us/gpt-5.2-chat · azure | LiteLLM ↗2026-10-25 UTC | $1.925 | $15.40 | 111,616 tokens | 估算o200k_base |
| GPT 5.3 chatazure/us/gpt-5.3-chat · azure | LiteLLM ↗2026-10-25 UTC | $1.925 | $15.40 | 111,616 tokens | 估算o200k_base |
| GPT 5.4azure/us/gpt-5.4 · azure | LiteLLM ↗2026-10-25 UTC | $2.75 | $16.50 | 922,000 tokens | 估算o200k_base |
| GPT 5.4 2026 03 05azure/us/gpt-5.4-2026-03-05 · azure | LiteLLM ↗2026-10-25 UTC | $2.75 | $16.50 | 922,000 tokens | 估算o200k_base |
| GPT 5.5azure/us/gpt-5.5 · azure | LiteLLM ↗2026-10-25 UTC | $5.50 | $33.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.5 2026 04 23azure/us/gpt-5.5-2026-04-23 · azure | LiteLLM ↗2026-10-25 UTC | $5.50 | $33.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.5 2026 04 24azure/us/gpt-5.5-2026-04-24 · azure | LiteLLM ↗2026-10-25 UTC | $5.50 | $33.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6azure/us/gpt-5.6 · azure | LiteLLM ↗2026-10-25 UTC | $4.40 | $22.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 lunaazure/us/gpt-5.6-luna · azure | LiteLLM ↗2026-10-25 UTC | $0.22 | $1.32 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 solazure/us/gpt-5.6-sol · azure | LiteLLM ↗2026-10-25 UTC | $4.40 | $22.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 terraazure/us/gpt-5.6-terra · azure | LiteLLM ↗2026-10-25 UTC | $2.20 | $13.20 | 922,000 tokens | 估算o200k_base |
| GPT 6 astraazure/us/gpt-6-astra · azure | LiteLLM ↗2026-10-25 UTC | $11.00 | $55.00 | 922,000 tokens | 估算o200k_base |
| GPT 6 lunaazure/us/gpt-6-luna · azure | LiteLLM ↗2026-10-25 UTC | $0.11 | $0.55 | 922,000 tokens | 估算o200k_base |
| GPT 6 solazure/us/gpt-6-sol · azure | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 922,000 tokens | 估算o200k_base |
| GPT 6.1 solazure/us/gpt-6.1-sol · azure | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 922,000 tokens | 估算o200k_base |
| GPT chat latestazure/us/gpt-chat-latest · azure | LiteLLM ↗2026-10-25 UTC | $5.50 | $33.00 | 128,000 tokens | 估算o200k_base |
| o1azure/us/o1 · azure | LiteLLM ↗2026-10-25 UTC | $16.50 | $66.00 | 200,000 tokens | 估算o200k_base |
| o1 2024 12 17azure/us/o1-2024-12-17 · azure | LiteLLM ↗2026-10-25 UTC | $16.50 | $66.00 | 200,000 tokens | 估算o200k_base |
| o1 mini 2024 09 12azure/us/o1-mini-2024-09-12 · azure | LiteLLM ↗2026-10-25 UTC | $1.21 | $4.84 | 128,000 tokens | 估算o200k_base |
| o1 previewazure/us/o1-preview · azure | LiteLLM ↗2026-10-25 UTC | $16.50 | $66.00 | 128,000 tokens | 估算o200k_base |
| o3azure/us/o3 · azure | LiteLLM ↗2026-10-25 UTC | $2.20 | $8.80 | 200,000 tokens | 估算o200k_base |
| o3 2025 04 16azure/us/o3-2025-04-16 · azure | LiteLLM ↗2026-10-25 UTC | $2.20 | $8.80 | 200,000 tokens | 估算o200k_base |
| o3 miniazure/us/o3-mini · azure | LiteLLM ↗2026-10-25 UTC | $1.21 | $4.84 | 200,000 tokens | 估算o200k_base |
| o3 mini 2025 01 31azure/us/o3-mini-2025-01-31 · azure | LiteLLM ↗2026-10-25 UTC | $1.21 | $4.84 | 200,000 tokens | 估算o200k_base |
| o4 miniazure/us/o4-mini · azure | LiteLLM ↗2026-10-25 UTC | $1.21 | $4.84 | 200,000 tokens | 估算o200k_base |
| o4 mini 2025 04 16azure/us/o4-mini-2025-04-16 · azure | LiteLLM ↗2026-10-25 UTC | $1.21 | $4.84 | 200,000 tokens | 估算o200k_base |
| DeepSeek V4 Flash 0731baseten/deepseek-ai/DeepSeek-V4-Flash-0731 · baseten | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.26 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Probaseten/deepseek-ai/DeepSeek-V4-Pro · baseten | LiteLLM ↗2026-10-25 UTC | $1.74 | $3.48 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Pro 0813baseten/deepseek-ai/DeepSeek-V4-Pro-0813 · baseten | LiteLLM ↗2026-10-25 UTC | $1.32 | $3.96 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4.1 Flashbaseten/deepseek-ai/DeepSeek-V4.1-Flash · baseten | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4.1 Flash 1017baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017 · baseten | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4.1 Flash 1017 Fastbaseten/deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast · baseten | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4.1 Flash Fastbaseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast · baseten | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 1,048,576 tokens | 估算o200k_base |
| muse spark openbaseten/meta-models/muse-spark-open · baseten | LiteLLM ↗2026-10-25 UTC | $1.25 | $4.25 | 1,048,576 tokens | 估算o200k_base |
| Kimi K2.6baseten/moonshotai/Kimi-K2.6 · baseten | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,000 tokens | 估算o200k_base |
| Kimi K2.7 Codebaseten/moonshotai/Kimi-K2.7-Code · baseten | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,000 tokens | 估算o200k_base |
| Kimi K3baseten/moonshotai/Kimi-K3 · baseten | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,048,576 tokens | 估算o200k_base |
| NVIDIA Nemotron 3 Ultra 550B A55Bbaseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B · baseten | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 202,800 tokens | 估算o200k_base |
| NVIDIA Nemotron 3.5 Super VL 120B A12Bbaseten/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B · baseten | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.50 | 1,048,576 tokens | 估算o200k_base |
| GPT oss 120bbaseten/openai/gpt-oss-120b · baseten | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 128,072 tokens | 估算o200k_base |
| Beam 1.0baseten/reflection/Beam-1.0 · baseten | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| inklingbaseten/thinkingmachines/inkling · baseten | LiteLLM ↗2026-10-25 UTC | $1.00 | $4.05 | 1,048,576 tokens | 估算o200k_base |
| inkling smallbaseten/thinkingmachines/inkling-small · baseten | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| GLM 4.7baseten/zai-org/GLM-4.7 · baseten | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 200,000 tokens | 估算o200k_base |
| GLM 5.2baseten/zai-org/GLM-5.2 · baseten | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| GLM 5.2 Fastbaseten/zai-org/GLM-5.2-Fast · baseten | LiteLLM ↗2026-10-25 UTC | $2.10 | $6.60 | 1,048,576 tokens | 估算o200k_base |
| GLM 5.3baseten/zai-org/GLM-5.3 · baseten | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| GLM 5.3 Fastbaseten/zai-org/GLM-5.3-Fast · baseten | LiteLLM ↗2026-10-25 UTC | $2.10 | $6.60 | 1,048,576 tokens | 估算o200k_base |
| GLM 5.3 Flashbaseten/zai-org/GLM-5.3-Flash · baseten | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,048,576 tokens | 估算o200k_base |
| anthropic.Claude haiku 4 5bedrock_mantle/anthropic.claude-haiku-4-5 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude haiku 5 5bedrock_mantle/anthropic.claude-haiku-5-5 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.11 | $0.55 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 5 5bedrock_mantle/anthropic.claude-opus-5-5 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $4.40 | $22.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 5 5bedrock_mantle/anthropic.claude-sonnet-5-5 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek.v3.1bedrock_mantle/deepseek.v3.1 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.58 | $1.68 | 128,000 tokens | 估算o200k_base |
| google.gemma 4 26b a4bbedrock_mantle/google.gemma-4-26b-a4b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.40 | 256,000 tokens | 估算o200k_base |
| google.gemma 4 31bbedrock_mantle/google.gemma-4-31b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.40 | 256,000 tokens | 估算o200k_base |
| google.gemma 4 e2bbedrock_mantle/google.gemma-4-e2b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.08 | 128,000 tokens | 估算o200k_base |
| moonshotai.kimi k2 thinkingbedrock_mantle/moonshotai.kimi-k2-thinking · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 256,000 tokens | 估算o200k_base |
| openai.GPT oss 120bbedrock_mantle/openai.gpt-oss-120b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| openai.GPT oss 20bbedrock_mantle/openai.gpt-oss-20b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.30 | 131,072 tokens | 估算o200k_base |
| openai.GPT oss safeguard 120bbedrock_mantle/openai.gpt-oss-safeguard-120b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| openai.GPT oss safeguard 20bbedrock_mantle/openai.gpt-oss-safeguard-20b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.20 | 131,072 tokens | 估算o200k_base |
| Qwen.qwen3 235b a22b 2507bedrock_mantle/qwen.qwen3-235b-a22b-2507 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.88 | 256,000 tokens | 估算o200k_base |
| Qwen.qwen3 32bbedrock_mantle/qwen.qwen3-32b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 32,000 tokens | 估算o200k_base |
| Qwen.qwen3 coder 30b a3b instructbedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 256,000 tokens | 估算o200k_base |
| Qwen.qwen3 coder 480b a35b instructbedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.45 | $1.80 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 next 80b a3b instructbedrock_mantle/qwen.qwen3-next-80b-a3b-instruct · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.14 | $1.20 | 256,000 tokens | 估算o200k_base |
| Qwen.qwen3 vl 235b a22b instructbedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.53 | $2.66 | 256,000 tokens | 估算o200k_base |
| openai.GPT oss 120bbedrock_mantle/us-gov-east-1/openai.gpt-oss-120b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.72 | 131,072 tokens | 估算o200k_base |
| openai.GPT oss 20bbedrock_mantle/us-gov-east-1/openai.gpt-oss-20b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.084 | $0.36 | 131,072 tokens | 估算o200k_base |
| xai.grok 4.6bedrock_mantle/us-gov-east-1/xai.grok-4.6 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $2.64 | $7.92 | 500,000 tokens | 估算o200k_base |
| anthropic.Claude haiku 5 5bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.60 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 5 5bedrock_mantle/us-gov-west-1/anthropic.claude-opus-5-5 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $4.80 | $24.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 5 5bedrock_mantle/us-gov-west-1/anthropic.claude-sonnet-5-5 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $2.40 | $12.00 | 1,000,000 tokens | 估算o200k_base |
| google.gemma 4 26b a4bbedrock_mantle/us-gov-west-1/google.gemma-4-26b-a4b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.156 | $0.48 | 256,000 tokens | 估算o200k_base |
| google.gemma 4 31bbedrock_mantle/us-gov-west-1/google.gemma-4-31b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.168 | $0.48 | 256,000 tokens | 估算o200k_base |
| google.gemma 4 e2bbedrock_mantle/us-gov-west-1/google.gemma-4-e2b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.048 | $0.096 | 128,000 tokens | 估算o200k_base |
| openai.GPT oss 120bbedrock_mantle/us-gov-west-1/openai.gpt-oss-120b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.72 | 131,072 tokens | 估算o200k_base |
| openai.GPT oss 20bbedrock_mantle/us-gov-west-1/openai.gpt-oss-20b · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $0.084 | $0.36 | 131,072 tokens | 估算o200k_base |
| xai.grok 4.3bedrock_mantle/us-gov-west-1/xai.grok-4.3 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $1.50 | $3.00 | 1,048,576 tokens | 估算o200k_base |
| xai.grok 4.6bedrock_mantle/us-gov-west-1/xai.grok-4.6 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $2.64 | $7.92 | 500,000 tokens | 估算o200k_base |
| xai.grok 4.3bedrock_mantle/xai.grok-4.3 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,048,576 tokens | 估算o200k_base |
| xai.grok 4.6bedrock_mantle/xai.grok-4.6 · bedrock_mantle | LiteLLM ↗2026-10-25 UTC | $2.20 | $6.60 | 500,000 tokens | 估算o200k_base |
| cohere.command light text v14bedrock/*/1-month-commitment/cohere.command-light-text-v14 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 4,096 tokens | 估算o200k_base |
| cohere.command text v14bedrock/*/1-month-commitment/cohere.command-text-v14 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 4,096 tokens | 估算o200k_base |
| cohere.command light text v14bedrock/*/6-month-commitment/cohere.command-light-text-v14 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 4,096 tokens | 估算o200k_base |
| cohere.command text v14bedrock/*/6-month-commitment/cohere.command-text-v14 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 4,096 tokens | 估算o200k_base |
| anthropic.Claude instant v1bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v1bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude instant v1bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v1bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude instant v1bedrock/ap-northeast-1/anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.23 | $7.55 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v1bedrock/ap-northeast-1/anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $8.00 | $24.00 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1bedrock/ap-northeast-1/anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | $8.00 | $24.00 | 100,000 tokens | 估算o200k_base |
| DeepSeek.v3.2bedrock/ap-northeast-1/deepseek.v3.2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.74 | $2.22 | 163,840 tokens | 估算o200k_base |
| minimax.minimax m2.1bedrock/ap-northeast-1/minimax.minimax-m2.1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/ap-northeast-1/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| moonshotai.kimi k2 thinkingbedrock/ap-northeast-1/moonshotai.kimi-k2-thinking · bedrock | LiteLLM ↗2026-10-25 UTC | $0.73 | $3.03 | 262,144 tokens | 估算o200k_base |
| moonshotai.kimi k2.5bedrock/ap-northeast-1/moonshotai.kimi-k2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.72 | $3.60 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 coder nextbedrock/ap-northeast-1/qwen.qwen3-coder-next · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.44 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 next 80b a3bbedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b · bedrock | LiteLLM ↗2026-10-25 UTC | $0.18 | $1.45 | 262,144 tokens | 估算o200k_base |
| DeepSeek.v3.2bedrock/ap-south-1/deepseek.v3.2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.74 | $2.22 | 163,840 tokens | 估算o200k_base |
| meta.llama3 70b instruct v1:0bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.18 | $4.20 | 8,192 tokens | 估算o200k_base |
| meta.llama3 8b instruct v1:0bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $0.72 | 8,192 tokens | 估算o200k_base |
| minimax.minimax m2.1bedrock/ap-south-1/minimax.minimax-m2.1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/ap-south-1/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| moonshotai.kimi k2 thinkingbedrock/ap-south-1/moonshotai.kimi-k2-thinking · bedrock | LiteLLM ↗2026-10-25 UTC | $0.71 | $2.94 | 262,144 tokens | 估算o200k_base |
| moonshotai.kimi k2.5bedrock/ap-south-1/moonshotai.kimi-k2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.72 | $3.60 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 coder nextbedrock/ap-south-1/qwen.qwen3-coder-next · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.44 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 next 80b a3bbedrock/ap-south-1/qwen.qwen3-next-80b-a3b · bedrock | LiteLLM ↗2026-10-25 UTC | $0.18 | $1.41 | 262,144 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/ap-southeast-2/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.31 | $1.24 | 196,000 tokens | 估算o200k_base |
| Qwen.qwen3 next 80b a3bbedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b · bedrock | LiteLLM ↗2026-10-25 UTC | $0.1545 | $1.236 | 262,144 tokens | 估算o200k_base |
| DeepSeek.v3.2bedrock/ap-southeast-3/deepseek.v3.2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.74 | $2.22 | 163,840 tokens | 估算o200k_base |
| minimax.minimax m2.1bedrock/ap-southeast-3/minimax.minimax-m2.1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/ap-southeast-3/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| moonshotai.kimi k2.5bedrock/ap-southeast-3/moonshotai.kimi-k2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.72 | $3.60 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 coder nextbedrock/ap-southeast-3/qwen.qwen3-coder-next · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.44 | 262,144 tokens | 估算o200k_base |
| meta.llama3 70b instruct v1:0bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.05 | $4.03 | 8,192 tokens | 估算o200k_base |
| meta.llama3 8b instruct v1:0bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.35 | $0.69 | 8,192 tokens | 估算o200k_base |
| Claude fable 5bedrock/claude_platform/claude-fable-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude fable 5 1bedrock/claude_platform/claude-fable-5-1 · bedrock | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude haiku 4 5bedrock/claude_platform/claude-haiku-4-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| Claude haiku 5 5bedrock/claude_platform/claude-haiku-5-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 5bedrock/claude_platform/claude-opus-4-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 4 6bedrock/claude_platform/claude-opus-4-6 · bedrock | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 7bedrock/claude_platform/claude-opus-4-7 · bedrock | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 8bedrock/claude_platform/claude-opus-4-8 · bedrock | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5bedrock/claude_platform/claude-opus-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5 5bedrock/claude_platform/claude-opus-5-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 4 5bedrock/claude_platform/claude-sonnet-4-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 4 6bedrock/claude_platform/claude-sonnet-4-6 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 5bedrock/claude_platform/claude-sonnet-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 5 5bedrock/claude_platform/claude-sonnet-5-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude instant v1bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v1bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude instant v1bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v1bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude instant v1bedrock/eu-central-1/anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.48 | $8.38 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v1bedrock/eu-central-1/anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $8.00 | $24.00 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1bedrock/eu-central-1/anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | $8.00 | $24.00 | 100,000 tokens | 估算o200k_base |
| minimax.minimax m2.1bedrock/eu-central-1/minimax.minimax-m2.1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/eu-central-1/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| Qwen.qwen3 coder nextbedrock/eu-central-1/qwen.qwen3-coder-next · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.44 | 262,144 tokens | 估算o200k_base |
| DeepSeek.v3.2bedrock/eu-north-1/deepseek.v3.2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.74 | $2.22 | 163,840 tokens | 估算o200k_base |
| minimax.minimax m2.1bedrock/eu-north-1/minimax.minimax-m2.1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/eu-north-1/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| moonshotai.kimi k2.5bedrock/eu-north-1/moonshotai.kimi-k2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.72 | $3.60 | 262,144 tokens | 估算o200k_base |
| minimax.minimax m2.1bedrock/eu-south-1/minimax.minimax-m2.1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/eu-south-1/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| Qwen.qwen3 coder nextbedrock/eu-south-1/qwen.qwen3-coder-next · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.44 | 262,144 tokens | 估算o200k_base |
| meta.llama3 70b instruct v1:0bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.86 | $3.78 | 8,192 tokens | 估算o200k_base |
| meta.llama3 8b instruct v1:0bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.32 | $0.65 | 8,192 tokens | 估算o200k_base |
| minimax.minimax m2.1bedrock/eu-west-1/minimax.minimax-m2.1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/eu-west-1/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| Qwen.qwen3 coder nextbedrock/eu-west-1/qwen.qwen3-coder-next · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.44 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 next 80b a3bbedrock/eu-west-1/qwen.qwen3-next-80b-a3b · bedrock | LiteLLM ↗2026-10-25 UTC | $0.18 | $1.41 | 262,144 tokens | 估算o200k_base |
| meta.llama3 70b instruct v1:0bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.45 | $4.55 | 8,192 tokens | 估算o200k_base |
| meta.llama3 8b instruct v1:0bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.39 | $0.78 | 8,192 tokens | 估算o200k_base |
| minimax.minimax m2.1bedrock/eu-west-2/minimax.minimax-m2.1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.47 | $1.86 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/eu-west-2/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.47 | $1.86 | 196,000 tokens | 估算o200k_base |
| nvidia.nemotron super 3 120bbedrock/eu-west-2/nvidia.nemotron-super-3-120b · bedrock | LiteLLM ↗2026-10-25 UTC | $0.23 | $1.01 | 256,000 tokens | 估算o200k_base |
| Qwen.qwen3 coder nextbedrock/eu-west-2/qwen.qwen3-coder-next · bedrock | LiteLLM ↗2026-10-25 UTC | $0.78 | $1.86 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 next 80b a3bbedrock/eu-west-2/qwen.qwen3-next-80b-a3b · bedrock | LiteLLM ↗2026-10-25 UTC | $0.23 | $1.86 | 262,144 tokens | 估算o200k_base |
| Mistral.Mistral 7b instruct v0:2bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.26 | 32,000 tokens | 估算o200k_base |
| Mistral.Mistral large 2402 v1:0bedrock/eu-west-3/mistral.mistral-large-2402-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $5.20 | $15.60 | 32,000 tokens | 估算o200k_base |
| Mistral.mixtral 8x7b instruct v0:1bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.59 | $0.91 | 32,000 tokens | 估算o200k_base |
| anthropic.Claude 3 5 sonnet 20240620 v1:0bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| moonshotai.kimi k2 thinkingbedrock/moonshotai.kimi-k2-thinking · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 262,144 tokens | 估算o200k_base |
| moonshotai.kimi k2.5bedrock/moonshotai.kimi-k2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.00 | 262,144 tokens | 估算o200k_base |
| DeepSeek.v3.2bedrock/sa-east-1/deepseek.v3.2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.74 | $2.22 | 163,840 tokens | 估算o200k_base |
| meta.llama3 70b instruct v1:0bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $4.45 | $5.88 | 8,192 tokens | 估算o200k_base |
| meta.llama3 8b instruct v1:0bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.01 | 8,192 tokens | 估算o200k_base |
| minimax.minimax m2.1bedrock/sa-east-1/minimax.minimax-m2.1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/sa-east-1/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.36 | $1.44 | 196,000 tokens | 估算o200k_base |
| moonshotai.kimi k2 thinkingbedrock/sa-east-1/moonshotai.kimi-k2-thinking · bedrock | LiteLLM ↗2026-10-25 UTC | $0.73 | $3.03 | 262,144 tokens | 估算o200k_base |
| moonshotai.kimi k2.5bedrock/sa-east-1/moonshotai.kimi-k2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.72 | $3.60 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 coder nextbedrock/sa-east-1/qwen.qwen3-coder-next · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.44 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 next 80b a3bbedrock/sa-east-1/qwen.qwen3-next-80b-a3b · bedrock | LiteLLM ↗2026-10-25 UTC | $0.18 | $1.45 | 262,144 tokens | 估算o200k_base |
| anthropic.Claude instant v1bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v1bedrock/us-east-1/1-month-commitment/anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude instant v1bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v1bedrock/us-east-1/6-month-commitment/anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude instant v1bedrock/us-east-1/anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.80 | $2.40 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v1bedrock/us-east-1/anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $8.00 | $24.00 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1bedrock/us-east-1/anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | $8.00 | $24.00 | 100,000 tokens | 估算o200k_base |
| DeepSeek.v3.2bedrock/us-east-1/deepseek.v3.2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.62 | $1.85 | 163,840 tokens | 估算o200k_base |
| meta.llama3 70b instruct v1:0bedrock/us-east-1/meta.llama3-70b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.65 | $3.50 | 8,192 tokens | 估算o200k_base |
| meta.llama3 8b instruct v1:0bedrock/us-east-1/meta.llama3-8b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.60 | 8,192 tokens | 估算o200k_base |
| minimax.minimax m2.1bedrock/us-east-1/minimax.minimax-m2.1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/us-east-1/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,000 tokens | 估算o200k_base |
| Mistral.Mistral 7b instruct v0:2bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.20 | 32,000 tokens | 估算o200k_base |
| Mistral.Mistral large 2402 v1:0bedrock/us-east-1/mistral.mistral-large-2402-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $4.00 | $12.00 | 32,000 tokens | 估算o200k_base |
| Mistral.mixtral 8x7b instruct v0:1bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.45 | $0.70 | 32,000 tokens | 估算o200k_base |
| moonshotai.kimi k2 thinkingbedrock/us-east-1/moonshotai.kimi-k2-thinking · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 262,144 tokens | 估算o200k_base |
| moonshotai.kimi k2.5bedrock/us-east-1/moonshotai.kimi-k2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.00 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 coder nextbedrock/us-east-1/qwen.qwen3-coder-next · bedrock | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.20 | 262,144 tokens | 估算o200k_base |
| zai.glm 5bedrock/us-east-1/zai.glm-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.20 | 200,000 tokens | 估算o200k_base |
| DeepSeek.v3.2bedrock/us-east-2/deepseek.v3.2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.62 | $1.85 | 163,840 tokens | 估算o200k_base |
| minimax.minimax m2.1bedrock/us-east-2/minimax.minimax-m2.1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/us-east-2/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,000 tokens | 估算o200k_base |
| moonshotai.kimi k2 thinkingbedrock/us-east-2/moonshotai.kimi-k2-thinking · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 262,144 tokens | 估算o200k_base |
| moonshotai.kimi k2.5bedrock/us-east-2/moonshotai.kimi-k2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.00 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 coder nextbedrock/us-east-2/qwen.qwen3-coder-next · bedrock | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.20 | 262,144 tokens | 估算o200k_base |
| amazon.nova pro v1:0bedrock/us-gov-east-1/amazon.nova-pro-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.96 | $3.84 | 300,000 tokens | 估算o200k_base |
| amazon.titan text express v1bedrock/us-gov-east-1/amazon.titan-text-express-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $1.30 | $1.70 | 42,000 tokens | 估算o200k_base |
| amazon.titan text lite v1bedrock/us-gov-east-1/amazon.titan-text-lite-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.40 | 42,000 tokens | 估算o200k_base |
| amazon.titan text premier v1:0bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 42,000 tokens | 估算o200k_base |
| anthropic.Claude fable 5 1bedrock/us-gov-east-1/anthropic.claude-fable-5-1 · bedrock | LiteLLM ↗2026-10-25 UTC | $12.00 | $60.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude haiku 4 5 20251001 v1:0bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $1.20 | $6.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude haiku 5 5bedrock/us-gov-east-1/anthropic.claude-haiku-5-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.60 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 4 8bedrock/us-gov-east-1/anthropic.claude-opus-4-8 · bedrock | LiteLLM ↗2026-10-25 UTC | $6.00 | $30.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 5bedrock/us-gov-east-1/anthropic.claude-opus-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $6.00 | $30.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 5 5bedrock/us-gov-east-1/anthropic.claude-opus-5-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $4.80 | $24.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 4 5 20250929 v1:0bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.60 | $18.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 5bedrock/us-gov-east-1/anthropic.claude-sonnet-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.40 | $12.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 5 5bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.40 | $12.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 4 5 20250929 v1:0bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.60 | $18.00 | 200,000 tokens | 估算o200k_base |
| meta.llama3 70b instruct v1:0bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.65 | $3.50 | 8,000 tokens | 估算o200k_base |
| meta.llama3 8b instruct v1:0bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.65 | 8,000 tokens | 估算o200k_base |
| nvidia.nemotron nano 12b v2bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.24 | $0.72 | 128,000 tokens | 估算o200k_base |
| nvidia.nemotron nano 3 30bbedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b · bedrock | LiteLLM ↗2026-10-25 UTC | $0.072 | $0.288 | 262,144 tokens | 估算o200k_base |
| nvidia.nemotron nano 9b v2bedrock/us-gov-east-1/nvidia.nemotron-nano-9b-v2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.072 | $0.276 | 128,000 tokens | 估算o200k_base |
| nvidia.nemotron super 3 120bbedrock/us-gov-east-1/nvidia.nemotron-super-3-120b · bedrock | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.78 | 256,000 tokens | 估算o200k_base |
| openai.GPT oss 120b 1:0bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.72 | 128,000 tokens | 估算o200k_base |
| openai.GPT oss 20b 1:0bedrock/us-gov-east-1/openai.gpt-oss-20b-1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.084 | $0.36 | 128,000 tokens | 估算o200k_base |
| amazon.nova lite v1:0bedrock/us-gov-west-1/amazon.nova-lite-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.072 | $0.288 | 300,000 tokens | 估算o200k_base |
| amazon.nova micro v1:0bedrock/us-gov-west-1/amazon.nova-micro-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.042 | $0.168 | 128,000 tokens | 估算o200k_base |
| amazon.nova pro v1:0bedrock/us-gov-west-1/amazon.nova-pro-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.96 | $3.84 | 300,000 tokens | 估算o200k_base |
| amazon.titan text express v1bedrock/us-gov-west-1/amazon.titan-text-express-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.80 | $1.60 | 42,000 tokens | 估算o200k_base |
| amazon.titan text lite v1bedrock/us-gov-west-1/amazon.titan-text-lite-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.40 | 42,000 tokens | 估算o200k_base |
| amazon.titan text premier v1:0bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 42,000 tokens | 估算o200k_base |
| anthropic.Claude fable 5 1bedrock/us-gov-west-1/anthropic.claude-fable-5-1 · bedrock | LiteLLM ↗2026-10-25 UTC | $12.00 | $60.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude haiku 4 5 20251001 v1:0bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $1.20 | $6.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude haiku 5 5bedrock/us-gov-west-1/anthropic.claude-haiku-5-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.60 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 4 8bedrock/us-gov-west-1/anthropic.claude-opus-4-8 · bedrock | LiteLLM ↗2026-10-25 UTC | $6.00 | $30.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 5bedrock/us-gov-west-1/anthropic.claude-opus-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $6.00 | $30.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude opus 5 5bedrock/us-gov-west-1/anthropic.claude-opus-5-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $4.80 | $24.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 4 5 20250929 v1:0bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.60 | $18.00 | 200,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 5bedrock/us-gov-west-1/anthropic.claude-sonnet-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.40 | $12.00 | 1,000,000 tokens | 估算o200k_base |
| anthropic.Claude sonnet 5 5bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.40 | $12.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 4 5 20250929 v1:0bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.60 | $18.00 | 200,000 tokens | 估算o200k_base |
| meta.llama3 70b instruct v1:0bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.65 | $3.50 | 8,000 tokens | 估算o200k_base |
| meta.llama3 8b instruct v1:0bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.60 | 8,000 tokens | 估算o200k_base |
| nvidia.nemotron nano 12b v2bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.24 | $0.72 | 128,000 tokens | 估算o200k_base |
| nvidia.nemotron nano 3 30bbedrock/us-gov-west-1/nvidia.nemotron-nano-3-30b · bedrock | LiteLLM ↗2026-10-25 UTC | $0.072 | $0.288 | 262,144 tokens | 估算o200k_base |
| nvidia.nemotron nano 9b v2bedrock/us-gov-west-1/nvidia.nemotron-nano-9b-v2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.072 | $0.276 | 128,000 tokens | 估算o200k_base |
| nvidia.nemotron super 3 120bbedrock/us-gov-west-1/nvidia.nemotron-super-3-120b · bedrock | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.78 | 256,000 tokens | 估算o200k_base |
| openai.GPT oss 120b 1:0bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.72 | 128,000 tokens | 估算o200k_base |
| openai.GPT oss 20b 1:0bedrock/us-gov-west-1/openai.gpt-oss-20b-1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.084 | $0.36 | 128,000 tokens | 估算o200k_base |
| meta.llama3 70b instruct v1:0bedrock/us-west-1/meta.llama3-70b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.65 | $3.50 | 8,192 tokens | 估算o200k_base |
| meta.llama3 8b instruct v1:0bedrock/us-west-1/meta.llama3-8b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.60 | 8,192 tokens | 估算o200k_base |
| anthropic.Claude instant v1bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v1bedrock/us-west-2/1-month-commitment/anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude instant v1bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v1bedrock/us-west-2/6-month-commitment/anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude instant v1bedrock/us-west-2/anthropic.claude-instant-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.80 | $2.40 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v1bedrock/us-west-2/anthropic.claude-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $8.00 | $24.00 | 100,000 tokens | 估算o200k_base |
| anthropic.Claude v2:1bedrock/us-west-2/anthropic.claude-v2:1 · bedrock | LiteLLM ↗2026-10-25 UTC | $8.00 | $24.00 | 100,000 tokens | 估算o200k_base |
| DeepSeek.v3.2bedrock/us-west-2/deepseek.v3.2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.62 | $1.85 | 163,840 tokens | 估算o200k_base |
| minimax.minimax m2.1bedrock/us-west-2/minimax.minimax-m2.1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5bedrock/us-west-2/minimax.minimax-m2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,000 tokens | 估算o200k_base |
| Mistral.Mistral 7b instruct v0:2bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.20 | 32,000 tokens | 估算o200k_base |
| Mistral.Mistral large 2402 v1:0bedrock/us-west-2/mistral.mistral-large-2402-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $4.00 | $12.00 | 32,000 tokens | 估算o200k_base |
| Mistral.mixtral 8x7b instruct v0:1bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.45 | $0.70 | 32,000 tokens | 估算o200k_base |
| moonshotai.kimi k2 thinkingbedrock/us-west-2/moonshotai.kimi-k2-thinking · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 262,144 tokens | 估算o200k_base |
| moonshotai.kimi k2.5bedrock/us-west-2/moonshotai.kimi-k2.5 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.00 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 coder nextbedrock/us-west-2/qwen.qwen3-coder-next · bedrock | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.20 | 262,144 tokens | 估算o200k_base |
| zai.glm 5bedrock/us-west-2/zai.glm-5 · bedrock | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.20 | 200,000 tokens | 估算o200k_base |
| us.anthropic.Claude 3 5 haiku 20241022 v1:0bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.80 | $4.00 | 200,000 tokens | 估算o200k_base |
| c4ai aya expanse 32bc4ai-aya-expanse-32b · cohere_chat | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 128,000 tokens | 估算o200k_base |
| gemma 4 31bcerebras/gemma-4-31b · cerebras | LiteLLM ↗2026-10-25 UTC | $0.99 | $1.49 | 131,072 tokens | 估算o200k_base |
| GPT oss 120bcerebras/gpt-oss-120b · cerebras | LiteLLM ↗2026-10-25 UTC | $0.35 | $0.75 | 131,072 tokens | 估算o200k_base |
| Llama 3.1 70bcerebras/llama-3.1-70b · cerebras | LiteLLM ↗2026-10-25 UTC | $0.60 | $0.60 | 128,000 tokens | 估算o200k_base |
| Llama 3.1 8bcerebras/llama-3.1-8b · cerebras | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 128,000 tokens | 估算o200k_base |
| Llama 3.3 70bcerebras/llama-3.3-70b · cerebras | LiteLLM ↗2026-10-25 UTC | $0.85 | $1.20 | 128,000 tokens | 估算o200k_base |
| llama3.1 70bcerebras/llama3.1-70b · cerebras | LiteLLM ↗2026-10-25 UTC | $0.60 | $0.60 | 128,000 tokens | 估算o200k_base |
| llama3.1 8bcerebras/llama3.1-8b · cerebras | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 128,000 tokens | 估算o200k_base |
| Qwen 3 32bcerebras/qwen-3-32b · cerebras | LiteLLM ↗2026-10-25 UTC | $0.40 | $0.80 | 128,000 tokens | 估算o200k_base |
| Qwen 3.8 27bcerebras/qwen-3.8-27b · cerebras | LiteLLM ↗2026-10-25 UTC | $0.99 | $1.49 | 65,536 tokens | 估算o200k_base |
| chat latestchat-latest · openai | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 400,000 tokens | 估算o200k_base |
| chatdolphinchatdolphin · nlp_cloud | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.50 | 16,384 tokens | 估算o200k_base |
| Claude fable 5claude-fable-5 · anthropic | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude fable 5 1claude-fable-5-1 · anthropic | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude Haiku 4.5claude-haiku-4-5 · Anthropic | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| Claude haiku 4 5 20251001claude-haiku-4-5-20251001 · anthropic | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| Claude haiku 5 5claude-haiku-5-5 · anthropic | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 1,000,000 tokens | 估算o200k_base |
| Claude mythos 5claude-mythos-5 · anthropic | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude mythos 5 1claude-mythos-5-1 · anthropic | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude mythos previewclaude-mythos-preview · anthropic | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 5claude-opus-4-5 · anthropic | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 4 5 20251101claude-opus-4-5-20251101 · anthropic | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 4 6claude-opus-4-6 · anthropic | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 6 20260205claude-opus-4-6-20260205 · anthropic | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 7claude-opus-4-7 · anthropic | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 7 20260416claude-opus-4-7-20260416 · anthropic | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 8claude-opus-4-8 · anthropic | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5claude-opus-5 · anthropic | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5 5claude-opus-5-5 · anthropic | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 1,000,000 tokens | 估算o200k_base |
| Claude Sonnet 4.5claude-sonnet-4-5 · Anthropic | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 4 5 20250929claude-sonnet-4-5-20250929 · anthropic | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 4 5 20250929 v1:0claude-sonnet-4-5-20250929-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 4 6claude-sonnet-4-6 · anthropic | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 5claude-sonnet-5 · anthropic | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 5 5claude-sonnet-5-5 · anthropic | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| gemma sea lion v4 27b itcloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.351 | $0.555 | 128,000 tokens | 估算o200k_base |
| DeepSeek r1 distill Qwen 32bcloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.497 | $4.881 | 80,000 tokens | 估算o200k_base |
| gemma 2b it loracloudflare/@cf/google/gemma-2b-it-lora · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 8,192 tokens | 估算o200k_base |
| gemma 4 26b a4b itcloudflare/@cf/google/gemma-4-26b-a4b-it · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 256,000 tokens | 估算o200k_base |
| gemma 7b it loracloudflare/@cf/google/gemma-7b-it-lora · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 3,500 tokens | 估算o200k_base |
| granite 4.0 h microcloudflare/@cf/ibm-granite/granite-4.0-h-micro · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.017 | $0.112 | 131,000 tokens | 估算o200k_base |
| Llama 2 7b chat hf loracloudflare/@cf/meta-llama/llama-2-7b-chat-hf-lora · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 8,192 tokens | 估算o200k_base |
| Llama 2 7b chat fp16cloudflare/@cf/meta/llama-2-7b-chat-fp16 · cloudflare | LiteLLM ↗2026-10-25 UTC | $1.923 | $1.923 | 3,072 tokens | 估算o200k_base |
| Llama 2 7b chat int8cloudflare/@cf/meta/llama-2-7b-chat-int8 · cloudflare | LiteLLM ↗2026-10-25 UTC | $1.923 | $1.923 | 2,048 tokens | 估算o200k_base |
| Llama 3.1 8b instruct fp8cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8 · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.152 | $0.287 | 32,000 tokens | 估算o200k_base |
| Llama 3.2 11b vision instructcloudflare/@cf/meta/llama-3.2-11b-vision-instruct · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.0485 | $0.676 | 128,000 tokens | 估算o200k_base |
| Llama 3.2 1b instructcloudflare/@cf/meta/llama-3.2-1b-instruct · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.027 | $0.201 | 60,000 tokens | 估算o200k_base |
| Llama 3.2 3b instructcloudflare/@cf/meta/llama-3.2-3b-instruct · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.0509 | $0.335 | 80,000 tokens | 估算o200k_base |
| Llama 3.3 70b instruct fp8 fastcloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.293 | $2.253 | 24,000 tokens | 估算o200k_base |
| Llama 4 scout 17b 16e instructcloudflare/@cf/meta/llama-4-scout-17b-16e-instruct · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.27 | $0.85 | 131,000 tokens | 估算o200k_base |
| Llama guard 3 8bcloudflare/@cf/meta/llama-guard-3-8b · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.484 | $0.03 | 131,072 tokens | 估算o200k_base |
| Mistral 7b instruct v0.1cloudflare/@cf/mistral/mistral-7b-instruct-v0.1 · cloudflare | LiteLLM ↗2026-10-25 UTC | $1.923 | $1.923 | 8,192 tokens | 估算o200k_base |
| Mistral 7b instruct v0.2 loracloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 15,000 tokens | 估算o200k_base |
| Mistral small 3.1 24b instructcloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.351 | $0.555 | 128,000 tokens | 估算o200k_base |
| kimi k2.6cloudflare/@cf/moonshotai/kimi-k2.6 · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| kimi k2.7 codecloudflare/@cf/moonshotai/kimi-k2.7-code · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| nemotron 3 120b a12bcloudflare/@cf/nvidia/nemotron-3-120b-a12b · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 256,000 tokens | 估算o200k_base |
| GPT oss 120bcloudflare/@cf/openai/gpt-oss-120b · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.35 | $0.75 | 128,000 tokens | 估算o200k_base |
| GPT oss 20bcloudflare/@cf/openai/gpt-oss-20b · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.30 | 128,000 tokens | 估算o200k_base |
| qwen2.5 coder 32b instructcloudflare/@cf/qwen/qwen2.5-coder-32b-instruct · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.66 | $1.00 | 32,768 tokens | 估算o200k_base |
| qwen3 30b a3b fp8cloudflare/@cf/qwen/qwen3-30b-a3b-fp8 · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.0509 | $0.335 | 32,768 tokens | 估算o200k_base |
| qwq 32bcloudflare/@cf/qwen/qwq-32b · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.66 | $1.00 | 24,000 tokens | 估算o200k_base |
| glm 4.7 flashcloudflare/@cf/zai-org/glm-4.7-flash · cloudflare | LiteLLM ↗2026-10-25 UTC | $0.0605 | $0.40 | 131,072 tokens | 估算o200k_base |
| glm 5.2cloudflare/@cf/zai-org/glm-5.2 · cloudflare | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 262,144 tokens | 估算o200k_base |
| codellama 7b instruct awqcloudflare/@hf/thebloke/codellama-7b-instruct-awq · cloudflare | LiteLLM ↗2026-10-25 UTC | $1.923 | $1.923 | 4,096 tokens | 估算o200k_base |
| codestral 2405codestral/codestral-2405 · codestral | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,000 tokens | 估算o200k_base |
| codestral latestcodestral/codestral-latest · codestral | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,000 tokens | 估算o200k_base |
| cohere.command light text v14cohere.command-light-text-v14 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.60 | 4,096 tokens | 估算o200k_base |
| cohere.command text v14cohere.command-text-v14 · bedrock | LiteLLM ↗2026-10-25 UTC | $1.00 | $2.00 | 4,096 tokens | 估算o200k_base |
| command a 03 2025command-a-03-2025 · cohere_chat | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 256,000 tokens | 估算o200k_base |
| command a plus 05 2026command-a-plus-05-2026 · cohere_chat | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 128,000 tokens | 估算o200k_base |
| command r 08 2024command-r-08-2024 · cohere_chat | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| command r plus 08 2024command-r-plus-08-2024 · cohere_chat | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| command r7b 12 2024command-r7b-12-2024 · cohere_chat | LiteLLM ↗2026-10-25 UTC | $0.0375 | $0.15 | 128,000 tokens | 估算o200k_base |
| computer use previewcomputer-use-preview · openai | LiteLLM ↗2026-10-25 UTC | $3.00 | $12.00 | 8,192 tokens | 估算o200k_base |
| computer use preview 2025 03 11computer-use-preview-2025-03-11 · openai | LiteLLM ↗2026-10-25 UTC | $3.00 | $12.00 | 8,192 tokens | 估算o200k_base |
| DeepSeek v4.1 flashcoralbricks/deepseek-v4.1-flash · coralbricks | LiteLLM ↗2026-10-25 UTC | $0.01 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4.1 flash fastcoralbricks/deepseek-v4.1-flash-fast · coralbricks | LiteLLM ↗2026-10-25 UTC | $0.01 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4.1 flash fast fp4coralbricks/deepseek-v4.1-flash-fast-fp4 · coralbricks | LiteLLM ↗2026-10-25 UTC | $0.01 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| glm 5.3coralbricks/glm-5.3 · coralbricks | LiteLLM ↗2026-10-25 UTC | $1.12 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| glm 5.3 fastcoralbricks/glm-5.3-fast · coralbricks | LiteLLM ↗2026-10-25 UTC | $1.12 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| glm 5.3 fp4coralbricks/glm-5.3-fp4 · coralbricks | LiteLLM ↗2026-10-25 UTC | $1.12 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek R1 0528crusoe/deepseek-ai/DeepSeek-R1-0528 · crusoe | LiteLLM ↗2026-10-25 UTC | $3.00 | $7.00 | 163,840 tokens | 估算o200k_base |
| DeepSeek V3 0324crusoe/deepseek-ai/DeepSeek-V3-0324 · crusoe | LiteLLM ↗2026-10-25 UTC | $1.50 | $1.50 | 163,840 tokens | 估算o200k_base |
| gemma 3 12b itcrusoe/google/gemma-3-12b-it · crusoe | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| Llama 3.3 70B Instructcrusoe/meta-llama/Llama-3.3-70B-Instruct · crusoe | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| Kimi K2 Thinkingcrusoe/moonshotai/Kimi-K2-Thinking · crusoe | LiteLLM ↗2026-10-25 UTC | $2.50 | $2.50 | 262,144 tokens | 估算o200k_base |
| GPT oss 120bcrusoe/openai/gpt-oss-120b · crusoe | LiteLLM ↗2026-10-25 UTC | $0.80 | $0.80 | 131,072 tokens | 估算o200k_base |
| Qwen3 235B A22B Instruct 2507crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507 · crusoe | LiteLLM ↗2026-10-25 UTC | $3.00 | $3.00 | 262,144 tokens | 估算o200k_base |
| gemma 4 26bdarkbloom/gemma-4-26b · darkbloom | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.165 | 131,072 tokens | 估算o200k_base |
| GPT oss 20bdarkbloom/gpt-oss-20b · darkbloom | LiteLLM ↗2026-10-25 UTC | $0.0145 | $0.07 | 131,072 tokens | 估算o200k_base |
| DeepSeek v4 flashdashscope/deepseek-v4-flash · dashscope | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 flash 0731dashscope/deepseek-v4-flash-0731 · dashscope | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 prodashscope/deepseek-v4-pro · dashscope | LiteLLM ↗2026-10-25 UTC | $2.40 | $4.80 | 1,000,000 tokens | 估算o200k_base |
| glm 5.1dashscope/glm-5.1 · dashscope | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 202,745 tokens | 估算o200k_base |
| glm 5.2dashscope/glm-5.2 · dashscope | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| kimi k2.7 codedashscope/kimi-k2.7-code · dashscope | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 229,376 tokens | 估算o200k_base |
| Qwen coderdashscope/qwen-coder · dashscope | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.50 | 1,000,000 tokens | 估算o200k_base |
| Qwen flashdashscope/qwen-flash · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen flash 2025 07 28dashscope/qwen-flash-2025-07-28 · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen maxdashscope/qwen-max · dashscope | LiteLLM ↗2026-10-25 UTC | $1.60 | $6.40 | 30,720 tokens | 估算o200k_base |
| Qwen plusdashscope/qwen-plus · dashscope | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 129,024 tokens | 估算o200k_base |
| Qwen plus 2025 01 25dashscope/qwen-plus-2025-01-25 · dashscope | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 129,024 tokens | 估算o200k_base |
| Qwen plus 2025 04 28dashscope/qwen-plus-2025-04-28 · dashscope | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 129,024 tokens | 估算o200k_base |
| Qwen plus 2025 07 14dashscope/qwen-plus-2025-07-14 · dashscope | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 129,024 tokens | 估算o200k_base |
| Qwen plus 2025 07 28dashscope/qwen-plus-2025-07-28 · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen plus 2025 09 11dashscope/qwen-plus-2025-09-11 · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen plus latestdashscope/qwen-plus-latest · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen turbodashscope/qwen-turbo · dashscope | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 129,024 tokens | 估算o200k_base |
| Qwen turbo 2024 11 01dashscope/qwen-turbo-2024-11-01 · dashscope | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 1,000,000 tokens | 估算o200k_base |
| Qwen turbo 2025 04 28dashscope/qwen-turbo-2025-04-28 · dashscope | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 1,000,000 tokens | 估算o200k_base |
| Qwen turbo latestdashscope/qwen-turbo-latest · dashscope | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 1,000,000 tokens | 估算o200k_base |
| qwen3 30b a3bdashscope/qwen3-30b-a3b · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 129,024 tokens | 估算o200k_base |
| qwen3 coder flashdashscope/qwen3-coder-flash · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| qwen3 coder flash 2025 07 28dashscope/qwen3-coder-flash-2025-07-28 · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| qwen3 coder plusdashscope/qwen3-coder-plus · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| qwen3 coder plus 2025 07 22dashscope/qwen3-coder-plus-2025-07-22 · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| qwen3 maxdashscope/qwen3-max · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 258,048 tokens | 估算o200k_base |
| qwen3 max 2026 01 23dashscope/qwen3-max-2026-01-23 · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 258,048 tokens | 估算o200k_base |
| qwen3 max previewdashscope/qwen3-max-preview · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 258,048 tokens | 估算o200k_base |
| qwen3 next 80b a3b instructdashscope/qwen3-next-80b-a3b-instruct · dashscope | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.20 | 262,144 tokens | 估算o200k_base |
| qwen3 next 80b a3b thinkingdashscope/qwen3-next-80b-a3b-thinking · dashscope | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.20 | 262,144 tokens | 估算o200k_base |
| qwen3 vl 235b a22b instructdashscope/qwen3-vl-235b-a22b-instruct · dashscope | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 235b a22b thinkingdashscope/qwen3-vl-235b-a22b-thinking · dashscope | LiteLLM ↗2026-10-25 UTC | $0.40 | $4.00 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 32b instructdashscope/qwen3-vl-32b-instruct · dashscope | LiteLLM ↗2026-10-25 UTC | $0.16 | $0.64 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 32b thinkingdashscope/qwen3-vl-32b-thinking · dashscope | LiteLLM ↗2026-10-25 UTC | $0.16 | $2.87 | 131,072 tokens | 估算o200k_base |
| qwen3 vl plusdashscope/qwen3-vl-plus · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 260,096 tokens | 估算o200k_base |
| qwen3.5 plusdashscope/qwen3.5-plus · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 991,808 tokens | 估算o200k_base |
| qwen3.7 maxdashscope/qwen3.7-max · dashscope | LiteLLM ↗2026-10-25 UTC | $2.50 | $7.50 | 991,808 tokens | 估算o200k_base |
| qwen3.7 plusdashscope/qwen3.7-plus · dashscope | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 991,808 tokens | 估算o200k_base |
| qwen3.8 flashdashscope/qwen3.8-flash · dashscope | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.47 | 991,808 tokens | 估算o200k_base |
| qwen3.8 maxdashscope/qwen3.8-max · dashscope | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 991,808 tokens | 估算o200k_base |
| qwen3.8 omni flashdashscope/qwen3.8-omni-flash · dashscope | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.47 | 991,808 tokens | 估算o200k_base |
| qwq plusdashscope/qwq-plus · dashscope | LiteLLM ↗2026-10-25 UTC | $0.80 | $2.40 | 98,304 tokens | 估算o200k_base |
| databricks Claude fable 5databricks/databricks-claude-fable-5 · databricks | LiteLLM ↗2026-10-25 UTC | $10.00006 | $50.00002 | 1,000,000 tokens | 估算o200k_base |
| databricks Claude fable 5 1databricks/databricks-claude-fable-5-1 · databricks | LiteLLM ↗2026-10-25 UTC | $10.00006 | $50.00002 | 1,000,000 tokens | 估算o200k_base |
| databricks Claude haiku 4 5databricks/databricks-claude-haiku-4-5 · databricks | LiteLLM ↗2026-10-25 UTC | $1.00002 | $5.00003 | 200,000 tokens | 估算o200k_base |
| databricks Claude opus 4databricks/databricks-claude-opus-4 · databricks | LiteLLM ↗2026-10-25 UTC | $15.00002 | $75.00003 | 200,000 tokens | 估算o200k_base |
| databricks Claude opus 4 1databricks/databricks-claude-opus-4-1 · databricks | LiteLLM ↗2026-10-25 UTC | $15.00002 | $75.00003 | 200,000 tokens | 估算o200k_base |
| databricks Claude opus 4 5databricks/databricks-claude-opus-4-5 · databricks | LiteLLM ↗2026-10-25 UTC | $5.00003 | $25.00001 | 200,000 tokens | 估算o200k_base |
| databricks Claude opus 4 6databricks/databricks-claude-opus-4-6 · databricks | LiteLLM ↗2026-10-25 UTC | $5.00003 | $25.00001 | 1,000,000 tokens | 估算o200k_base |
| databricks Claude opus 4 7databricks/databricks-claude-opus-4-7 · databricks | LiteLLM ↗2026-10-25 UTC | $5.00003 | $25.00001 | 1,000,000 tokens | 估算o200k_base |
| databricks Claude opus 4 8databricks/databricks-claude-opus-4-8 · databricks | LiteLLM ↗2026-10-25 UTC | $5.00003 | $25.00001 | 1,000,000 tokens | 估算o200k_base |
| databricks Claude opus 5databricks/databricks-claude-opus-5 · databricks | LiteLLM ↗2026-10-25 UTC | $5.00003 | $25.00001 | 1,000,000 tokens | 估算o200k_base |
| databricks Claude opus 5 5databricks/databricks-claude-opus-5-5 · databricks | LiteLLM ↗2026-10-25 UTC | $4.00001 | $19.99998 | 1,000,000 tokens | 估算o200k_base |
| databricks Claude sonnet 4databricks/databricks-claude-sonnet-4 · databricks | LiteLLM ↗2026-10-25 UTC | $2.99999 | $15.00002 | 200,000 tokens | 估算o200k_base |
| databricks Claude sonnet 4 1databricks/databricks-claude-sonnet-4-1 · databricks | LiteLLM ↗2026-10-25 UTC | $2.99999 | $15.00002 | 200,000 tokens | 估算o200k_base |
| databricks Claude sonnet 4 5databricks/databricks-claude-sonnet-4-5 · databricks | LiteLLM ↗2026-10-25 UTC | $2.99999 | $15.00002 | 200,000 tokens | 估算o200k_base |
| databricks Claude sonnet 4 6databricks/databricks-claude-sonnet-4-6 · databricks | LiteLLM ↗2026-10-25 UTC | $2.99999 | $15.00002 | 1,000,000 tokens | 估算o200k_base |
| databricks Claude sonnet 5databricks/databricks-claude-sonnet-5 · databricks | LiteLLM ↗2026-10-25 UTC | $2.99999 | $15.00002 | 1,000,000 tokens | 估算o200k_base |
| databricks DeepSeek v4 flash 0731databricks/databricks-deepseek-v4-flash-0731 · databricks | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 1,000,000 tokens | 估算o200k_base |
| databricks DeepSeek v4 pro 0813databricks/databricks-deepseek-v4-pro-0813 · databricks | LiteLLM ↗2026-10-25 UTC | $1.31999 | $3.95997 | 1,000,000 tokens | 估算o200k_base |
| databricks Gemini 2 5 flashdatabricks/databricks-gemini-2-5-flash · databricks | LiteLLM ↗2026-10-25 UTC | $0.30002 | $2.49998 | 1,048,576 tokens | 估算o200k_base |
| databricks Gemini 2 5 prodatabricks/databricks-gemini-2-5-pro · databricks | LiteLLM ↗2026-10-25 UTC | $1.24999 | $9.99999 | 1,048,576 tokens | 估算o200k_base |
| databricks Gemini 3 1 flash imagedatabricks/databricks-gemini-3-1-flash-image · databricks | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 131,072 tokens | 估算o200k_base |
| databricks Gemini 3 1 flash litedatabricks/databricks-gemini-3-1-flash-lite · databricks | LiteLLM ↗2026-10-25 UTC | $0.31248 | $1.87502 | 1,048,576 tokens | 估算o200k_base |
| databricks Gemini 3 1 prodatabricks/databricks-gemini-3-1-pro · databricks | LiteLLM ↗2026-10-25 UTC | $2.49998 | $15.00002 | 1,048,576 tokens | 估算o200k_base |
| databricks Gemini 3 5 flashdatabricks/databricks-gemini-3-5-flash · databricks | LiteLLM ↗2026-10-25 UTC | $1.87502 | $11.24998 | 1,048,576 tokens | 估算o200k_base |
| databricks Gemini 3 5 flash litedatabricks/databricks-gemini-3-5-flash-lite · databricks | LiteLLM ↗2026-10-25 UTC | $0.37499 | $3.12501 | 1,048,576 tokens | 估算o200k_base |
| databricks Gemini 3 6 flashdatabricks/databricks-gemini-3-6-flash · databricks | LiteLLM ↗2026-10-25 UTC | $1.87502 | $9.37503 | 1,048,576 tokens | 估算o200k_base |
| databricks Gemini 3 7 flashdatabricks/databricks-gemini-3-7-flash · databricks | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 1,048,576 tokens | 估算o200k_base |
| databricks Gemini 3 8 flashdatabricks/databricks-gemini-3-8-flash · databricks | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 1,048,576 tokens | 估算o200k_base |
| databricks Gemini 3 flashdatabricks/databricks-gemini-3-flash · databricks | LiteLLM ↗2026-10-25 UTC | $0.62503 | $3.74997 | 1,048,576 tokens | 估算o200k_base |
| databricks Gemini 3 prodatabricks/databricks-gemini-3-pro · databricks | LiteLLM ↗2026-10-25 UTC | $2.49998 | $15.00002 | 1,048,576 tokens | 估算o200k_base |
| databricks Gemini 3 pro imagedatabricks/databricks-gemini-3-pro-image · databricks | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 65,536 tokens | 估算o200k_base |
| databricks gemma 3 12bdatabricks/databricks-gemma-3-12b · databricks | LiteLLM ↗2026-10-25 UTC | $0.15001 | $0.50001 | 128,000 tokens | 估算o200k_base |
| databricks glm 5 2databricks/databricks-glm-5-2 · databricks | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.39999 | 1,000,000 tokens | 估算o200k_base |
| databricks glm 5 3databricks/databricks-glm-5-3 · databricks | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.39999 | 1,048,576 tokens | 估算o200k_base |
| databricks glm 5 3 flashdatabricks/databricks-glm-5-3-flash · databricks | LiteLLM ↗2026-10-25 UTC | $0.15001 | $0.50001 | 1,048,576 tokens | 估算o200k_base |
| databricks GPT 5databricks/databricks-gpt-5 · databricks | LiteLLM ↗2026-10-25 UTC | $1.24999 | $9.99999 | 272,000 tokens | 估算o200k_base |
| databricks GPT 5 1databricks/databricks-gpt-5-1 · databricks | LiteLLM ↗2026-10-25 UTC | $1.24999 | $9.99999 | 272,000 tokens | 估算o200k_base |
| databricks GPT 5 2databricks/databricks-gpt-5-2 · databricks | LiteLLM ↗2026-10-25 UTC | $1.75 | $14.00 | 272,000 tokens | 估算o200k_base |
| databricks GPT 5 4databricks/databricks-gpt-5-4 · databricks | LiteLLM ↗2026-10-25 UTC | $2.49998 | $15.00002 | 922,000 tokens | 估算o200k_base |
| databricks GPT 5 4 minidatabricks/databricks-gpt-5-4-mini · databricks | LiteLLM ↗2026-10-25 UTC | $0.74998 | $4.50002 | 272,000 tokens | 估算o200k_base |
| databricks GPT 5 4 nanodatabricks/databricks-gpt-5-4-nano · databricks | LiteLLM ↗2026-10-25 UTC | $0.19999 | $1.24999 | 272,000 tokens | 估算o200k_base |
| databricks GPT 5 6 lunadatabricks/databricks-gpt-5-6-luna · databricks | LiteLLM ↗2026-10-25 UTC | $1.00002 | $5.99998 | 922,000 tokens | 估算o200k_base |
| databricks GPT 5 6 soldatabricks/databricks-gpt-5-6-sol · databricks | LiteLLM ↗2026-10-25 UTC | $4.00001 | $19.99998 | 922,000 tokens | 估算o200k_base |
| databricks GPT 5 6 terradatabricks/databricks-gpt-5-6-terra · databricks | LiteLLM ↗2026-10-25 UTC | $2.49998 | $15.00002 | 922,000 tokens | 估算o200k_base |
| databricks GPT 5 minidatabricks/databricks-gpt-5-mini · databricks | LiteLLM ↗2026-10-25 UTC | $0.24997 | $1.99997 | 272,000 tokens | 估算o200k_base |
| databricks GPT 5 nanodatabricks/databricks-gpt-5-nano · databricks | LiteLLM ↗2026-10-25 UTC | $0.04998 | $0.39998 | 272,000 tokens | 估算o200k_base |
| databricks GPT oss 120bdatabricks/databricks-gpt-oss-120b · databricks | LiteLLM ↗2026-10-25 UTC | $0.15001 | $0.59997 | 131,072 tokens | 估算o200k_base |
| databricks GPT oss 20bdatabricks/databricks-gpt-oss-20b · databricks | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.30002 | 131,072 tokens | 估算o200k_base |
| databricks grok 4 6databricks/databricks-grok-4-6 · databricks | LiteLLM ↗2026-10-25 UTC | $2.49998 | $7.50001 | 500,000 tokens | 估算o200k_base |
| databricks inklingdatabricks/databricks-inkling · databricks | LiteLLM ↗2026-10-25 UTC | $1.00002 | $4.04999 | 1,000,000 tokens | 估算o200k_base |
| databricks kimi k3databricks/databricks-kimi-k3 · databricks | LiteLLM ↗2026-10-25 UTC | $2.99999 | $15.00002 | 1,000,000 tokens | 估算o200k_base |
| databricks Llama 4 maverickdatabricks/databricks-llama-4-maverick · databricks | LiteLLM ↗2026-10-25 UTC | $0.50001 | $1.50003 | 128,000 tokens | 估算o200k_base |
| databricks meta Llama 3 1 8b instructdatabricks/databricks-meta-llama-3-1-8b-instruct · databricks | LiteLLM ↗2026-10-25 UTC | $0.15001 | $0.45003 | 200,000 tokens | 估算o200k_base |
| databricks meta Llama 3 3 70b instructdatabricks/databricks-meta-llama-3-3-70b-instruct · databricks | LiteLLM ↗2026-10-25 UTC | $0.50001 | $1.50003 | 128,000 tokens | 估算o200k_base |
| databricks qwen35 122b a10bdatabricks/databricks-qwen35-122b-a10b · databricks | LiteLLM ↗2026-10-25 UTC | $0.22001 | $2.20003 | 262,144 tokens | 估算o200k_base |
| daybreak blue latestdaybreak-blue-latest · openai | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 922,000 tokens | 估算o200k_base |
| daybreak red latestdaybreak-red-latest · openai | LiteLLM ↗2026-10-25 UTC | $12.50 | $75.00 | 400,000 tokens | 估算o200k_base |
| deep research pro preview 12 2025deep-research-pro-preview-12-2025 · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 65,536 tokens | 估算o200k_base |
| olmOCR 7B 0725 FP8deepinfra/allenai/olmOCR-7B-0725-FP8 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.27 | $1.50 | 16,384 tokens | 估算o200k_base |
| Claude 3 7 sonnet latestdeepinfra/anthropic/claude-3-7-sonnet-latest · deepinfra | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 200,000 tokens | 估算o200k_base |
| Claude 4 opusdeepinfra/anthropic/claude-4-opus · deepinfra | LiteLLM ↗2026-10-25 UTC | $16.50 | $82.50 | 200,000 tokens | 估算o200k_base |
| Claude 4 sonnetdeepinfra/anthropic/claude-4-sonnet · deepinfra | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 200,000 tokens | 估算o200k_base |
| Claude fable 5deepinfra/anthropic/claude-fable-5 · deepinfra | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude haiku 4 5deepinfra/anthropic/claude-haiku-4-5 · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 4 7deepinfra/anthropic/claude-opus-4-7 · deepinfra | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 8deepinfra/anthropic/claude-opus-4-8 · deepinfra | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5deepinfra/anthropic/claude-opus-5 · deepinfra | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 4 6deepinfra/anthropic/claude-sonnet-4-6 · deepinfra | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 5deepinfra/anthropic/claude-sonnet-5 · deepinfra | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| Seed 1.8deepinfra/ByteDance/Seed-1.8 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.25 | $2.00 | 256,000 tokens | 估算o200k_base |
| Seed 2.0 codedeepinfra/ByteDance/Seed-2.0-code · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.50 | $3.00 | 256,000 tokens | 估算o200k_base |
| Seed 2.0 minideepinfra/ByteDance/Seed-2.0-mini · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 256,000 tokens | 估算o200k_base |
| Seed 2.0 prodeepinfra/ByteDance/Seed-2.0-pro · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.50 | $3.00 | 256,000 tokens | 估算o200k_base |
| DeepSeek R1deepinfra/deepseek-ai/DeepSeek-R1 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.70 | $2.40 | 163,840 tokens | 估算o200k_base |
| DeepSeek R1 0528deepinfra/deepseek-ai/DeepSeek-R1-0528 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.50 | $2.15 | 163,840 tokens | 估算o200k_base |
| DeepSeek R1 0528 Turbodeepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.00 | 32,768 tokens | 估算o200k_base |
| DeepSeek R1 Distill Llama 70Bdeepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 131,072 tokens | 估算o200k_base |
| DeepSeek R1 Distill Qwen 32Bdeepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.27 | $0.27 | 131,072 tokens | 估算o200k_base |
| DeepSeek R1 Turbodeepinfra/deepseek-ai/DeepSeek-R1-Turbo · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.00 | 40,960 tokens | 估算o200k_base |
| DeepSeek V3deepinfra/deepseek-ai/DeepSeek-V3 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.32 | $0.89 | 163,840 tokens | 估算o200k_base |
| DeepSeek V3 0324deepinfra/deepseek-ai/DeepSeek-V3-0324 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.24 | $0.90 | 163,840 tokens | 估算o200k_base |
| DeepSeek V3.1deepinfra/deepseek-ai/DeepSeek-V3.1 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.95 | 163,840 tokens | 估算o200k_base |
| DeepSeek V3.1 Terminusdeepinfra/deepseek-ai/DeepSeek-V3.1-Terminus · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.27 | $1.00 | 163,840 tokens | 估算o200k_base |
| DeepSeek V3.2deepinfra/deepseek-ai/DeepSeek-V3.2 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.26 | $0.38 | 163,840 tokens | 估算o200k_base |
| DeepSeek V4 Flashdeepinfra/deepseek-ai/DeepSeek-V4-Flash · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.18 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Flash 0731deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.18 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Prodeepinfra/deepseek-ai/DeepSeek-V4-Pro · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.30 | $2.60 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Pro 0813deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813 · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.30 | $2.60 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4.1 Flashdeepinfra/deepseek-ai/DeepSeek-V4.1-Flash · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.42 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4.1 Flash 1017deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.42 | 1,048,576 tokens | 估算o200k_base |
| Gemini 2.5 flashdeepinfra/google/gemini-2.5-flash · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| Gemini 2.5 prodeepinfra/google/gemini-2.5-pro · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| Gemini 3.1 flash litedeepinfra/google/gemini-3.1-flash-lite · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.50 | 1,000,000 tokens | 估算o200k_base |
| Gemini 3.1 prodeepinfra/google/gemini-3.1-pro · deepinfra | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,000,000 tokens | 估算o200k_base |
| Gemini 3.5 flashdeepinfra/google/gemini-3.5-flash · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.50 | $9.00 | 1,000,000 tokens | 估算o200k_base |
| Gemini 3.7 flashdeepinfra/google/gemini-3.7-flash · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,000,000 tokens | 估算o200k_base |
| gemma 3 12b itdeepinfra/google/gemma-3-12b-it · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.15 | 131,072 tokens | 估算o200k_base |
| gemma 3 27b itdeepinfra/google/gemma-3-27b-it · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.16 | 131,072 tokens | 估算o200k_base |
| gemma 3 4b itdeepinfra/google/gemma-3-4b-it · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.10 | 131,072 tokens | 估算o200k_base |
| gemma 4 26B A4B itdeepinfra/google/gemma-4-26B-A4B-it · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.34 | 262,144 tokens | 估算o200k_base |
| gemma 4 31B itdeepinfra/google/gemma-4-31B-it · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.38 | 262,144 tokens | 估算o200k_base |
| gemma 4 31B it turbodeepinfra/google/gemma-4-31B-it-turbo · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.34 | 262,144 tokens | 估算o200k_base |
| gemma 4 31B it Ultradeepinfra/google/gemma-4-31B-it-Ultra · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.27 | $0.76 | 131,072 tokens | 估算o200k_base |
| gemma 4 E4B itdeepinfra/google/gemma-4-E4B-it · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.02 | $0.10 | 131,072 tokens | 估算o200k_base |
| MythoMax L2 13bdeepinfra/Gryphe/MythoMax-L2-13b · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.40 | $0.40 | 4,096 tokens | 估算o200k_base |
| Ling 3.0 flashdeepinfra/inclusionAI/Ling-3.0-flash · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.18 | 131,072 tokens | 估算o200k_base |
| Llama 3.2 11B Vision Instructdeepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.049 | $0.049 | 131,072 tokens | 估算o200k_base |
| Llama 3.2 3B Instructdeepinfra/meta-llama/Llama-3.2-3B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.02 | $0.02 | 131,072 tokens | 估算o200k_base |
| Llama 3.3 70B Instructdeepinfra/meta-llama/Llama-3.3-70B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.23 | $0.40 | 131,072 tokens | 估算o200k_base |
| Llama 3.3 70B Instruct Turbodeepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.32 | 131,072 tokens | 估算o200k_base |
| Llama 4 Maverick 17B 128E Instruct FP8deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.80 | 1,048,576 tokens | 估算o200k_base |
| Llama 4 Scout 17B 16E Instructdeepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 327,680 tokens | 估算o200k_base |
| Llama Guard 3 8Bdeepinfra/meta-llama/Llama-Guard-3-8B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.055 | $0.055 | 131,072 tokens | 估算o200k_base |
| Llama Guard 4 12Bdeepinfra/meta-llama/Llama-Guard-4-12B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.18 | 163,840 tokens | 估算o200k_base |
| Meta Llama 3 8B Instructdeepinfra/meta-llama/Meta-Llama-3-8B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.06 | 8,192 tokens | 估算o200k_base |
| Meta Llama 3.1 70B Instructdeepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.40 | $0.40 | 131,072 tokens | 估算o200k_base |
| Meta Llama 3.1 70B Instruct Turbodeepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.40 | $0.40 | 131,072 tokens | 估算o200k_base |
| Meta Llama 3.1 8B Instructdeepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.05 | 131,072 tokens | 估算o200k_base |
| Meta Llama 3.1 8B Instruct Turbodeepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.02 | $0.04 | 131,072 tokens | 估算o200k_base |
| Muse Glimmer 30Bdeepinfra/meta-models/Muse-Glimmer-30B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 131,072 tokens | 估算o200k_base |
| phi 4deepinfra/microsoft/phi-4 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.14 | 16,384 tokens | 估算o200k_base |
| WizardLM 2 8x22Bdeepinfra/microsoft/WizardLM-2-8x22B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.48 | $0.48 | 65,536 tokens | 估算o200k_base |
| MiniMax M2.7deepinfra/MiniMaxAI/MiniMax-M2.7 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.00 | 196,608 tokens | 估算o200k_base |
| MiniMax M2.7 Turbodeepinfra/MiniMaxAI/MiniMax-M2.7-Turbo · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.38 | $1.70 | 196,608 tokens | 估算o200k_base |
| MiniMax M3deepinfra/MiniMaxAI/MiniMax-M3 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.28 | $1.10 | 524,288 tokens | 估算o200k_base |
| Mistral Nemo Instruct 2407deepinfra/mistralai/Mistral-Nemo-Instruct-2407 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.019 | $0.03 | 131,072 tokens | 估算o200k_base |
| Mistral Small 24B Instruct 2501deepinfra/mistralai/Mistral-Small-24B-Instruct-2501 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.08 | 32,768 tokens | 估算o200k_base |
| Mistral Small 3.2 24B Instruct 2506deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.075 | $0.20 | 128,000 tokens | 估算o200k_base |
| Mixtral 8x7B Instruct v0.1deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.40 | $0.40 | 32,768 tokens | 估算o200k_base |
| Kimi K2 Instructdeepinfra/moonshotai/Kimi-K2-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.50 | $2.00 | 131,072 tokens | 估算o200k_base |
| Kimi K2 Instruct 0905deepinfra/moonshotai/Kimi-K2-Instruct-0905 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.50 | $2.00 | 262,144 tokens | 估算o200k_base |
| Kimi K2.5deepinfra/moonshotai/Kimi-K2.5 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.45 | $2.25 | 262,144 tokens | 估算o200k_base |
| Kimi K2.6deepinfra/moonshotai/Kimi-K2.6 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.50 | 262,144 tokens | 估算o200k_base |
| Kimi K2.7 Codedeepinfra/moonshotai/Kimi-K2.7-Code · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.68 | $3.40 | 262,144 tokens | 估算o200k_base |
| Kimi K3deepinfra/moonshotai/Kimi-K3 · deepinfra | LiteLLM ↗2026-10-25 UTC | $2.85 | $14.25 | 1,048,576 tokens | 估算o200k_base |
| Hermes 3 Llama 3.1 405Bdeepinfra/NousResearch/Hermes-3-Llama-3.1-405B · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.00 | $1.00 | 131,072 tokens | 估算o200k_base |
| Hermes 3 Llama 3.1 70Bdeepinfra/NousResearch/Hermes-3-Llama-3.1-70B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.70 | $0.70 | 131,072 tokens | 估算o200k_base |
| Llama 3.1 Nemotron 70B Instructdeepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.60 | $0.60 | 131,072 tokens | 估算o200k_base |
| Llama 3.3 Nemotron Super 49B v1.5deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 131,072 tokens | 估算o200k_base |
| Nemotron 3 Nano 30B A3Bdeepinfra/nvidia/Nemotron-3-Nano-30B-A3B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 262,144 tokens | 估算o200k_base |
| Nemotron Content Safety 3.5deepinfra/nvidia/Nemotron-Content-Safety-3.5 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| NVIDIA Nemotron 3 Super 120B A12Bdeepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.085 | $0.40 | 262,144 tokens | 估算o200k_base |
| NVIDIA Nemotron 3 Ultra 550B A55Bdeepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.50 | $2.20 | 262,144 tokens | 估算o200k_base |
| NVIDIA Nemotron 3.5 Lightningdeepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.20 | 262,144 tokens | 估算o200k_base |
| NVIDIA Nemotron Nano 9B v2deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.16 | 131,072 tokens | 估算o200k_base |
| GPT oss 120bdeepinfra/openai/gpt-oss-120b · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.037 | $0.17 | 131,072 tokens | 估算o200k_base |
| GPT oss 120b Turbodeepinfra/openai/gpt-oss-120b-Turbo · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| GPT oss 120b Ultradeepinfra/openai/gpt-oss-120b-Ultra · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.95 | 131,072 tokens | 估算o200k_base |
| GPT oss 20bdeepinfra/openai/gpt-oss-20b · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.14 | 131,072 tokens | 估算o200k_base |
| Qwen2.5 72B Instructdeepinfra/Qwen/Qwen2.5-72B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.36 | $0.40 | 32,768 tokens | 估算o200k_base |
| Qwen2.5 7B Instructdeepinfra/Qwen/Qwen2.5-7B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.10 | 32,768 tokens | 估算o200k_base |
| Qwen2.5 VL 32B Instructdeepinfra/Qwen/Qwen2.5-VL-32B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 128,000 tokens | 估算o200k_base |
| Qwen3 14Bdeepinfra/Qwen/Qwen3-14B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.24 | 40,960 tokens | 估算o200k_base |
| Qwen3 235B A22Bdeepinfra/Qwen/Qwen3-235B-A22B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.54 | 40,960 tokens | 估算o200k_base |
| Qwen3 235B A22B Instruct 2507deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.55 | 262,144 tokens | 估算o200k_base |
| Qwen3 235B A22B Thinking 2507deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.90 | 262,144 tokens | 估算o200k_base |
| Qwen3 30B A3Bdeepinfra/Qwen/Qwen3-30B-A3B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.50 | 40,960 tokens | 估算o200k_base |
| Qwen3 32Bdeepinfra/Qwen/Qwen3-32B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.28 | 40,960 tokens | 估算o200k_base |
| Qwen3 Coder 480B A35B Instructdeepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 262,144 tokens | 估算o200k_base |
| Qwen3 Coder 480B A35B Instruct Turbodeepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.00 | 262,144 tokens | 估算o200k_base |
| Qwen3 Maxdeepinfra/Qwen/Qwen3-Max · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.20 | $6.00 | 256,000 tokens | 估算o200k_base |
| Qwen3 Max Thinkingdeepinfra/Qwen/Qwen3-Max-Thinking · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.20 | $6.00 | 256,000 tokens | 估算o200k_base |
| Qwen3 Next 80B A3B Instructdeepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.09 | $1.10 | 262,144 tokens | 估算o200k_base |
| Qwen3 Next 80B A3B Thinkingdeepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.14 | $1.40 | 262,144 tokens | 估算o200k_base |
| Qwen3 VL 235B A22B Instructdeepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.88 | 262,144 tokens | 估算o200k_base |
| Qwen3 VL 30B A3B Instructdeepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 262,144 tokens | 估算o200k_base |
| Qwen3.5 122B A10Bdeepinfra/Qwen/Qwen3.5-122B-A10B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.29 | $2.40 | 262,144 tokens | 估算o200k_base |
| Qwen3.5 27Bdeepinfra/Qwen/Qwen3.5-27B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.26 | $2.60 | 262,144 tokens | 估算o200k_base |
| Qwen3.5 35B A3Bdeepinfra/Qwen/Qwen3.5-35B-A3B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.14 | $1.00 | 262,144 tokens | 估算o200k_base |
| Qwen3.5 397B A17Bdeepinfra/Qwen/Qwen3.5-397B-A17B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.45 | $3.00 | 262,144 tokens | 估算o200k_base |
| Qwen3.5 9Bdeepinfra/Qwen/Qwen3.5-9B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.15 | 262,144 tokens | 估算o200k_base |
| Qwen3.6 27Bdeepinfra/Qwen/Qwen3.6-27B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.32 | $3.20 | 262,144 tokens | 估算o200k_base |
| Qwen3.6 35B A3Bdeepinfra/Qwen/Qwen3.6-35B-A3B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.95 | 262,144 tokens | 估算o200k_base |
| Qwen3.7 Maxdeepinfra/Qwen/Qwen3.7-Max · deepinfra | LiteLLM ↗2026-10-25 UTC | $2.50 | $7.50 | 256,000 tokens | 估算o200k_base |
| Qwen3.8 2.4T A95Bdeepinfra/Qwen/Qwen3.8-2.4T-A95B · deepinfra | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 262,144 tokens | 估算o200k_base |
| Qwen3.8 27Bdeepinfra/Qwen/Qwen3.8-27B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.40 | $3.00 | 262,144 tokens | 估算o200k_base |
| Qwen3.8 Maxdeepinfra/Qwen/Qwen3.8-Max · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.65 | $4.951 | 256,000 tokens | 估算o200k_base |
| QwQ 32Bdeepinfra/Qwen/QwQ-32B · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.40 | 131,072 tokens | 估算o200k_base |
| L3 8B Lunaris v1 Turbodeepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.05 | 8,192 tokens | 估算o200k_base |
| L3.1 70B Euryale v2.2deepinfra/Sao10K/L3.1-70B-Euryale-v2.2 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.85 | $0.85 | 131,072 tokens | 估算o200k_base |
| L3.3 70B Euryale v2.3deepinfra/Sao10K/L3.3-70B-Euryale-v2.3 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.65 | $0.75 | 131,072 tokens | 估算o200k_base |
| Step 3.7 Flashdeepinfra/stepfun-ai/Step-3.7-Flash · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.15 | 262,144 tokens | 估算o200k_base |
| Hy3deepinfra/tencent/Hy3 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.58 | 262,144 tokens | 估算o200k_base |
| Inklingdeepinfra/thinkingmachines/Inkling · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.05 | 524,288 tokens | 估算o200k_base |
| Inkling Smalldeepinfra/thinkingmachines/Inkling-Small · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.45 | $1.20 | 524,288 tokens | 估算o200k_base |
| MiMo V2.5deepinfra/XiaomiMiMo/MiMo-V2.5 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.40 | $2.00 | 262,144 tokens | 估算o200k_base |
| MiMo V2.5 Prodeepinfra/XiaomiMiMo/MiMo-V2.5-Pro · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.00 | 1,048,576 tokens | 估算o200k_base |
| GLM 4.5deepinfra/zai-org/GLM-4.5 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 131,072 tokens | 估算o200k_base |
| GLM 4.6deepinfra/zai-org/GLM-4.6 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.50 | $2.00 | 202,752 tokens | 估算o200k_base |
| GLM 4.7deepinfra/zai-org/GLM-4.7 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.75 | 202,752 tokens | 估算o200k_base |
| GLM 4.7 Flashdeepinfra/zai-org/GLM-4.7-Flash · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.40 | 202,752 tokens | 估算o200k_base |
| GLM 5deepinfra/zai-org/GLM-5 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.08 | 202,752 tokens | 估算o200k_base |
| GLM 5.1deepinfra/zai-org/GLM-5.1 · deepinfra | LiteLLM ↗2026-10-25 UTC | $1.05 | $3.50 | 202,752 tokens | 估算o200k_base |
| GLM 5.2deepinfra/zai-org/GLM-5.2 · deepinfra | LiteLLM ↗2026-10-25 UTC | $0.75 | $2.40 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek chatdeepseek-chat · deepseek | LiteLLM ↗2026-10-25 UTC | $0.28 | $0.42 | 131,072 tokens | 估算o200k_base |
| DeepSeek flashdeepseek-flash · deepseek | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek reasonerdeepseek-reasoner · deepseek | LiteLLM ↗2026-10-25 UTC | $0.28 | $0.42 | 131,072 tokens | 估算o200k_base |
| DeepSeek v3 2 251201deepseek-v3-2-251201 · volcengine | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 98,304 tokens | 估算o200k_base |
| DeepSeek v4 flashdeepseek-v4-flash · deepseek | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 flash vision expdeepseek-v4-flash-vision-exp · deepseek | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 prodeepseek-v4-pro · deepseek | LiteLLM ↗2026-10-25 UTC | $1.32 | $3.96 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek.r1 v1:0deepseek.r1-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.35 | $5.40 | 128,000 tokens | 估算o200k_base |
| DeepSeek.v3 v1:0deepseek.v3-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.58 | $1.68 | 128,000 tokens | 估算o200k_base |
| DeepSeek.v3.2deepseek.v3.2 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.62 | $1.85 | 164,000 tokens | 估算o200k_base |
| DeepSeek chatdeepseek/deepseek-chat · deepseek | LiteLLM ↗2026-10-25 UTC | $0.28 | $0.42 | 131,072 tokens | 估算o200k_base |
| DeepSeek coderdeepseek/deepseek-coder · deepseek | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 128,000 tokens | 估算o200k_base |
| DeepSeek flashdeepseek/deepseek-flash · deepseek | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek r1deepseek/deepseek-r1 · deepseek | LiteLLM ↗2026-10-25 UTC | $0.55 | $2.19 | 65,536 tokens | 估算o200k_base |
| DeepSeek reasonerdeepseek/deepseek-reasoner · deepseek | LiteLLM ↗2026-10-25 UTC | $0.28 | $0.42 | 131,072 tokens | 估算o200k_base |
| DeepSeek v3deepseek/deepseek-v3 · deepseek | LiteLLM ↗2026-10-25 UTC | $0.27 | $1.10 | 65,536 tokens | 估算o200k_base |
| DeepSeek v3.2deepseek/deepseek-v3.2 · deepseek | LiteLLM ↗2026-10-25 UTC | $0.28 | $0.40 | 163,840 tokens | 估算o200k_base |
| DeepSeek v4 flashdeepseek/deepseek-v4-flash · deepseek | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 flash vision expdeepseek/deepseek-v4-flash-vision-exp · deepseek | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 prodeepseek/deepseek-v4-pro · deepseek | LiteLLM ↗2026-10-25 UTC | $1.32 | $3.96 | 1,000,000 tokens | 估算o200k_base |
| eu.amazon.nova 2 lite v1:0eu.amazon.nova-2-lite-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.429 | $3.597 | 1,000,000 tokens | 估算o200k_base |
| eu.amazon.nova 2 pro preview 20251202 v1:0eu.amazon.nova-2-pro-preview-20251202-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.375 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| eu.amazon.nova lite v1:0eu.amazon.nova-lite-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.078 | $0.312 | 300,000 tokens | 估算o200k_base |
| eu.amazon.nova micro v1:0eu.amazon.nova-micro-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.046 | $0.184 | 128,000 tokens | 估算o200k_base |
| eu.amazon.nova pro v1:0eu.amazon.nova-pro-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.05 | $4.20 | 300,000 tokens | 估算o200k_base |
| eu.anthropic.Claude 3 5 haiku 20241022 v1:0eu.anthropic.claude-3-5-haiku-20241022-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.80 | $4.00 | 200,000 tokens | 估算o200k_base |
| eu.anthropic.Claude 3 5 sonnet 20240620 v1:0eu.anthropic.claude-3-5-sonnet-20240620-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| eu.anthropic.Claude 3 5 sonnet 20241022 v2:0eu.anthropic.claude-3-5-sonnet-20241022-v2:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| eu.anthropic.Claude 3 7 sonnet 20250219 v1:0eu.anthropic.claude-3-7-sonnet-20250219-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| eu.anthropic.Claude 3 opus 20240229 v1:0eu.anthropic.claude-3-opus-20240229-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| eu.anthropic.Claude fable 5eu.anthropic.claude-fable-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $11.00 | $55.00 | 1,000,000 tokens | 估算o200k_base |
| eu.anthropic.Claude fable 5 1eu.anthropic.claude-fable-5-1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $11.00 | $55.00 | 1,000,000 tokens | 估算o200k_base |
| eu.anthropic.Claude haiku 4 5 20251001 v1:0eu.anthropic.claude-haiku-4-5-20251001-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.10 | $5.50 | 200,000 tokens | 估算o200k_base |
| eu.anthropic.Claude haiku 5 5eu.anthropic.claude-haiku-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.11 | $0.55 | 1,000,000 tokens | 估算o200k_base |
| eu.anthropic.Claude opus 4 1 20250805 v1:0eu.anthropic.claude-opus-4-1-20250805-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| eu.anthropic.Claude opus 4 20250514 v1:0eu.anthropic.claude-opus-4-20250514-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| eu.anthropic.Claude opus 4 5 20251101 v1:0eu.anthropic.claude-opus-4-5-20251101-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 200,000 tokens | 估算o200k_base |
| eu.anthropic.Claude opus 4 6 v1eu.anthropic.claude-opus-4-6-v1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| eu.anthropic.Claude opus 4 7eu.anthropic.claude-opus-4-7 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| eu.anthropic.Claude opus 4 8eu.anthropic.claude-opus-4-8 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| eu.anthropic.Claude opus 5eu.anthropic.claude-opus-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| eu.anthropic.Claude opus 5 5eu.anthropic.claude-opus-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $4.40 | $22.00 | 1,000,000 tokens | 估算o200k_base |
| eu.anthropic.Claude sonnet 4 20250514 v1:0eu.anthropic.claude-sonnet-4-20250514-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| eu.anthropic.Claude sonnet 4 5 20250929 v1:0eu.anthropic.claude-sonnet-4-5-20250929-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 200,000 tokens | 估算o200k_base |
| eu.anthropic.Claude sonnet 4 6eu.anthropic.claude-sonnet-4-6 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 1,000,000 tokens | 估算o200k_base |
| eu.anthropic.Claude sonnet 5eu.anthropic.claude-sonnet-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| eu.anthropic.Claude sonnet 5 5eu.anthropic.claude-sonnet-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| eu.DeepSeek.v3.2eu.deepseek.v3.2 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.74 | $2.22 | 163,840 tokens | 估算o200k_base |
| eu.meta.llama3 2 1b instruct v1:0eu.meta.llama3-2-1b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.13 | 128,000 tokens | 估算o200k_base |
| eu.meta.llama3 2 3b instruct v1:0eu.meta.llama3-2-3b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.19 | $0.19 | 128,000 tokens | 估算o200k_base |
| eu.Mistral.pixtral large 2502 v1:0eu.mistral.pixtral-large-2502-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| Qwerky 72Bfeatherless_ai/featherless-ai/Qwerky-72B · featherless_ai | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 32,768 tokens | 估算o200k_base |
| Qwerky QwQ 32Bfeatherless_ai/featherless-ai/Qwerky-QwQ-32B · featherless_ai | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 32,768 tokens | 估算o200k_base |
| chronos hermes 13b v2fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| code Llama 13bfireworks_ai/accounts/fireworks/models/code-llama-13b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 16,384 tokens | 估算o200k_base |
| code Llama 13b instructfireworks_ai/accounts/fireworks/models/code-llama-13b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 16,384 tokens | 估算o200k_base |
| code Llama 13b pythonfireworks_ai/accounts/fireworks/models/code-llama-13b-python · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 16,384 tokens | 估算o200k_base |
| code Llama 34bfireworks_ai/accounts/fireworks/models/code-llama-34b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 16,384 tokens | 估算o200k_base |
| code Llama 34b instructfireworks_ai/accounts/fireworks/models/code-llama-34b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 16,384 tokens | 估算o200k_base |
| code Llama 34b pythonfireworks_ai/accounts/fireworks/models/code-llama-34b-python · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 16,384 tokens | 估算o200k_base |
| code Llama 70bfireworks_ai/accounts/fireworks/models/code-llama-70b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| code Llama 70b instructfireworks_ai/accounts/fireworks/models/code-llama-70b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| code Llama 70b pythonfireworks_ai/accounts/fireworks/models/code-llama-70b-python · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| code Llama 7bfireworks_ai/accounts/fireworks/models/code-llama-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 16,384 tokens | 估算o200k_base |
| code Llama 7b instructfireworks_ai/accounts/fireworks/models/code-llama-7b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 16,384 tokens | 估算o200k_base |
| code Llama 7b pythonfireworks_ai/accounts/fireworks/models/code-llama-7b-python · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 16,384 tokens | 估算o200k_base |
| code Qwen 1p5 7bfireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 65,536 tokens | 估算o200k_base |
| codegemma 2bfireworks_ai/accounts/fireworks/models/codegemma-2b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 8,192 tokens | 估算o200k_base |
| codegemma 7bfireworks_ai/accounts/fireworks/models/codegemma-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| cogito 671b v2 p1fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 163,840 tokens | 估算o200k_base |
| cogito v1 preview Llama 3bfireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| cogito v1 preview Llama 70bfireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| cogito v1 preview Llama 8bfireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| cogito v1 preview Qwen 14bfireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| cogito v1 preview Qwen 32bfireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| dbrx instructfireworks_ai/accounts/fireworks/models/dbrx-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 32,768 tokens | 估算o200k_base |
| DeepSeek coder 1b basefireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 16,384 tokens | 估算o200k_base |
| DeepSeek coder 33b instructfireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 16,384 tokens | 估算o200k_base |
| DeepSeek coder 7b basefireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| DeepSeek coder 7b base v1p5fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| DeepSeek coder 7b instruct v1p5fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| DeepSeek coder v2 instructfireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 65,536 tokens | 估算o200k_base |
| DeepSeek coder v2 lite basefireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.50 | 163,840 tokens | 估算o200k_base |
| DeepSeek coder v2 lite instructfireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.50 | 163,840 tokens | 估算o200k_base |
| DeepSeek prover v2fireworks_ai/accounts/fireworks/models/deepseek-prover-v2 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 163,840 tokens | 估算o200k_base |
| DeepSeek r1fireworks_ai/accounts/fireworks/models/deepseek-r1 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $8.00 | 163,840 tokens | 估算o200k_base |
| DeepSeek r1 0528fireworks_ai/accounts/fireworks/models/deepseek-r1-0528 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $8.00 | 163,840 tokens | 估算o200k_base |
| DeepSeek r1 0528 distill qwen3 8bfireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| DeepSeek r1 basicfireworks_ai/accounts/fireworks/models/deepseek-r1-basic · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.55 | $2.19 | 163,840 tokens | 估算o200k_base |
| DeepSeek r1 distill Llama 70bfireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| DeepSeek r1 distill Llama 8bfireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| DeepSeek r1 distill Qwen 14bfireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| DeepSeek r1 distill Qwen 1p5bfireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| DeepSeek r1 distill Qwen 32bfireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| DeepSeek r1 distill Qwen 7bfireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| DeepSeek v2 lite chatfireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.50 | 163,840 tokens | 估算o200k_base |
| DeepSeek v2p5fireworks_ai/accounts/fireworks/models/deepseek-v2p5 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 32,768 tokens | 估算o200k_base |
| DeepSeek v3fireworks_ai/accounts/fireworks/models/deepseek-v3 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| DeepSeek v3 0324fireworks_ai/accounts/fireworks/models/deepseek-v3-0324 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 163,840 tokens | 估算o200k_base |
| DeepSeek v3p1fireworks_ai/accounts/fireworks/models/deepseek-v3p1 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.56 | $1.68 | 128,000 tokens | 估算o200k_base |
| DeepSeek v3p1 terminusfireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.56 | $1.68 | 128,000 tokens | 估算o200k_base |
| DeepSeek v3p2fireworks_ai/accounts/fireworks/models/deepseek-v3p2 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.56 | $1.68 | 163,840 tokens | 估算o200k_base |
| DeepSeek v4 flashfireworks_ai/accounts/fireworks/models/deepseek-v4-flash · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 flash 0731fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.66 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 flash vision expfireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.66 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 profireworks_ai/accounts/fireworks/models/deepseek-v4-pro · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 pro 0813fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.32 | $3.96 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4p1 flashfireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4p1 flash 1017fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4p1 flash 1017 usfireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.45 | $1.80 | 1,048,576 tokens | 估算o200k_base |
| devstral small 2505fireworks_ai/accounts/fireworks/models/devstral-small-2505 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| dobby mini unhinged plus Llama 3 1 8bfireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| dobby unhinged Llama 3 3 70b newfireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| dolphin 2 9 2 qwen2 72bfireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| dolphin 2p6 mixtral 8x7bfireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.50 | 32,768 tokens | 估算o200k_base |
| ember 1fireworks_ai/accounts/fireworks/models/ember-1 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,048,576 tokens | 估算o200k_base |
| ernie 4p5 21b a3b ptfireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| ernie 4p5 300b a47b ptfireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| fare 20bfireworks_ai/accounts/fireworks/models/fare-20b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| firefunction v1fireworks_ai/accounts/fireworks/models/firefunction-v1 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.50 | 32,768 tokens | 估算o200k_base |
| firefunction v2fireworks_ai/accounts/fireworks/models/firefunction-v2 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 8,192 tokens | 估算o200k_base |
| firellava 13bfireworks_ai/accounts/fireworks/models/firellava-13b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| firesearch ocr v6fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| flux 1 devfireworks_ai/accounts/fireworks/models/flux-1-dev · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 4,096 tokens | 估算o200k_base |
| flux 1 dev controlnet unionfireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.001 | $0.001 | 4,096 tokens | 估算o200k_base |
| flux 1 schnellfireworks_ai/accounts/fireworks/models/flux-1-schnell · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 4,096 tokens | 估算o200k_base |
| gemma 2b itfireworks_ai/accounts/fireworks/models/gemma-2b-it · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 8,192 tokens | 估算o200k_base |
| gemma 3 27b itfireworks_ai/accounts/fireworks/models/gemma-3-27b-it · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| gemma 7bfireworks_ai/accounts/fireworks/models/gemma-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| gemma 7b itfireworks_ai/accounts/fireworks/models/gemma-7b-it · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| gemma2 9b itfireworks_ai/accounts/fireworks/models/gemma2-9b-it · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| glm 4p5fireworks_ai/accounts/fireworks/models/glm-4p5 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.55 | $2.19 | 131,072 tokens | 估算o200k_base |
| glm 4p5 airfireworks_ai/accounts/fireworks/models/glm-4p5-air · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.88 | 131,072 tokens | 估算o200k_base |
| glm 4p5vfireworks_ai/accounts/fireworks/models/glm-4p5v · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 131,072 tokens | 估算o200k_base |
| glm 4p6fireworks_ai/accounts/fireworks/models/glm-4p6 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.55 | $2.19 | 202,752 tokens | 估算o200k_base |
| glm 4p7fireworks_ai/accounts/fireworks/models/glm-4p7 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 202,752 tokens | 估算o200k_base |
| glm 5p1fireworks_ai/accounts/fireworks/models/glm-5p1 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 202,752 tokens | 估算o200k_base |
| glm 5p2fireworks_ai/accounts/fireworks/models/glm-5p2 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| glm 5p3fireworks_ai/accounts/fireworks/models/glm-5p3 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| glm 5p3 flashfireworks_ai/accounts/fireworks/models/glm-5p3-flash · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,048,576 tokens | 估算o200k_base |
| GPT oss 120bfireworks_ai/accounts/fireworks/models/gpt-oss-120b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| GPT oss 20bfireworks_ai/accounts/fireworks/models/gpt-oss-20b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.30 | 131,072 tokens | 估算o200k_base |
| GPT oss safeguard 120bfireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 131,072 tokens | 估算o200k_base |
| GPT oss safeguard 20bfireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.50 | 131,072 tokens | 估算o200k_base |
| hermes 2 pro Mistral 7bfireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| inklingfireworks_ai/accounts/fireworks/models/inkling · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.00 | $4.05 | 1,048,576 tokens | 估算o200k_base |
| internvl3 38bfireworks_ai/accounts/fireworks/models/internvl3-38b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 16,384 tokens | 估算o200k_base |
| internvl3 78bfireworks_ai/accounts/fireworks/models/internvl3-78b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 16,384 tokens | 估算o200k_base |
| internvl3 8bfireworks_ai/accounts/fireworks/models/internvl3-8b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 16,384 tokens | 估算o200k_base |
| kat coderfireworks_ai/accounts/fireworks/models/kat-coder · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 262,144 tokens | 估算o200k_base |
| kat dev 32bfireworks_ai/accounts/fireworks/models/kat-dev-32b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| kat dev 72b expfireworks_ai/accounts/fireworks/models/kat-dev-72b-exp · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| kimi k2 instructfireworks_ai/accounts/fireworks/models/kimi-k2-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 131,072 tokens | 估算o200k_base |
| kimi k2 instruct 0905fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 262,144 tokens | 估算o200k_base |
| kimi k2 thinkingfireworks_ai/accounts/fireworks/models/kimi-k2-thinking · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 262,144 tokens | 估算o200k_base |
| kimi k2p5fireworks_ai/accounts/fireworks/models/kimi-k2p5 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.00 | 262,144 tokens | 估算o200k_base |
| kimi k2p6fireworks_ai/accounts/fireworks/models/kimi-k2p6 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| kimi k2p7 codefireworks_ai/accounts/fireworks/models/kimi-k2p7-code · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| kimi k3fireworks_ai/accounts/fireworks/models/kimi-k3 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,048,576 tokens | 估算o200k_base |
| Llama guard 2 8bfireworks_ai/accounts/fireworks/models/llama-guard-2-8b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| Llama guard 3 1bfireworks_ai/accounts/fireworks/models/llama-guard-3-1b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| Llama guard 3 8bfireworks_ai/accounts/fireworks/models/llama-guard-3-8b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| Llama v2 13bfireworks_ai/accounts/fireworks/models/llama-v2-13b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| Llama v2 13b chatfireworks_ai/accounts/fireworks/models/llama-v2-13b-chat · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| Llama v2 70bfireworks_ai/accounts/fireworks/models/llama-v2-70b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 4,096 tokens | 估算o200k_base |
| Llama v2 70b chatfireworks_ai/accounts/fireworks/models/llama-v2-70b-chat · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 2,048 tokens | 估算o200k_base |
| Llama v2 7bfireworks_ai/accounts/fireworks/models/llama-v2-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| Llama v2 7b chatfireworks_ai/accounts/fireworks/models/llama-v2-7b-chat · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| Llama v3 70b instructfireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 8,192 tokens | 估算o200k_base |
| Llama v3 70b instruct hffireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 8,192 tokens | 估算o200k_base |
| Llama v3 8bfireworks_ai/accounts/fireworks/models/llama-v3-8b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| Llama v3 8b instruct hffireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| Llama v3p1 405b instructfireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $3.00 | 131,072 tokens | 估算o200k_base |
| Llama v3p1 405b instruct longfireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 4,096 tokens | 估算o200k_base |
| Llama v3p1 70b instructfireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| Llama v3p1 70b instruct 1bfireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 4,096 tokens | 估算o200k_base |
| Llama v3p1 8b instructfireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| Llama v3p1 nemotron 70b instructfireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| Llama v3p2 11b vision instructfireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| Llama v3p2 1bfireworks_ai/accounts/fireworks/models/llama-v3p2-1b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| Llama v3p2 1b instructfireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| Llama v3p2 3bfireworks_ai/accounts/fireworks/models/llama-v3p2-3b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| Llama v3p2 3b instructfireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| Llama v3p2 90b vision instructfireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| Llama v3p3 70b instructfireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| llama4 maverick instruct basicfireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.88 | 131,072 tokens | 估算o200k_base |
| llama4 scout instruct basicfireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| llamaguard 7bfireworks_ai/accounts/fireworks/models/llamaguard-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| llava yi 34bfireworks_ai/accounts/fireworks/models/llava-yi-34b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| minimax m1 80kfireworks_ai/accounts/fireworks/models/minimax-m1-80k · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 4,096 tokens | 估算o200k_base |
| minimax m2fireworks_ai/accounts/fireworks/models/minimax-m2 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,608 tokens | 估算o200k_base |
| minimax m2p1fireworks_ai/accounts/fireworks/models/minimax-m2p1 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,608 tokens | 估算o200k_base |
| minimax m2p7fireworks_ai/accounts/fireworks/models/minimax-m2p7 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 196,608 tokens | 估算o200k_base |
| minimax m3fireworks_ai/accounts/fireworks/models/minimax-m3 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 512,000 tokens | 估算o200k_base |
| minimax m3p1 flashfireworks_ai/accounts/fireworks/models/minimax-m3p1-flash · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 1,048,576 tokens | 估算o200k_base |
| ministral 3 14b instruct 2512fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 256,000 tokens | 估算o200k_base |
| ministral 3 3b instruct 2512fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 256,000 tokens | 估算o200k_base |
| ministral 3 8b instruct 2512fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 256,000 tokens | 估算o200k_base |
| Mistral 7bfireworks_ai/accounts/fireworks/models/mistral-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| Mistral 7b instruct 4kfireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| Mistral 7b instruct v0p2fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| Mistral 7b instruct v3fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| Mistral 7b v0p2fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| Mistral large 3 fp8fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 256,000 tokens | 估算o200k_base |
| Mistral nemo base 2407fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 128,000 tokens | 估算o200k_base |
| Mistral nemo instruct 2407fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 128,000 tokens | 估算o200k_base |
| Mistral small 24b instruct 2501fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 32,768 tokens | 估算o200k_base |
| mixtral 8x22bfireworks_ai/accounts/fireworks/models/mixtral-8x22b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 65,536 tokens | 估算o200k_base |
| mixtral 8x22b instructfireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 65,536 tokens | 估算o200k_base |
| mixtral 8x22b instruct hffireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 65,536 tokens | 估算o200k_base |
| mixtral 8x7bfireworks_ai/accounts/fireworks/models/mixtral-8x7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.50 | 32,768 tokens | 估算o200k_base |
| mixtral 8x7b instructfireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.50 | 32,768 tokens | 估算o200k_base |
| mixtral 8x7b instruct hffireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.50 | 32,768 tokens | 估算o200k_base |
| muse glimmer 30bfireworks_ai/accounts/fireworks/models/muse-glimmer-30b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.35 | $1.50 | 131,072 tokens | 估算o200k_base |
| muse spark openfireworks_ai/accounts/fireworks/models/muse-spark-open · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.25 | $4.25 | 1,048,576 tokens | 估算o200k_base |
| mythomax l2 13bfireworks_ai/accounts/fireworks/models/mythomax-l2-13b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| nemotron 3 ultra nvfp4fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 262,144 tokens | 估算o200k_base |
| nemotron lightning 3p5 30b a3bfireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 262,144 tokens | 估算o200k_base |
| nemotron nano v2 12b vlfireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| nous capybara 7b v1p9fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| nous hermes 2 mixtral 8x7b dpofireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.50 | 32,768 tokens | 估算o200k_base |
| nous hermes 2 yi 34bfireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| nous hermes llama2 13bfireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| nous hermes llama2 70bfireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| nous hermes llama2 7bfireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| nvidia nemotron nano 12b v2fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 128,000 tokens | 估算o200k_base |
| nvidia nemotron nano 9b v2fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 128,000 tokens | 估算o200k_base |
| openchat 3p5 0106 7bfireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| openhermes 2 Mistral 7bfireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| openhermes 2p5 Mistral 7bfireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| openorca 7bfireworks_ai/accounts/fireworks/models/openorca-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| phi 2 3bfireworks_ai/accounts/fireworks/models/phi-2-3b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 2,048 tokens | 估算o200k_base |
| phi 3 mini 128k instructfireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| phi 3 vision 128k instructfireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,064 tokens | 估算o200k_base |
| phind code Llama 34b python v1fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 16,384 tokens | 估算o200k_base |
| phind code Llama 34b v1fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 16,384 tokens | 估算o200k_base |
| phind code Llama 34b v2fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 16,384 tokens | 估算o200k_base |
| pythia 12bfireworks_ai/accounts/fireworks/models/pythia-12b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 2,048 tokens | 估算o200k_base |
| Qwen qwq 32b previewfireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 32,768 tokens | 估算o200k_base |
| Qwen v2p5 14b instructfireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| Qwen v2p5 7bfireworks_ai/accounts/fireworks/models/qwen-v2p5-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| qwen1p5 72b chatfireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 32,768 tokens | 估算o200k_base |
| qwen2 72b instructfireworks_ai/accounts/fireworks/models/qwen2-72b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 32,768 tokens | 估算o200k_base |
| qwen2 7b instructfireworks_ai/accounts/fireworks/models/qwen2-7b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| qwen2 vl 2b instructfireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 32,768 tokens | 估算o200k_base |
| qwen2 vl 72b instructfireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 32,768 tokens | 估算o200k_base |
| qwen2 vl 7b instructfireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| qwen2p5 0p5b instructfireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 32,768 tokens | 估算o200k_base |
| qwen2p5 14bfireworks_ai/accounts/fireworks/models/qwen2p5-14b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| qwen2p5 1p5b instructfireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 32,768 tokens | 估算o200k_base |
| qwen2p5 32bfireworks_ai/accounts/fireworks/models/qwen2p5-32b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| qwen2p5 32b instructfireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 32,768 tokens | 估算o200k_base |
| qwen2p5 72bfireworks_ai/accounts/fireworks/models/qwen2p5-72b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| qwen2p5 72b instructfireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 32,768 tokens | 估算o200k_base |
| qwen2p5 7b instructfireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| qwen2p5 coder 0p5bfireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 32,768 tokens | 估算o200k_base |
| qwen2p5 coder 0p5b instructfireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 32,768 tokens | 估算o200k_base |
| qwen2p5 coder 14bfireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| qwen2p5 coder 14b instructfireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| qwen2p5 coder 1p5bfireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 32,768 tokens | 估算o200k_base |
| qwen2p5 coder 1p5b instructfireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 32,768 tokens | 估算o200k_base |
| qwen2p5 coder 32bfireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 32,768 tokens | 估算o200k_base |
| qwen2p5 coder 32b instructfireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| qwen2p5 coder 32b instruct 128kfireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| qwen2p5 coder 32b instruct 32k ropefireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 32,768 tokens | 估算o200k_base |
| qwen2p5 coder 32b instruct 64kfireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 65,536 tokens | 估算o200k_base |
| qwen2p5 coder 3bfireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 32,768 tokens | 估算o200k_base |
| qwen2p5 coder 3b instructfireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 32,768 tokens | 估算o200k_base |
| qwen2p5 coder 7bfireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| qwen2p5 coder 7b instructfireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| qwen2p5 math 72b instructfireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| qwen2p5 vl 32b instructfireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 128,000 tokens | 估算o200k_base |
| qwen2p5 vl 3b instructfireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 128,000 tokens | 估算o200k_base |
| qwen2p5 vl 72b instructfireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 128,000 tokens | 估算o200k_base |
| qwen2p5 vl 7b instructfireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 128,000 tokens | 估算o200k_base |
| qwen3 0p6bfireworks_ai/accounts/fireworks/models/qwen3-0p6b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 40,960 tokens | 估算o200k_base |
| qwen3 14bfireworks_ai/accounts/fireworks/models/qwen3-14b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 40,960 tokens | 估算o200k_base |
| qwen3 1p7bfireworks_ai/accounts/fireworks/models/qwen3-1p7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| qwen3 1p7b fp8 draftfireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 262,144 tokens | 估算o200k_base |
| qwen3 1p7b fp8 draft 131072fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| qwen3 1p7b fp8 draft 40960fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 40,960 tokens | 估算o200k_base |
| qwen3 235b a22bfireworks_ai/accounts/fireworks/models/qwen3-235b-a22b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.88 | 131,072 tokens | 估算o200k_base |
| qwen3 235b a22b instruct 2507fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.88 | 262,144 tokens | 估算o200k_base |
| qwen3 235b a22b thinking 2507fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.88 | 262,144 tokens | 估算o200k_base |
| qwen3 30b a3bfireworks_ai/accounts/fireworks/models/qwen3-30b-a3b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| qwen3 30b a3b instruct 2507fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $0.50 | 262,144 tokens | 估算o200k_base |
| qwen3 30b a3b thinking 2507fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 262,144 tokens | 估算o200k_base |
| qwen3 32bfireworks_ai/accounts/fireworks/models/qwen3-32b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| qwen3 4bfireworks_ai/accounts/fireworks/models/qwen3-4b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 40,960 tokens | 估算o200k_base |
| qwen3 4b instruct 2507fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 262,144 tokens | 估算o200k_base |
| qwen3 8bfireworks_ai/accounts/fireworks/models/qwen3-8b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 40,960 tokens | 估算o200k_base |
| qwen3 coder 30b a3b instructfireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 262,144 tokens | 估算o200k_base |
| qwen3 coder 480b a35b instructfireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.45 | $1.80 | 262,144 tokens | 估算o200k_base |
| qwen3 coder 480b instruct bf16fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 262,144 tokens | 估算o200k_base |
| qwen3 next 80b a3b instructfireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| qwen3 next 80b a3b thinkingfireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| qwen3 vl 235b a22b instructfireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.88 | 262,144 tokens | 估算o200k_base |
| qwen3 vl 235b a22b thinkingfireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.88 | 262,144 tokens | 估算o200k_base |
| qwen3 vl 30b a3b instructfireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 262,144 tokens | 估算o200k_base |
| qwen3 vl 30b a3b thinkingfireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 262,144 tokens | 估算o200k_base |
| qwen3 vl 32b instructfireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| qwen3 vl 8b instructfireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 262,144 tokens | 估算o200k_base |
| qwen3p7 plusfireworks_ai/accounts/fireworks/models/qwen3p7-plus · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 262,144 tokens | 估算o200k_base |
| qwen3p8 maxfireworks_ai/accounts/fireworks/models/qwen3p8-max · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 262,144 tokens | 估算o200k_base |
| qwq 32bfireworks_ai/accounts/fireworks/models/qwq-32b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 131,072 tokens | 估算o200k_base |
| rolm ocrfireworks_ai/accounts/fireworks/models/rolm-ocr · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 128,000 tokens | 估算o200k_base |
| snorkel Mistral 7b pairrm dpofireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| stablecode 3bfireworks_ai/accounts/fireworks/models/stablecode-3b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 4,096 tokens | 估算o200k_base |
| starcoder 16bfireworks_ai/accounts/fireworks/models/starcoder-16b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| starcoder 7bfireworks_ai/accounts/fireworks/models/starcoder-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| starcoder2 15bfireworks_ai/accounts/fireworks/models/starcoder2-15b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 16,384 tokens | 估算o200k_base |
| starcoder2 3bfireworks_ai/accounts/fireworks/models/starcoder2-3b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 16,384 tokens | 估算o200k_base |
| starcoder2 7bfireworks_ai/accounts/fireworks/models/starcoder2-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 16,384 tokens | 估算o200k_base |
| toppy m 7bfireworks_ai/accounts/fireworks/models/toppy-m-7b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| yi 34bfireworks_ai/accounts/fireworks/models/yi-34b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| yi 34b 200k capybarafireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 200,000 tokens | 估算o200k_base |
| yi 34b chatfireworks_ai/accounts/fireworks/models/yi-34b-chat · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 4,096 tokens | 估算o200k_base |
| yi 6bfireworks_ai/accounts/fireworks/models/yi-6b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 4,096 tokens | 估算o200k_base |
| yi largefireworks_ai/accounts/fireworks/models/yi-large · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $3.00 | 32,768 tokens | 估算o200k_base |
| zephyr 7b betafireworks_ai/accounts/fireworks/models/zephyr-7b-beta · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| DeepSeek v4p1 flash usfireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-us · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.45 | $1.80 | 1,048,576 tokens | 估算o200k_base |
| glm 5p1 fastfireworks_ai/accounts/fireworks/routers/glm-5p1-fast · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.80 | $8.80 | 202,800 tokens | 估算o200k_base |
| glm 5p2 fastfireworks_ai/accounts/fireworks/routers/glm-5p2-fast · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.10 | $6.60 | 1,048,576 tokens | 估算o200k_base |
| glm 5p2 fast usfireworks_ai/accounts/fireworks/routers/glm-5p2-fast-us · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.10 | $6.60 | 1,048,576 tokens | 估算o200k_base |
| glm 5p3 fastfireworks_ai/accounts/fireworks/routers/glm-5p3-fast · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.10 | $6.60 | 1,048,576 tokens | 估算o200k_base |
| glm 5p3 flash usfireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.225 | $0.75 | 1,048,576 tokens | 估算o200k_base |
| glm 5p3 usfireworks_ai/accounts/fireworks/routers/glm-5p3-us · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.10 | $6.60 | 1,048,576 tokens | 估算o200k_base |
| kimi k2p6 fastfireworks_ai/accounts/fireworks/routers/kimi-k2p6-fast · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 262,144 tokens | 估算o200k_base |
| kimi k2p7 code fastfireworks_ai/accounts/fireworks/routers/kimi-k2p7-code-fast · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.90 | $8.00 | 262,144 tokens | 估算o200k_base |
| kimi k3 fastfireworks_ai/accounts/fireworks/routers/kimi-k3-fast · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $4.50 | $22.50 | 1,048,576 tokens | 估算o200k_base |
| kimi k3 usfireworks_ai/accounts/fireworks/routers/kimi-k3-us · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $4.50 | $22.50 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 flashfireworks_ai/deepseek-v4-flash · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 flash 0731fireworks_ai/deepseek-v4-flash-0731 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.66 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 flash vision expfireworks_ai/deepseek-v4-flash-vision-exp · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.66 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 pro 0813fireworks_ai/deepseek-v4-pro-0813 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.32 | $3.96 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4p1 flashfireworks_ai/deepseek-v4p1-flash · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4p1 flash usfireworks_ai/deepseek-v4p1-flash-us · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.45 | $1.80 | 1,048,576 tokens | 估算o200k_base |
| glm 4p7fireworks_ai/glm-4p7 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 202,752 tokens | 估算o200k_base |
| glm 5p1fireworks_ai/glm-5p1 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 202,752 tokens | 估算o200k_base |
| glm 5p1 fastfireworks_ai/glm-5p1-fast · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.80 | $8.80 | 202,800 tokens | 估算o200k_base |
| glm 5p2fireworks_ai/glm-5p2 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| glm 5p2 fastfireworks_ai/glm-5p2-fast · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.10 | $6.60 | 1,048,576 tokens | 估算o200k_base |
| glm 5p2 fast usfireworks_ai/glm-5p2-fast-us · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.10 | $6.60 | 1,048,576 tokens | 估算o200k_base |
| glm 5p3fireworks_ai/glm-5p3 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| glm 5p3 fastfireworks_ai/glm-5p3-fast · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.10 | $6.60 | 1,048,576 tokens | 估算o200k_base |
| glm 5p3 flashfireworks_ai/glm-5p3-flash · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,048,576 tokens | 估算o200k_base |
| glm 5p3 flash usfireworks_ai/glm-5p3-flash-us · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.225 | $0.75 | 1,048,576 tokens | 估算o200k_base |
| glm 5p3 usfireworks_ai/glm-5p3-us · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.10 | $6.60 | 1,048,576 tokens | 估算o200k_base |
| GPT oss 120bfireworks_ai/gpt-oss-120b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| GPT oss 20bfireworks_ai/gpt-oss-20b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.30 | 131,072 tokens | 估算o200k_base |
| kimi k2p5fireworks_ai/kimi-k2p5 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.00 | 262,144 tokens | 估算o200k_base |
| kimi k2p6fireworks_ai/kimi-k2p6 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| kimi k2p6 fastfireworks_ai/kimi-k2p6-fast · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 262,144 tokens | 估算o200k_base |
| kimi k2p7 codefireworks_ai/kimi-k2p7-code · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| kimi k2p7 code fastfireworks_ai/kimi-k2p7-code-fast · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $1.90 | $8.00 | 262,144 tokens | 估算o200k_base |
| kimi k3fireworks_ai/kimi-k3 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,048,576 tokens | 估算o200k_base |
| kimi k3 fastfireworks_ai/kimi-k3-fast · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $4.50 | $22.50 | 1,048,576 tokens | 估算o200k_base |
| kimi k3 usfireworks_ai/kimi-k3-us · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $4.50 | $22.50 | 1,048,576 tokens | 估算o200k_base |
| minimax m2p1fireworks_ai/minimax-m2p1 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,608 tokens | 估算o200k_base |
| minimax m3fireworks_ai/minimax-m3 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 512,000 tokens | 估算o200k_base |
| muse glimmer 30bfireworks_ai/muse-glimmer-30b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.35 | $1.50 | 131,072 tokens | 估算o200k_base |
| nemotron 3 ultra nvfp4fireworks_ai/nemotron-3-ultra-nvfp4 · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 262,144 tokens | 估算o200k_base |
| nemotron lightning 3p5 30b a3bfireworks_ai/nemotron-lightning-3p5-30b-a3b · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 262,144 tokens | 估算o200k_base |
| qwen3p7 plusfireworks_ai/qwen3p7-plus · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 262,144 tokens | 估算o200k_base |
| qwen3p8 maxfireworks_ai/qwen3p8-max · fireworks_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 262,144 tokens | 估算o200k_base |
| DeepSeek V3.2friendliai/deepseek-ai/DeepSeek-V3.2 · friendliai | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 163,840 tokens | 估算o200k_base |
| gemma 4 31B itfriendliai/google/gemma-4-31B-it · friendliai | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.40 | 262,144 tokens | 估算o200k_base |
| MiniMax M2.5friendliai/MiniMaxAI/MiniMax-M2.5 · friendliai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,608 tokens | 估算o200k_base |
| GLM 5.1friendliai/zai-org/GLM-5.1 · friendliai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 202,752 tokens | 估算o200k_base |
| GLM 5.2friendliai/zai-org/GLM-5.2 · friendliai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| GLM 5.3friendliai/zai-org/GLM-5.3 · friendliai | LiteLLM ↗2026-10-25 UTC | $1.26 | $3.96 | 1,048,576 tokens | 估算o200k_base |
| GLM 5.3 Flashfriendliai/zai-org/GLM-5.3-Flash · friendliai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,048,576 tokens | 估算o200k_base |
| ft:GPT 3.5 turboft:gpt-3.5-turbo · openai | LiteLLM ↗2026-10-25 UTC | $3.00 | $6.00 | 16,385 tokens | 估算o200k_base |
| ft:GPT 3.5 turbo 0125ft:gpt-3.5-turbo-0125 · openai | LiteLLM ↗2026-10-25 UTC | $3.00 | $6.00 | 16,385 tokens | 估算o200k_base |
| ft:GPT 3.5 turbo 0613ft:gpt-3.5-turbo-0613 · openai | LiteLLM ↗2026-10-25 UTC | $3.00 | $6.00 | 4,096 tokens | 估算o200k_base |
| ft:GPT 3.5 turbo 1106ft:gpt-3.5-turbo-1106 · openai | LiteLLM ↗2026-10-25 UTC | $3.00 | $6.00 | 16,385 tokens | 估算o200k_base |
| ft:GPT 4 0613ft:gpt-4-0613 · openai | LiteLLM ↗2026-10-25 UTC | $30.00 | $60.00 | 8,192 tokens | 估算o200k_base |
| ft:GPT 4.1 2025 04 14ft:gpt-4.1-2025-04-14 · openai | LiteLLM ↗2026-10-25 UTC | $3.00 | $12.00 | 1,047,576 tokens | 估算o200k_base |
| ft:GPT 4.1 mini 2025 04 14ft:gpt-4.1-mini-2025-04-14 · openai | LiteLLM ↗2026-10-25 UTC | $0.80 | $3.20 | 1,047,576 tokens | 估算o200k_base |
| ft:GPT 4.1 nano 2025 04 14ft:gpt-4.1-nano-2025-04-14 · openai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.80 | 1,047,576 tokens | 估算o200k_base |
| ft:GPT 4o 2024 08 06ft:gpt-4o-2024-08-06 · openai | LiteLLM ↗2026-10-25 UTC | $3.75 | $15.00 | 128,000 tokens | 估算o200k_base |
| ft:GPT 4o 2024 11 20ft:gpt-4o-2024-11-20 · openai | LiteLLM ↗2026-10-25 UTC | $3.75 | $15.00 | 128,000 tokens | 估算o200k_base |
| ft:GPT 4o mini 2024 07 18ft:gpt-4o-mini-2024-07-18 · openai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 128,000 tokens | 估算o200k_base |
| ft:o4 mini 2025 04 16ft:o4-mini-2025-04-16 · openai | LiteLLM ↗2026-10-25 UTC | $4.00 | $16.00 | 200,000 tokens | 估算o200k_base |
| Gemini 2.5 computer use preview 10 2025gemini-2.5-computer-use-preview-10-2025 · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 128,000 tokens | 估算o200k_base |
| Gemini 2.5 Flashgemini-2.5-flash · Google | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 2.5 flash litegemini-2.5-flash-lite · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 1,048,576 tokens | 估算o200k_base |
| Gemini 2.5 flash lite preview 09 2025gemini-2.5-flash-lite-preview-09-2025 · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 1,048,576 tokens | 估算o200k_base |
| Gemini 2.5 flash preview 09 2025gemini-2.5-flash-preview-09-2025 · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 2.5 progemini-2.5-pro · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 2.5 pro preview ttsgemini-2.5-pro-preview-tts · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $1.00 | $20.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3 flash previewgemini-3-flash-preview · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.50 | $3.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 flash litegemini-3.1-flash-lite · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 flash lite previewgemini-3.1-flash-lite-preview · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 pro previewgemini-3.1-pro-preview · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 pro preview customtoolsgemini-3.1-pro-preview-customtools · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.5 flashgemini-3.5-flash · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $1.50 | $9.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.5 flash litegemini-3.5-flash-lite · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.6 flashgemini-3.6-flash · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.7 flashgemini-3.7-flash · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.8 flashgemini-3.8-flash · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.8 flash cybergemini-3.8-flash-cyber · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini exp 1206gemini-exp-1206 · gemini | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini flash latestgemini-flash-latest · gemini | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,048,576 tokens | 估算o200k_base |
| Gemini flash lite latestgemini-flash-lite-latest · gemini | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini omni flash previewgemini-omni-flash-preview · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $1.50 | $9.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini pro latestgemini-pro-latest · gemini | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini robotics er 1.5 previewgemini-robotics-er-1.5-preview · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini robotics er 2 previewgemini-robotics-er-2-preview · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 131,072 tokens | 估算o200k_base |
| deep research max preview 04 2026gemini/deep-research-max-preview-04-2026 · gemini | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| deep research preview 04 2026gemini/deep-research-preview-04-2026 · gemini | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| deep research pro preview 12 2025gemini/deep-research-pro-preview-12-2025 · gemini | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 2.5 computer use preview 10 2025gemini/gemini-2.5-computer-use-preview-10-2025 · gemini | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 128,000 tokens | 估算o200k_base |
| Gemini 2.5 flashgemini/gemini-2.5-flash · gemini | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 2.5 flash litegemini/gemini-2.5-flash-lite · gemini | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 1,048,576 tokens | 估算o200k_base |
| Gemini 2.5 progemini/gemini-2.5-pro · gemini | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 2.5 pro preview ttsgemini/gemini-2.5-pro-preview-tts · gemini | LiteLLM ↗2026-10-25 UTC | $1.00 | $20.00 | 8,192 tokens | 估算o200k_base |
| Gemini 3 flash previewgemini/gemini-3-flash-preview · gemini | LiteLLM ↗2026-10-25 UTC | $0.50 | $3.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 flash litegemini/gemini-3.1-flash-lite · gemini | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 flash lite previewgemini/gemini-3.1-flash-lite-preview · gemini | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 pro previewgemini/gemini-3.1-pro-preview · gemini | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 pro preview customtoolsgemini/gemini-3.1-pro-preview-customtools · gemini | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.5 flashgemini/gemini-3.5-flash · gemini | LiteLLM ↗2026-10-25 UTC | $1.50 | $9.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.5 flash litegemini/gemini-3.5-flash-lite · gemini | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.6 flashgemini/gemini-3.6-flash · gemini | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.7 flashgemini/gemini-3.7-flash · gemini | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.8 flashgemini/gemini-3.8-flash · gemini | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,048,576 tokens | 估算o200k_base |
| Gemini 4 argongemini/gemini-4-argon · gemini | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini exp 1114gemini/gemini-exp-1114 · gemini | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini exp 1206gemini/gemini-exp-1206 · gemini | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 2,097,152 tokens | 估算o200k_base |
| Gemini flash latestgemini/gemini-flash-latest · gemini | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,048,576 tokens | 估算o200k_base |
| Gemini flash lite latestgemini/gemini-flash-lite-latest · gemini | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini gemma 2 27b itgemini/gemini-gemma-2-27b-it · gemini | LiteLLM ↗2026-10-25 UTC | $0.35 | $1.05 | 8,192 tokens | 估算o200k_base |
| Gemini gemma 2 9b itgemini/gemini-gemma-2-9b-it · gemini | LiteLLM ↗2026-10-25 UTC | $0.35 | $1.05 | 8,192 tokens | 估算o200k_base |
| Gemini omni 1.1 flashgemini/gemini-omni-1.1-flash · gemini | LiteLLM ↗2026-10-25 UTC | $1.50 | $9.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini omni flash previewgemini/gemini-omni-flash-preview · gemini | LiteLLM ↗2026-10-25 UTC | $1.50 | $9.00 | 131,072 tokens | 估算o200k_base |
| Gemini pro latestgemini/gemini-pro-latest · gemini | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini robotics er 2 previewgemini/gemini-robotics-er-2-preview · gemini | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 131,072 tokens | 估算o200k_base |
| Gemini robotics er 2 streaming previewgemini/gemini-robotics-er-2-streaming-preview · gemini | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 131,072 tokens | 估算o200k_base |
| gemma 3 27b itgemini/gemma-3-27b-it · gemini | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 131,072 tokens | 估算o200k_base |
| gemma 4 26b a4b itgemini/gemma-4-26b-a4b-it · gemini | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 262,144 tokens | 估算o200k_base |
| gemma 4 31b itgemini/gemma-4-31b-it · gemini | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 262,144 tokens | 估算o200k_base |
| learnlm 1.5 pro experimentalgemini/learnlm-1.5-pro-experimental · gemini | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,767 tokens | 估算o200k_base |
| lyria 3 clip previewgemini/lyria-3-clip-preview · gemini | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 131,072 tokens | 估算o200k_base |
| lyria 3 pro previewgemini/lyria-3-pro-preview · gemini | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 131,072 tokens | 估算o200k_base |
| lyria 3.5gemini/lyria-3.5 · gemini | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 131,072 tokens | 估算o200k_base |
| lyria 3.5 clip previewgemini/lyria-3.5-clip-preview · gemini | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 131,072 tokens | 估算o200k_base |
| lyria 3.5 pro previewgemini/lyria-3.5-pro-preview · gemini | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 131,072 tokens | 估算o200k_base |
| lyria realtime expgemini/lyria-realtime-exp · gemini | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 1,048,576 tokens | 估算o200k_base |
| GigaChat 2gigachat/GigaChat-2 · gigachat | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 128,000 tokens | 估算o200k_base |
| GigaChat 2 Maxgigachat/GigaChat-2-Max · gigachat | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 128,000 tokens | 估算o200k_base |
| GigaChat 2 Progigachat/GigaChat-2-Pro · gigachat | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 128,000 tokens | 估算o200k_base |
| Claude fable 5github_copilot/claude-fable-5 · github_copilot | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 200,000 tokens | 估算o200k_base |
| Claude fable 5.1github_copilot/claude-fable-5.1 · github_copilot | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 200,000 tokens | 估算o200k_base |
| Claude haiku 4.5github_copilot/claude-haiku-4.5 · github_copilot | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 128,000 tokens | 估算o200k_base |
| Claude haiku 5.5github_copilot/claude-haiku-5.5 · github_copilot | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 128,000 tokens | 估算o200k_base |
| Claude opus 4.8github_copilot/claude-opus-4.8 · github_copilot | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 4.8 fastgithub_copilot/claude-opus-4.8-fast · github_copilot | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 5github_copilot/claude-opus-5 · github_copilot | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 5.5github_copilot/claude-opus-5.5 · github_copilot | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 4.6github_copilot/claude-sonnet-4.6 · github_copilot | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 5github_copilot/claude-sonnet-5 · github_copilot | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 5.5github_copilot/claude-sonnet-5.5 · github_copilot | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 200,000 tokens | 估算o200k_base |
| Gemini 3.7 flashgithub_copilot/gemini-3.7-flash · github_copilot | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 200,000 tokens | 估算o200k_base |
| Gemini 3.8 flashgithub_copilot/gemini-3.8-flash · github_copilot | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 200,000 tokens | 估算o200k_base |
| Gemini 4 argongithub_copilot/gemini-4-argon · github_copilot | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 200,000 tokens | 估算o200k_base |
| GPT 3.5 turbogithub_copilot/gpt-3.5-turbo · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 16,384 tokens | 估算o200k_base |
| GPT 3.5 turbo 0613github_copilot/gpt-3.5-turbo-0613 · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 16,384 tokens | 估算o200k_base |
| GPT 4github_copilot/gpt-4 · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 32,768 tokens | 估算o200k_base |
| GPT 4 0613github_copilot/gpt-4-0613 · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 32,768 tokens | 估算o200k_base |
| GPT 4 o previewgithub_copilot/gpt-4-o-preview · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 64,000 tokens | 估算o200k_base |
| GPT 4.1github_copilot/gpt-4.1 · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 128,000 tokens | 估算o200k_base |
| GPT 4.1 2025 04 14github_copilot/gpt-4.1-2025-04-14 · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 128,000 tokens | 估算o200k_base |
| GPT 4ogithub_copilot/gpt-4o · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 64,000 tokens | 估算o200k_base |
| GPT 4o 2024 05 13github_copilot/gpt-4o-2024-05-13 · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 64,000 tokens | 估算o200k_base |
| GPT 4o 2024 08 06github_copilot/gpt-4o-2024-08-06 · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 64,000 tokens | 估算o200k_base |
| GPT 4o 2024 11 20github_copilot/gpt-4o-2024-11-20 · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 64,000 tokens | 估算o200k_base |
| GPT 4o minigithub_copilot/gpt-4o-mini · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 64,000 tokens | 估算o200k_base |
| GPT 4o mini 2024 07 18github_copilot/gpt-4o-mini-2024-07-18 · github_copilot | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 64,000 tokens | 估算o200k_base |
| GPT 5 minigithub_copilot/gpt-5-mini · github_copilot | LiteLLM ↗2026-10-25 UTC | $0.25 | $2.00 | 128,000 tokens | 估算o200k_base |
| GPT 5.4github_copilot/gpt-5.4 · github_copilot | LiteLLM ↗2026-10-25 UTC | $2.50 | $15.00 | 272,000 tokens | 估算o200k_base |
| grok 4.5github_copilot/grok-4.5 · github_copilot | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 500,000 tokens | 估算o200k_base |
| grok 4.6github_copilot/grok-4.6 · github_copilot | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 500,000 tokens | 估算o200k_base |
| grok 4.7github_copilot/grok-4.7 · github_copilot | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 500,000 tokens | 估算o200k_base |
| kimi k3github_copilot/kimi-k3 · github_copilot | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 917,504 tokens | 估算o200k_base |
| glm 4 7 251222glm-4-7-251222 · volcengine | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 204,800 tokens | 估算o200k_base |
| global.amazon.nova 2 lite v1:0global.amazon.nova-2-lite-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| global.anthropic.Claude fable 5global.anthropic.claude-fable-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| global.anthropic.Claude fable 5 1global.anthropic.claude-fable-5-1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| global.anthropic.Claude haiku 4 5 20251001 v1:0global.anthropic.claude-haiku-4-5-20251001-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| global.anthropic.Claude haiku 5 5global.anthropic.claude-haiku-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 1,000,000 tokens | 估算o200k_base |
| global.anthropic.Claude mythos 5 1global.anthropic.claude-mythos-5-1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| global.anthropic.Claude opus 4 5 20251101 v1:0global.anthropic.claude-opus-4-5-20251101-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| global.anthropic.Claude opus 4 6 v1global.anthropic.claude-opus-4-6-v1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| global.anthropic.Claude opus 4 7global.anthropic.claude-opus-4-7 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| global.anthropic.Claude opus 4 8global.anthropic.claude-opus-4-8 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| global.anthropic.Claude opus 5global.anthropic.claude-opus-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| global.anthropic.Claude opus 5 5global.anthropic.claude-opus-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 1,000,000 tokens | 估算o200k_base |
| global.anthropic.Claude sonnet 4 20250514 v1:0global.anthropic.claude-sonnet-4-20250514-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| global.anthropic.Claude sonnet 4 5 20250929 v1:0global.anthropic.claude-sonnet-4-5-20250929-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| global.anthropic.Claude sonnet 4 6global.anthropic.claude-sonnet-4-6 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,000,000 tokens | 估算o200k_base |
| global.anthropic.Claude sonnet 5global.anthropic.claude-sonnet-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| global.anthropic.Claude sonnet 5 5global.anthropic.claude-sonnet-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| global.moonshotai.kimi k3global.moonshotai.kimi-k3 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,000,000 tokens | 估算o200k_base |
| global.openai.GPT 5.4global.openai.gpt-5.4 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.50 | $15.00 | 1,050,000 tokens | 估算o200k_base |
| global.openai.GPT 5.5global.openai.gpt-5.5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 1,050,000 tokens | 估算o200k_base |
| global.openai.GPT 5.6 lunaglobal.openai.gpt-5.6-luna · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.20 | 1,050,000 tokens | 估算o200k_base |
| global.openai.GPT 5.6 solglobal.openai.gpt-5.6-sol · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 1,050,000 tokens | 估算o200k_base |
| global.openai.GPT 5.6 terraglobal.openai.gpt-5.6-terra · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,050,000 tokens | 估算o200k_base |
| global.openai.GPT 6 astraglobal.openai.gpt-6-astra · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,050,000 tokens | 估算o200k_base |
| global.openai.GPT 6 lunaglobal.openai.gpt-6-luna · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 1,050,000 tokens | 估算o200k_base |
| global.openai.GPT 6 solglobal.openai.gpt-6-sol · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,050,000 tokens | 估算o200k_base |
| global.openai.GPT 6.1 solglobal.openai.gpt-6.1-sol · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| global.twelvelabs.pegasus 1 5 v1:0global.twelvelabs.pegasus-1-5-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | $7.50 | 261,120 tokens | 估算o200k_base |
| global.xai.grok 4.6global.xai.grok-4.6 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 500,000 tokens | 估算o200k_base |
| global.xai.grok 4.7global.xai.grok-4.7 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 524,288 tokens | 估算o200k_base |
| global.zai.glm 5.3global.zai.glm-5.3 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.68 | $5.28 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4gmi/anthropic/claude-opus-4 · gmi | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 409,600 tokens | 估算o200k_base |
| Claude opus 4.5gmi/anthropic/claude-opus-4.5 · gmi | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 409,600 tokens | 估算o200k_base |
| Claude sonnet 4gmi/anthropic/claude-sonnet-4 · gmi | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 409,600 tokens | 估算o200k_base |
| Claude sonnet 4.5gmi/anthropic/claude-sonnet-4.5 · gmi | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 409,600 tokens | 估算o200k_base |
| DeepSeek V3 0324gmi/deepseek-ai/DeepSeek-V3-0324 · gmi | LiteLLM ↗2026-10-25 UTC | $0.28 | $0.88 | 163,840 tokens | 估算o200k_base |
| DeepSeek V3.2gmi/deepseek-ai/DeepSeek-V3.2 · gmi | LiteLLM ↗2026-10-25 UTC | $0.28 | $0.40 | 163,840 tokens | 估算o200k_base |
| Gemini 3 flash previewgmi/google/gemini-3-flash-preview · gmi | LiteLLM ↗2026-10-25 UTC | $0.50 | $3.00 | 1,048,576 tokens | 估算o200k_base |
| MiniMax M2.1gmi/MiniMaxAI/MiniMax-M2.1 · gmi | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,608 tokens | 估算o200k_base |
| Kimi K2 Thinkinggmi/moonshotai/Kimi-K2-Thinking · gmi | LiteLLM ↗2026-10-25 UTC | $0.80 | $1.20 | 262,144 tokens | 估算o200k_base |
| GPT 4ogmi/openai/gpt-4o · gmi | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 131,072 tokens | 估算o200k_base |
| GPT 4o minigmi/openai/gpt-4o-mini · gmi | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| GPT 5gmi/openai/gpt-5 · gmi | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 409,600 tokens | 估算o200k_base |
| GPT 5.1gmi/openai/gpt-5.1 · gmi | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 409,600 tokens | 估算o200k_base |
| GPT 5.2gmi/openai/gpt-5.2 · gmi | LiteLLM ↗2026-10-25 UTC | $1.75 | $14.00 | 409,600 tokens | 估算o200k_base |
| Qwen3 VL 235B A22B Instruct FP8gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8 · gmi | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.40 | 262,144 tokens | 估算o200k_base |
| GLM 4.7 FP8gmi/zai-org/GLM-4.7-FP8 · gmi | LiteLLM ↗2026-10-25 UTC | $0.40 | $2.00 | 202,752 tokens | 估算o200k_base |
| google.gemma 3 12b itgoogle.gemma-3-12b-it · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.29 | 128,000 tokens | 估算o200k_base |
| google.gemma 3 27b itgoogle.gemma-3-27b-it · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.23 | $0.38 | 128,000 tokens | 估算o200k_base |
| google.gemma 3 4b itgoogle.gemma-3-4b-it · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.08 | 128,000 tokens | 估算o200k_base |
| GPT 3.5 turbogpt-3.5-turbo · openai | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 16,385 tokens | 估算cl100k_base |
| GPT 3.5 turbo 0125gpt-3.5-turbo-0125 · openai | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 16,385 tokens | 估算cl100k_base |
| GPT 3.5 turbo 1106gpt-3.5-turbo-1106 · openai | LiteLLM ↗2026-10-25 UTC | $1.00 | $2.00 | 16,385 tokens | 估算cl100k_base |
| GPT 3.5 turbo 16kgpt-3.5-turbo-16k · openai | LiteLLM ↗2026-10-25 UTC | $3.00 | $4.00 | 16,385 tokens | 估算cl100k_base |
| GPT 4gpt-4 · openai | LiteLLM ↗2026-10-25 UTC | $30.00 | $60.00 | 8,192 tokens | 估算cl100k_base |
| GPT 4 0613gpt-4-0613 · openai | LiteLLM ↗2026-10-25 UTC | $30.00 | $60.00 | 8,192 tokens | 估算cl100k_base |
| GPT 4 1106 previewgpt-4-1106-preview · openai | LiteLLM ↗2026-10-25 UTC | $10.00 | $30.00 | 128,000 tokens | 估算cl100k_base |
| GPT 4 turbogpt-4-turbo · openai | LiteLLM ↗2026-10-25 UTC | $10.00 | $30.00 | 128,000 tokens | 估算cl100k_base |
| GPT 4 turbo 2024 04 09gpt-4-turbo-2024-04-09 · openai | LiteLLM ↗2026-10-25 UTC | $10.00 | $30.00 | 128,000 tokens | 估算cl100k_base |
| GPT-4.1gpt-4.1 · OpenAI | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 1,047,576 tokens | 精确o200k_base |
| GPT 4.1 2025 04 14gpt-4.1-2025-04-14 · openai | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 1,047,576 tokens | 估算o200k_base |
| GPT-4.1 minigpt-4.1-mini · OpenAI | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 1,047,576 tokens | 精确o200k_base |
| GPT 4.1 mini 2025 04 14gpt-4.1-mini-2025-04-14 · openai | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 1,047,576 tokens | 估算o200k_base |
| GPT 4.1 nanogpt-4.1-nano · openai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 1,047,576 tokens | 估算o200k_base |
| GPT 4.1 nano 2025 04 14gpt-4.1-nano-2025-04-14 · openai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 1,047,576 tokens | 估算o200k_base |
| GPT-4ogpt-4o · OpenAI | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 精确o200k_base |
| GPT 4o 2024 05 13gpt-4o-2024-05-13 · openai | LiteLLM ↗2026-10-25 UTC | $5.00 | $15.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 08 06gpt-4o-2024-08-06 · openai | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o 2024 11 20gpt-4o-2024-11-20 · openai | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o audio preview 2024 12 17gpt-4o-audio-preview-2024-12-17 · openai | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o audio preview 2025 06 03gpt-4o-audio-preview-2025-06-03 · openai | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT-4o minigpt-4o-mini · OpenAI | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 精确o200k_base |
| GPT 4o mini 2024 07 18gpt-4o-mini-2024-07-18 · openai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| GPT 4o mini audio preview 2024 12 17gpt-4o-mini-audio-preview-2024-12-17 · openai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| GPT 4o mini search previewgpt-4o-mini-search-preview · openai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| GPT 4o mini search preview 2025 03 11gpt-4o-mini-search-preview-2025-03-11 · openai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| GPT 4o search previewgpt-4o-search-preview · openai | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o search preview 2025 03 11gpt-4o-search-preview-2025-03-11 · openai | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 5gpt-5 · openai | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 272,000 tokens | 估算o200k_base |
| GPT 5 2025 08 07gpt-5-2025-08-07 · openai | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 272,000 tokens | 估算o200k_base |
| GPT 5 chatgpt-5-chat · openai | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 5 chat latestgpt-5-chat-latest · openai | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 5 minigpt-5-mini · openai | LiteLLM ↗2026-10-25 UTC | $0.25 | $2.00 | 272,000 tokens | 估算o200k_base |
| GPT 5 mini 2025 08 07gpt-5-mini-2025-08-07 · openai | LiteLLM ↗2026-10-25 UTC | $0.25 | $2.00 | 272,000 tokens | 估算o200k_base |
| GPT 5 nanogpt-5-nano · openai | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.40 | 272,000 tokens | 估算o200k_base |
| GPT 5 nano 2025 08 07gpt-5-nano-2025-08-07 · openai | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.40 | 272,000 tokens | 估算o200k_base |
| GPT 5 search apigpt-5-search-api · openai | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 272,000 tokens | 估算o200k_base |
| GPT 5 search api 2025 10 14gpt-5-search-api-2025-10-14 · openai | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 272,000 tokens | 估算o200k_base |
| GPT 5.1gpt-5.1 · openai | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 272,000 tokens | 估算o200k_base |
| GPT 5.1 2025 11 13gpt-5.1-2025-11-13 · openai | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 272,000 tokens | 估算o200k_base |
| GPT 5.1 chat latestgpt-5.1-chat-latest · openai | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 5.2gpt-5.2 · openai | LiteLLM ↗2026-10-25 UTC | $1.75 | $14.00 | 272,000 tokens | 估算o200k_base |
| GPT 5.2 2025 12 11gpt-5.2-2025-12-11 · openai | LiteLLM ↗2026-10-25 UTC | $1.75 | $14.00 | 272,000 tokens | 估算o200k_base |
| GPT 5.2 chat latestgpt-5.2-chat-latest · openai | LiteLLM ↗2026-10-25 UTC | $1.75 | $14.00 | 128,000 tokens | 估算o200k_base |
| GPT 5.3 chat latestgpt-5.3-chat-latest · openai | LiteLLM ↗2026-10-25 UTC | $1.75 | $14.00 | 128,000 tokens | 估算o200k_base |
| GPT 5.4gpt-5.4 · openai | LiteLLM ↗2026-10-25 UTC | $2.50 | $15.00 | 1,050,000 tokens | 估算o200k_base |
| GPT 5.4 2026 03 05gpt-5.4-2026-03-05 · openai | LiteLLM ↗2026-10-25 UTC | $2.50 | $15.00 | 1,050,000 tokens | 估算o200k_base |
| GPT 5.4 minigpt-5.4-mini · openai | LiteLLM ↗2026-10-25 UTC | $0.75 | $4.50 | 272,000 tokens | 估算o200k_base |
| GPT 5.4 mini 2026 03 17gpt-5.4-mini-2026-03-17 · openai | LiteLLM ↗2026-10-25 UTC | $0.75 | $4.50 | 272,000 tokens | 估算o200k_base |
| GPT 5.4 nanogpt-5.4-nano · openai | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.25 | 272,000 tokens | 估算o200k_base |
| GPT 5.4 nano 2026 03 17gpt-5.4-nano-2026-03-17 · openai | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.25 | 272,000 tokens | 估算o200k_base |
| GPT 5.5gpt-5.5 · openai | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 1,050,000 tokens | 估算o200k_base |
| GPT 5.5 2026 04 23gpt-5.5-2026-04-23 · openai | LiteLLM ↗2026-10-25 UTC | $5.00 | $30.00 | 1,050,000 tokens | 估算o200k_base |
| GPT 5.6gpt-5.6 · openai | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 cybergpt-5.6-cyber · openai | LiteLLM ↗2026-10-25 UTC | $12.50 | $75.00 | 400,000 tokens | 估算o200k_base |
| GPT 5.6 lunagpt-5.6-luna · openai | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.20 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 solgpt-5.6-sol · openai | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 922,000 tokens | 估算o200k_base |
| GPT 5.6 terragpt-5.6-terra · openai | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 922,000 tokens | 估算o200k_base |
| GPT 6 astragpt-6-astra · openai | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 922,000 tokens | 估算o200k_base |
| GPT 6 lunagpt-6-luna · openai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 922,000 tokens | 估算o200k_base |
| GPT 6 solgpt-6-sol · openai | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 922,000 tokens | 估算o200k_base |
| GPT 6.1 solgpt-6.1-sol · openai | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 922,000 tokens | 估算o200k_base |
| GPT audiogpt-audio · openai | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT audio 1.5gpt-audio-1.5 · openai | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT audio 2025 08 28gpt-audio-2025-08-28 · openai | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT audio minigpt-audio-mini · openai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 128,000 tokens | 估算o200k_base |
| GPT audio mini 2025 10 06gpt-audio-mini-2025-10-06 · openai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 128,000 tokens | 估算o200k_base |
| GPT audio mini 2025 12 15gpt-audio-mini-2025-12-15 · openai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 128,000 tokens | 估算o200k_base |
| alibaba qwen3 32bgradient_ai/alibaba-qwen3-32b · gradient_ai | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 131,072 tokens | 估算o200k_base |
| anthropic Claude 3 opusgradient_ai/anthropic-claude-3-opus · gradient_ai | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| anthropic Claude 3.5 haikugradient_ai/anthropic-claude-3.5-haiku · gradient_ai | LiteLLM ↗2026-10-25 UTC | $0.80 | $4.00 | 200,000 tokens | 估算o200k_base |
| anthropic Claude 3.5 sonnetgradient_ai/anthropic-claude-3.5-sonnet · gradient_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| anthropic Claude 3.7 sonnetgradient_ai/anthropic-claude-3.7-sonnet · gradient_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| DeepSeek r1 distill Llama 70bgradient_ai/deepseek-r1-distill-llama-70b · gradient_ai | LiteLLM ↗2026-10-25 UTC | $0.99 | $0.99 | 32,768 tokens | 估算o200k_base |
| llama3 8b instructgradient_ai/llama3-8b-instruct · gradient_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| llama3.3 70b instructgradient_ai/llama3.3-70b-instruct · gradient_ai | LiteLLM ↗2026-10-25 UTC | $0.65 | $0.65 | 128,000 tokens | 估算o200k_base |
| Mistral nemo instruct 2407gradient_ai/mistral-nemo-instruct-2407 · gradient_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.30 | 128,000 tokens | 估算o200k_base |
| openai GPT 4ogradient_ai/openai-gpt-4o · gradient_ai | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 128,000 tokens | 估算o200k_base |
| openai GPT 4o minigradient_ai/openai-gpt-4o-mini · gradient_ai | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 128,000 tokens | 估算o200k_base |
| openai o3gradient_ai/openai-o3 · gradient_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 200,000 tokens | 估算o200k_base |
| openai o3 minigradient_ai/openai-o3-mini · gradient_ai | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 200,000 tokens | 估算o200k_base |
| Llama guard 3 8bgroq/llama-guard-3-8b · groq | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| Llama prompt guard 2 22mgroq/meta-llama/llama-prompt-guard-2-22m · groq | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.03 | 512 tokens | 估算o200k_base |
| Llama prompt guard 2 86mgroq/meta-llama/llama-prompt-guard-2-86m · groq | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.04 | 512 tokens | 估算o200k_base |
| GPT oss 120bgroq/openai/gpt-oss-120b · groq | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| GPT oss 20bgroq/openai/gpt-oss-20b · groq | LiteLLM ↗2026-10-25 UTC | $0.075 | $0.30 | 131,072 tokens | 估算o200k_base |
| GPT oss safeguard 20bgroq/openai/gpt-oss-safeguard-20b · groq | LiteLLM ↗2026-10-25 UTC | $0.075 | $0.30 | 131,072 tokens | 估算o200k_base |
| qwen3.8 27bgroq/qwen/qwen3.8-27b · groq | LiteLLM ↗2026-10-25 UTC | $0.80 | $4.00 | 131,072 tokens | 估算o200k_base |
| Claude 3 5 haikuheroku/claude-3-5-haiku · heroku | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 200,000 tokens | 估算o200k_base |
| Claude 3 5 sonnet latestheroku/claude-3-5-sonnet-latest · heroku | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 200,000 tokens | 估算o200k_base |
| Claude 3 7 sonnetheroku/claude-3-7-sonnet · heroku | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 200,000 tokens | 估算o200k_base |
| Claude 4 sonnetheroku/claude-4-sonnet · heroku | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 200,000 tokens | 估算o200k_base |
| DeepSeek R1hyperbolic/deepseek-ai/DeepSeek-R1 · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.40 | $0.40 | 32,768 tokens | 估算o200k_base |
| DeepSeek R1 0528hyperbolic/deepseek-ai/DeepSeek-R1-0528 · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.25 | 131,072 tokens | 估算o200k_base |
| DeepSeek V3hyperbolic/deepseek-ai/DeepSeek-V3 · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| DeepSeek V3 0324hyperbolic/deepseek-ai/DeepSeek-V3-0324 · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.40 | $0.40 | 32,768 tokens | 估算o200k_base |
| Llama 3.2 3B Instructhyperbolic/meta-llama/Llama-3.2-3B-Instruct · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 32,768 tokens | 估算o200k_base |
| Llama 3.3 70B Instructhyperbolic/meta-llama/Llama-3.3-70B-Instruct · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 131,072 tokens | 估算o200k_base |
| Meta Llama 3 70B Instructhyperbolic/meta-llama/Meta-Llama-3-70B-Instruct · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 131,072 tokens | 估算o200k_base |
| Meta Llama 3.1 405B Instructhyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 32,768 tokens | 估算o200k_base |
| Meta Llama 3.1 70B Instructhyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 32,768 tokens | 估算o200k_base |
| Meta Llama 3.1 8B Instructhyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 32,768 tokens | 估算o200k_base |
| Kimi K2 Instructhyperbolic/moonshotai/Kimi-K2-Instruct · hyperbolic | LiteLLM ↗2026-10-25 UTC | $2.00 | $2.00 | 131,072 tokens | 估算o200k_base |
| Hermes 3 Llama 3.1 70Bhyperbolic/NousResearch/Hermes-3-Llama-3.1-70B · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 32,768 tokens | 估算o200k_base |
| Qwen2.5 72B Instructhyperbolic/Qwen/Qwen2.5-72B-Instruct · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 131,072 tokens | 估算o200k_base |
| Qwen2.5 Coder 32B Instructhyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 32,768 tokens | 估算o200k_base |
| Qwen3 235B A22Bhyperbolic/Qwen/Qwen3-235B-A22B · hyperbolic | LiteLLM ↗2026-10-25 UTC | $2.00 | $2.00 | 131,072 tokens | 估算o200k_base |
| QwQ 32Bhyperbolic/Qwen/QwQ-32B · hyperbolic | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| in.moonshotai.kimi k3in.moonshotai.kimi-k3 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 1,000,000 tokens | 估算o200k_base |
| mercury 2inception/mercury-2 · inception | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.75 | 128,000 tokens | 估算o200k_base |
| mercury 2.5inception/mercury-2.5 · inception | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.75 | 260,000 tokens | 估算o200k_base |
| DeepSeek V3inferenceapis/deepseek-ai/DeepSeek-V3 · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.19 | $0.38 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Flashinferenceapis/deepseek-ai/DeepSeek-V4-Flash · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.19 | $0.38 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Flash 0731inferenceapis/deepseek-ai/DeepSeek-V4-Flash-0731 · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.19 | $0.38 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Proinferenceapis/deepseek-ai/DeepSeek-V4-Pro · inferenceapis | LiteLLM ↗2026-10-25 UTC | $1.72 | $5.15 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Pro 0813inferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813 · inferenceapis | LiteLLM ↗2026-10-25 UTC | $1.72 | $5.15 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4.1 Flashinferenceapis/deepseek-ai/DeepSeek-V4.1-Flash · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek chatinferenceapis/deepseek-chat · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.19 | $0.38 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek flashinferenceapis/deepseek-flash · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek reasonerinferenceapis/deepseek-reasoner · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.19 | $0.38 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v3inferenceapis/deepseek-v3 · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.19 | $0.38 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 flashinferenceapis/deepseek-v4-flash · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.19 | $0.38 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 proinferenceapis/deepseek-v4-pro · inferenceapis | LiteLLM ↗2026-10-25 UTC | $1.72 | $5.15 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4.1 flashinferenceapis/deepseek-v4.1-flash · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 1,048,576 tokens | 估算o200k_base |
| glm 5.3inferenceapis/glm-5.3 · inferenceapis | LiteLLM ↗2026-10-25 UTC | $1.82 | $5.72 | 1,048,575 tokens | 估算o200k_base |
| glm 5.3 flashinferenceapis/glm-5.3-flash · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.66 | 1,048,575 tokens | 估算o200k_base |
| GPT oss 120binferenceapis/gpt-oss-120b · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.80 | 131,072 tokens | 估算o200k_base |
| GPT oss 20binferenceapis/gpt-oss-20b · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.19 | 131,072 tokens | 估算o200k_base |
| kimi k2.7 codeinferenceapis/kimi-k2.7-code · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.89 | $4.42 | 262,144 tokens | 估算o200k_base |
| Llama 3.1 8b instantinferenceapis/llama-3.1-8b-instant · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.50 | 131,072 tokens | 估算o200k_base |
| Llama 3.3 70binferenceapis/llama-3.3-70b · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.50 | 131,072 tokens | 估算o200k_base |
| Llama 3.3 70b instructinferenceapis/llama-3.3-70b-instruct · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.50 | 131,072 tokens | 估算o200k_base |
| Llama 3.3 70b versatileinferenceapis/llama-3.3-70b-versatile · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.50 | 131,072 tokens | 估算o200k_base |
| Llama 3.3 70B Instructinferenceapis/meta-llama/Llama-3.3-70B-Instruct · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.50 | 131,072 tokens | 估算o200k_base |
| Llama 3.3 70B Instruct Turboinferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.50 | 131,072 tokens | 估算o200k_base |
| minimax m3inferenceapis/minimax-m3 · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.39 | $1.56 | 524,288 tokens | 估算o200k_base |
| MiniMax M3inferenceapis/MiniMaxAI/MiniMax-M3 · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.39 | $1.56 | 524,288 tokens | 估算o200k_base |
| Kimi K2.7 Codeinferenceapis/moonshotai/Kimi-K2.7-Code · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.89 | $4.42 | 262,144 tokens | 估算o200k_base |
| GPT oss 120binferenceapis/openai/gpt-oss-120b · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.80 | 131,072 tokens | 估算o200k_base |
| GPT oss 20binferenceapis/openai/gpt-oss-20b · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.19 | 131,072 tokens | 估算o200k_base |
| Qwen3 VL 235B A22B Instructinferenceapis/Qwen/Qwen3-VL-235B-A22B-Instruct · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.26 | $1.15 | 262,144 tokens | 估算o200k_base |
| Qwen3.8 Flashinferenceapis/Qwen/Qwen3.8-Flash · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,000,000 tokens | 估算o200k_base |
| qwen3 vlinferenceapis/qwen3-vl · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.26 | $1.15 | 262,144 tokens | 估算o200k_base |
| qwen3 vl 235binferenceapis/qwen3-vl-235b · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.26 | $1.15 | 262,144 tokens | 估算o200k_base |
| qwen3.8 flashinferenceapis/qwen3.8-flash · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,000,000 tokens | 估算o200k_base |
| GLM 5.3inferenceapis/zai-org/GLM-5.3 · inferenceapis | LiteLLM ↗2026-10-25 UTC | $1.82 | $5.72 | 1,048,575 tokens | 估算o200k_base |
| GLM 5.3 Flashinferenceapis/zai-org/GLM-5.3-Flash · inferenceapis | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.66 | 1,048,575 tokens | 估算o200k_base |
| jamba 1.5jamba-1.5 · ai21 | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 256,000 tokens | 估算o200k_base |
| jamba 1.5 largejamba-1.5-large · ai21 | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 256,000 tokens | 估算o200k_base |
| jamba 1.5 large@001jamba-1.5-large@001 · ai21 | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 256,000 tokens | 估算o200k_base |
| jamba 1.5 minijamba-1.5-mini · ai21 | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 256,000 tokens | 估算o200k_base |
| jamba 1.5 mini@001jamba-1.5-mini@001 · ai21 | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 256,000 tokens | 估算o200k_base |
| jamba large 1.6jamba-large-1.6 · ai21 | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 256,000 tokens | 估算o200k_base |
| jamba large 1.7jamba-large-1.7 · ai21 | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 256,000 tokens | 估算o200k_base |
| jamba mini 1.6jamba-mini-1.6 · ai21 | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 256,000 tokens | 估算o200k_base |
| jamba mini 1.7jamba-mini-1.7 · ai21 | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 256,000 tokens | 估算o200k_base |
| jp.amazon.nova 2 lite v1:0jp.amazon.nova-2-lite-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.396 | $3.311 | 1,000,000 tokens | 估算o200k_base |
| jp.anthropic.Claude haiku 4 5 20251001 v1:0jp.anthropic.claude-haiku-4-5-20251001-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.10 | $5.50 | 200,000 tokens | 估算o200k_base |
| jp.anthropic.Claude haiku 5 5jp.anthropic.claude-haiku-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.11 | $0.55 | 1,000,000 tokens | 估算o200k_base |
| jp.anthropic.Claude opus 4 7jp.anthropic.claude-opus-4-7 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| jp.anthropic.Claude opus 4 8jp.anthropic.claude-opus-4-8 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| jp.anthropic.Claude opus 5jp.anthropic.claude-opus-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| jp.anthropic.Claude opus 5 5jp.anthropic.claude-opus-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $4.40 | $22.00 | 1,000,000 tokens | 估算o200k_base |
| jp.anthropic.Claude sonnet 4 5 20250929 v1:0jp.anthropic.claude-sonnet-4-5-20250929-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 200,000 tokens | 估算o200k_base |
| jp.anthropic.Claude sonnet 4 6jp.anthropic.claude-sonnet-4-6 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 1,000,000 tokens | 估算o200k_base |
| jp.anthropic.Claude sonnet 5jp.anthropic.claude-sonnet-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| jp.anthropic.Claude sonnet 5 5jp.anthropic.claude-sonnet-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| kimi k2 thinking 251104kimi-k2-thinking-251104 · volcengine | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 229,376 tokens | 估算o200k_base |
| DeepSeek llama3.3 70blambda_ai/deepseek-llama3.3-70b · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 131,072 tokens | 估算o200k_base |
| DeepSeek r1 0528lambda_ai/deepseek-r1-0528 · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 131,072 tokens | 估算o200k_base |
| DeepSeek r1 671blambda_ai/deepseek-r1-671b · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.80 | $0.80 | 131,072 tokens | 估算o200k_base |
| DeepSeek v3 0324lambda_ai/deepseek-v3-0324 · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 131,072 tokens | 估算o200k_base |
| hermes3 405blambda_ai/hermes3-405b · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.80 | $0.80 | 131,072 tokens | 估算o200k_base |
| hermes3 70blambda_ai/hermes3-70b · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 131,072 tokens | 估算o200k_base |
| hermes3 8blambda_ai/hermes3-8b · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.025 | $0.04 | 131,072 tokens | 估算o200k_base |
| lfm 40blambda_ai/lfm-40b · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.20 | 131,072 tokens | 估算o200k_base |
| lfm 7blambda_ai/lfm-7b · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.025 | $0.04 | 131,072 tokens | 估算o200k_base |
| Llama 4 maverick 17b 128e instruct fp8lambda_ai/llama-4-maverick-17b-128e-instruct-fp8 · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.10 | 131,072 tokens | 估算o200k_base |
| Llama 4 scout 17b 16e instructlambda_ai/llama-4-scout-17b-16e-instruct · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.10 | 16,384 tokens | 估算o200k_base |
| llama3.1 405b instruct fp8lambda_ai/llama3.1-405b-instruct-fp8 · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.80 | $0.80 | 131,072 tokens | 估算o200k_base |
| llama3.1 70b instruct fp8lambda_ai/llama3.1-70b-instruct-fp8 · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 131,072 tokens | 估算o200k_base |
| llama3.1 8b instructlambda_ai/llama3.1-8b-instruct · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.025 | $0.04 | 131,072 tokens | 估算o200k_base |
| llama3.1 nemotron 70b instruct fp8lambda_ai/llama3.1-nemotron-70b-instruct-fp8 · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 131,072 tokens | 估算o200k_base |
| llama3.2 11b vision instructlambda_ai/llama3.2-11b-vision-instruct · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.015 | $0.025 | 131,072 tokens | 估算o200k_base |
| llama3.2 3b instructlambda_ai/llama3.2-3b-instruct · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.015 | $0.025 | 131,072 tokens | 估算o200k_base |
| llama3.3 70b instruct fp8lambda_ai/llama3.3-70b-instruct-fp8 · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.30 | 131,072 tokens | 估算o200k_base |
| qwen25 coder 32b instructlambda_ai/qwen25-coder-32b-instruct · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.10 | 131,072 tokens | 估算o200k_base |
| qwen3 32b fp8lambda_ai/qwen3-32b-fp8 · lambda_ai | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.10 | 131,072 tokens | 估算o200k_base |
| Gemma 3 4b it GGUFlemonade/Gemma-3-4b-it-GGUF · lemonade | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 128,000 tokens | 估算o200k_base |
| GPT oss 120b mxfp GGUFlemonade/gpt-oss-120b-mxfp-GGUF · lemonade | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 131,072 tokens | 估算o200k_base |
| GPT oss 20b mxfp4 GGUFlemonade/gpt-oss-20b-mxfp4-GGUF · lemonade | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 131,072 tokens | 估算o200k_base |
| Qwen3 4B Instruct 2507 GGUFlemonade/Qwen3-4B-Instruct-2507-GGUF · lemonade | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 262,144 tokens | 估算o200k_base |
| Qwen3 Coder 30B A3B Instruct GGUFlemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF · lemonade | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 262,144 tokens | 估算o200k_base |
| DeepSeek v4 flashlibertai/deepseek-v4-flash · libertai | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.75 | 200,000 tokens | 估算o200k_base |
| DeepSeek v4 flash thinkinglibertai/deepseek-v4-flash-thinking · libertai | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.75 | 200,000 tokens | 估算o200k_base |
| gemma 4 31b itlibertai/gemma-4-31b-it · libertai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.40 | 262,144 tokens | 估算o200k_base |
| gemma 4 31b it thinkinglibertai/gemma-4-31b-it-thinking · libertai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.40 | 262,144 tokens | 估算o200k_base |
| hermes 3 8b teelibertai/hermes-3-8b-tee · libertai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 16,000 tokens | 估算o200k_base |
| qwen3.5 122b a10blibertai/qwen3.5-122b-a10b · libertai | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.75 | 262,144 tokens | 估算o200k_base |
| qwen3.5 122b a10b thinkinglibertai/qwen3.5-122b-a10b-thinking · libertai | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.75 | 262,144 tokens | 估算o200k_base |
| qwen3.6 27blibertai/qwen3.6-27b · libertai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 262,144 tokens | 估算o200k_base |
| qwen3.6 27b thinkinglibertai/qwen3.6-27b-thinking · libertai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 262,144 tokens | 估算o200k_base |
| qwen3.6 35b a3blibertai/qwen3.6-35b-a3b · libertai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 262,144 tokens | 估算o200k_base |
| qwen3.6 35b a3b thinkinglibertai/qwen3.6-35b-a3b-thinking · libertai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 262,144 tokens | 估算o200k_base |
| codellama 7bllamagate/codellama-7b · llamagate | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.12 | 16,384 tokens | 估算o200k_base |
| DeepSeek coder 6.7bllamagate/deepseek-coder-6.7b · llamagate | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.12 | 16,384 tokens | 估算o200k_base |
| DeepSeek r1 7b Qwenllamagate/deepseek-r1-7b-qwen · llamagate | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.15 | 131,072 tokens | 估算o200k_base |
| DeepSeek r1 8bllamagate/deepseek-r1-8b · llamagate | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.20 | 65,536 tokens | 估算o200k_base |
| dolphin3 8bllamagate/dolphin3-8b · llamagate | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.15 | 128,000 tokens | 估算o200k_base |
| gemma3 4bllamagate/gemma3-4b · llamagate | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.08 | 128,000 tokens | 估算o200k_base |
| Llama 3.1 8bllamagate/llama-3.1-8b · llamagate | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.05 | 131,072 tokens | 估算o200k_base |
| Llama 3.2 3bllamagate/llama-3.2-3b · llamagate | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.08 | 131,072 tokens | 估算o200k_base |
| llava 7bllamagate/llava-7b · llamagate | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.20 | 4,096 tokens | 估算o200k_base |
| Mistral 7b v0.3llamagate/mistral-7b-v0.3 · llamagate | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.15 | 32,768 tokens | 估算o200k_base |
| openthinker 7bllamagate/openthinker-7b · llamagate | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.15 | 32,768 tokens | 估算o200k_base |
| qwen2.5 coder 7bllamagate/qwen2.5-coder-7b · llamagate | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.12 | 32,768 tokens | 估算o200k_base |
| qwen3 8bllamagate/qwen3-8b · llamagate | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.14 | 32,768 tokens | 估算o200k_base |
| qwen3 vl 8bllamagate/qwen3-vl-8b · llamagate | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.55 | 32,768 tokens | 估算o200k_base |
| medlm largemedlm-large · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 8,192 tokens | 估算o200k_base |
| medlm mediummedlm-medium · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 32,768 tokens | 估算o200k_base |
| Llama 3.3 70B Instructmeta_llama/Llama-3.3-70B-Instruct · meta_llama | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 128,000 tokens | 估算o200k_base |
| Llama 3.3 8B Instructmeta_llama/Llama-3.3-8B-Instruct · meta_llama | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 128,000 tokens | 估算o200k_base |
| Llama 4 Maverick 17B 128E Instruct FP8meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · meta_llama | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 1,000,000 tokens | 估算o200k_base |
| Llama 4 Scout 17B 16E Instruct FP8meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8 · meta_llama | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 10,000,000 tokens | 估算o200k_base |
| meta.llama2 13b chat v1meta.llama2-13b-chat-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.75 | $1.00 | 4,096 tokens | 估算o200k_base |
| meta.llama2 70b chat v1meta.llama2-70b-chat-v1 · bedrock | LiteLLM ↗2026-10-25 UTC | $1.95 | $2.56 | 4,096 tokens | 估算o200k_base |
| meta.llama3 1 405b instruct v1:0meta.llama3-1-405b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.40 | $2.40 | 128,000 tokens | 估算o200k_base |
| meta.llama3 1 70b instruct v1:0meta.llama3-1-70b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| meta.llama3 1 8b instruct v1:0meta.llama3-1-8b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.22 | 128,000 tokens | 估算o200k_base |
| meta.llama3 2 11b instruct v1:0meta.llama3-2-11b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.16 | $0.16 | 128,000 tokens | 估算o200k_base |
| meta.llama3 2 1b instruct v1:0meta.llama3-2-1b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 128,000 tokens | 估算o200k_base |
| meta.llama3 2 3b instruct v1:0meta.llama3-2-3b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 128,000 tokens | 估算o200k_base |
| meta.llama3 2 90b instruct v1:0meta.llama3-2-90b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| meta.llama3 3 70b instruct v1:0meta.llama3-3-70b-instruct-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| meta.llama3 70b instruct v1:0meta.llama3-70b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.65 | $3.50 | 8,192 tokens | 估算o200k_base |
| meta.llama3 8b instruct v1:0meta.llama3-8b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.60 | 8,192 tokens | 估算o200k_base |
| meta.llama4 maverick 17b instruct v1:0meta.llama4-maverick-17b-instruct-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.24 | $0.97 | 1,000,000 tokens | 估算o200k_base |
| meta.llama4 scout 17b instruct v1:0meta.llama4-scout-17b-instruct-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.17 | $0.66 | 10,000,000 tokens | 估算o200k_base |
| muse spark 1.1meta/muse-spark-1.1 · meta | LiteLLM ↗2026-10-25 UTC | $1.25 | $4.25 | 1,048,576 tokens | 估算o200k_base |
| muse spark 1.2meta/muse-spark-1.2 · meta | LiteLLM ↗2026-10-25 UTC | $1.25 | $4.25 | 1,048,576 tokens | 估算o200k_base |
| muse spark 1.2 contributormeta/muse-spark-1.2-contributor · meta | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.20 | 1,048,576 tokens | 估算o200k_base |
| muse spark 1.3meta/muse-spark-1.3 · meta | LiteLLM ↗2026-10-25 UTC | $1.25 | $4.25 | 1,048,576 tokens | 估算o200k_base |
| muse spark 1.3 contributormeta/muse-spark-1.3-contributor · meta | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.20 | 1,048,576 tokens | 估算o200k_base |
| muse wonder 1.0meta/muse-wonder-1.0 · meta | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 1,048,576 tokens | 估算o200k_base |
| minimax.minimax m2minimax.minimax-m2 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| minimax.minimax m2.1minimax.minimax-m2.1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,000 tokens | 估算o200k_base |
| minimax.minimax m2.5minimax.minimax-m2.5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,000 tokens | 估算o200k_base |
| MiniMax M2minimax/MiniMax-M2 · minimax | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 200,000 tokens | 估算o200k_base |
| MiniMax M2.1minimax/MiniMax-M2.1 · minimax | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| MiniMax M2.1 lightningminimax/MiniMax-M2.1-lightning · minimax | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.40 | 1,000,000 tokens | 估算o200k_base |
| MiniMax M2.5minimax/MiniMax-M2.5 · minimax | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| MiniMax M2.5 lightningminimax/MiniMax-M2.5-lightning · minimax | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.40 | 1,000,000 tokens | 估算o200k_base |
| MiniMax M3minimax/MiniMax-M3 · minimax | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| Mistral.devstral 2 123bmistral.devstral-2-123b · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.40 | $2.00 | 256,000 tokens | 估算o200k_base |
| Mistral.magistral small 2509mistral.magistral-small-2509 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 128,000 tokens | 估算o200k_base |
| Mistral.ministral 3 14b instructmistral.ministral-3-14b-instruct · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 128,000 tokens | 估算o200k_base |
| Mistral.ministral 3 3b instructmistral.ministral-3-3b-instruct · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 128,000 tokens | 估算o200k_base |
| Mistral.ministral 3 8b instructmistral.ministral-3-8b-instruct · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 128,000 tokens | 估算o200k_base |
| Mistral.Mistral 7b instruct v0:2mistral.mistral-7b-instruct-v0:2 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.20 | 32,000 tokens | 估算o200k_base |
| Mistral.Mistral large 2402 v1:0mistral.mistral-large-2402-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $4.00 | $12.00 | 32,000 tokens | 估算o200k_base |
| Mistral.Mistral large 2407 v1:0mistral.mistral-large-2407-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| Mistral.Mistral large 3 675b instructmistral.mistral-large-3-675b-instruct · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 256,000 tokens | 估算o200k_base |
| Mistral.Mistral small 2402 v1:0mistral.mistral-small-2402-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.00 | 32,000 tokens | 估算o200k_base |
| Mistral.mixtral 8x7b instruct v0:1mistral.mixtral-8x7b-instruct-v0:1 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.45 | $0.70 | 32,000 tokens | 估算o200k_base |
| Mistral.pixtral large 2502 v1:0mistral.pixtral-large-2502-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| Mistral.voxtral mini 3b 2507mistral.voxtral-mini-3b-2507 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.04 | 32,768 tokens | 估算o200k_base |
| Mistral.voxtral small 24b 2507mistral.voxtral-small-24b-2507 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 32,768 tokens | 估算o200k_base |
| codestral 2508mistral/codestral-2508 · mistral | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.90 | 128,000 tokens | 估算o200k_base |
| codestral latestmistral/codestral-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.90 | 128,000 tokens | 估算o200k_base |
| codestral mamba latestmistral/codestral-mamba-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.25 | 256,000 tokens | 估算o200k_base |
| devstral latestmistral/devstral-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.40 | $2.00 | 256,000 tokens | 估算o200k_base |
| devstral medium latestmistral/devstral-medium-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.40 | $2.00 | 256,000 tokens | 估算o200k_base |
| devstral small latestmistral/devstral-small-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 256,000 tokens | 估算o200k_base |
| glm 5 2mistral/glm-5-2 · mistral | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| labs leanstral 1 5mistral/labs-leanstral-1-5 · mistral | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 262,144 tokens | 估算o200k_base |
| labs leanstral 1 5 1mistral/labs-leanstral-1-5-1 · mistral | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 262,144 tokens | 估算o200k_base |
| magistral medium latestmistral/magistral-medium-latest · mistral | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 262,144 tokens | 估算o200k_base |
| magistral small latestmistral/magistral-small-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 262,144 tokens | 估算o200k_base |
| ministral 14b 2512mistral/ministral-14b-2512 · mistral | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 262,144 tokens | 估算o200k_base |
| ministral 14b latestmistral/ministral-14b-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 262,144 tokens | 估算o200k_base |
| ministral 3 14b 2512mistral/ministral-3-14b-2512 · mistral | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 262,144 tokens | 估算o200k_base |
| ministral 3 3b 2512mistral/ministral-3-3b-2512 · mistral | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| ministral 3 8b 2512mistral/ministral-3-8b-2512 · mistral | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 262,144 tokens | 估算o200k_base |
| ministral 3b 2512mistral/ministral-3b-2512 · mistral | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| ministral 3b latestmistral/ministral-3b-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,072 tokens | 估算o200k_base |
| ministral 8b 2512mistral/ministral-8b-2512 · mistral | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 262,144 tokens | 估算o200k_base |
| ministral 8b latestmistral/ministral-8b-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 262,144 tokens | 估算o200k_base |
| Mistral code agent latestmistral/mistral-code-agent-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.40 | $2.00 | 256,000 tokens | 估算o200k_base |
| Mistral code fim latestmistral/mistral-code-fim-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.90 | 128,000 tokens | 估算o200k_base |
| Mistral code latestmistral/mistral-code-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.90 | 128,000 tokens | 估算o200k_base |
| Mistral large 2512mistral/mistral-large-2512 · mistral | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 262,144 tokens | 估算o200k_base |
| Mistral large 3mistral/mistral-large-3 · mistral | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 262,144 tokens | 估算o200k_base |
| Mistral large 4mistral/mistral-large-4 · mistral | LiteLLM ↗2026-10-25 UTC | $0.68 | $2.09 | 1,048,576 tokens | 估算o200k_base |
| Mistral large 4 0mistral/mistral-large-4-0 · mistral | LiteLLM ↗2026-10-25 UTC | $0.68 | $2.09 | 1,048,576 tokens | 估算o200k_base |
| Mistral large latestmistral/mistral-large-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 262,144 tokens | 估算o200k_base |
| Mistral mediummistral/mistral-medium · mistral | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 262,144 tokens | 估算o200k_base |
| Mistral medium 2604mistral/mistral-medium-2604 · mistral | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 262,144 tokens | 估算o200k_base |
| Mistral medium 3mistral/mistral-medium-3 · mistral | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 262,144 tokens | 估算o200k_base |
| Mistral medium 3 5mistral/mistral-medium-3-5 · mistral | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 262,144 tokens | 估算o200k_base |
| Mistral medium 3.5mistral/mistral-medium-3.5 · mistral | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 262,144 tokens | 估算o200k_base |
| Mistral medium latestmistral/mistral-medium-latest · mistral | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 262,144 tokens | 估算o200k_base |
| Mistral smallmistral/mistral-small · mistral | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 32,000 tokens | 估算o200k_base |
| Mistral small 2603mistral/mistral-small-2603 · mistral | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 262,144 tokens | 估算o200k_base |
| Mistral small latestmistral/mistral-small-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 262,144 tokens | 估算o200k_base |
| Mistral tinymistral/mistral-tiny · mistral | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.25 | 32,000 tokens | 估算o200k_base |
| Mistral vibe cli fastmistral/mistral-vibe-cli-fast · mistral | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 262,144 tokens | 估算o200k_base |
| Mistral vibe cli latestmistral/mistral-vibe-cli-latest · mistral | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 262,144 tokens | 估算o200k_base |
| Mistral vibe cli with toolsmistral/mistral-vibe-cli-with-tools · mistral | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 262,144 tokens | 估算o200k_base |
| open Mistral nemomistral/open-mistral-nemo · mistral | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.30 | 128,000 tokens | 估算o200k_base |
| pixtral large latestmistral/pixtral-large-latest · mistral | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| voxtral small 2507mistral/voxtral-small-2507 · mistral | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 32,768 tokens | 估算o200k_base |
| voxtral small latestmistral/voxtral-small-latest · mistral | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 32,768 tokens | 估算o200k_base |
| zai glm 5mistral/zai-glm-5 · mistral | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| zai glm 5 2mistral/zai-glm-5-2 · mistral | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| zai glm 5 3mistral/zai-glm-5-3 · mistral | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| zai glm 5 3 flashmistral/zai-glm-5-3-flash · mistral | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,048,576 tokens | 估算o200k_base |
| zai glm latestmistral/zai-glm-latest · mistral | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| moonshot.kimi k2 thinkingmoonshot.kimi-k2-thinking · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 256,000 tokens | 估算o200k_base |
| kimi k2.5moonshot/kimi-k2.5 · moonshot | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.00 | 262,144 tokens | 估算o200k_base |
| kimi k2.6moonshot/kimi-k2.6 · moonshot | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| kimi k2.7 codemoonshot/kimi-k2.7-code · moonshot | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| kimi k3moonshot/kimi-k3 · moonshot | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,048,576 tokens | 估算o200k_base |
| moonshot v1 128kmoonshot/moonshot-v1-128k · moonshot | LiteLLM ↗2026-10-25 UTC | $2.00 | $5.00 | 131,072 tokens | 估算o200k_base |
| moonshot v1 128k vision previewmoonshot/moonshot-v1-128k-vision-preview · moonshot | LiteLLM ↗2026-10-25 UTC | $2.00 | $5.00 | 131,072 tokens | 估算o200k_base |
| moonshot v1 32kmoonshot/moonshot-v1-32k · moonshot | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.00 | 32,768 tokens | 估算o200k_base |
| moonshot v1 32k vision previewmoonshot/moonshot-v1-32k-vision-preview · moonshot | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.00 | 32,768 tokens | 估算o200k_base |
| moonshot v1 8kmoonshot/moonshot-v1-8k · moonshot | LiteLLM ↗2026-10-25 UTC | $0.20 | $2.00 | 8,192 tokens | 估算o200k_base |
| moonshot v1 8k vision previewmoonshot/moonshot-v1-8k-vision-preview · moonshot | LiteLLM ↗2026-10-25 UTC | $0.20 | $2.00 | 8,192 tokens | 估算o200k_base |
| moonshot v1 automoonshot/moonshot-v1-auto · moonshot | LiteLLM ↗2026-10-25 UTC | $2.00 | $5.00 | 131,072 tokens | 估算o200k_base |
| moonshotai.kimi k2.5moonshotai.kimi-k2.5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.00 | 256,000 tokens | 估算o200k_base |
| moonshotai.kimi k3moonshotai.kimi-k3 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 1,000,000 tokens | 估算o200k_base |
| morph v3 fastmorph/morph-v3-fast · morph | LiteLLM ↗2026-10-25 UTC | $0.80 | $1.20 | 16,000 tokens | 估算o200k_base |
| morph v3 largemorph/morph-v3-large · morph | LiteLLM ↗2026-10-25 UTC | $0.90 | $1.90 | 16,000 tokens | 估算o200k_base |
| DeepSeek R1nebius/deepseek-ai/DeepSeek-R1 · nebius | LiteLLM ↗2026-10-25 UTC | $0.80 | $2.40 | 128,000 tokens | 估算o200k_base |
| DeepSeek R1 0528nebius/deepseek-ai/DeepSeek-R1-0528 · nebius | LiteLLM ↗2026-10-25 UTC | $0.80 | $2.40 | 164,000 tokens | 估算o200k_base |
| DeepSeek R1 Distill Llama 70Bnebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B · nebius | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.75 | 128,000 tokens | 估算o200k_base |
| DeepSeek V3nebius/deepseek-ai/DeepSeek-V3 · nebius | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 128,000 tokens | 估算o200k_base |
| DeepSeek V3 0324nebius/deepseek-ai/DeepSeek-V3-0324 · nebius | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 128,000 tokens | 估算o200k_base |
| DeepSeek V4 Flashnebius/deepseek-ai/DeepSeek-V4-Flash · nebius | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Flash 0731nebius/deepseek-ai/DeepSeek-V4-Flash-0731 · nebius | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 1,024,000 tokens | 估算o200k_base |
| DeepSeek V4 Pronebius/deepseek-ai/DeepSeek-V4-Pro · nebius | LiteLLM ↗2026-10-25 UTC | $1.75 | $3.50 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Pro 0813nebius/deepseek-ai/DeepSeek-V4-Pro-0813 · nebius | LiteLLM ↗2026-10-25 UTC | $1.32 | $3.96 | 979,000 tokens | 估算o200k_base |
| DeepSeek V4.1 Flashnebius/deepseek-ai/DeepSeek-V4.1-Flash · nebius | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,048,000 tokens | 估算o200k_base |
| gemma 3 27b itnebius/google/gemma-3-27b-it · nebius | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 110,000 tokens | 估算o200k_base |
| Llama 3.3 70B Instructnebius/meta-llama/Llama-3.3-70B-Instruct · nebius | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.40 | 131,072 tokens | 估算o200k_base |
| Llama Guard 3 8Bnebius/meta-llama/Llama-Guard-3-8B · nebius | LiteLLM ↗2026-10-25 UTC | $0.02 | $0.06 | 128,000 tokens | 估算o200k_base |
| Meta Llama 3.1 405B Instructnebius/meta-llama/Meta-Llama-3.1-405B-Instruct · nebius | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.00 | 128,000 tokens | 估算o200k_base |
| Meta Llama 3.1 70B Instructnebius/meta-llama/Meta-Llama-3.1-70B-Instruct · nebius | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.40 | 128,000 tokens | 估算o200k_base |
| Meta Llama 3.1 8B Instructnebius/meta-llama/Meta-Llama-3.1-8B-Instruct · nebius | LiteLLM ↗2026-10-25 UTC | $0.02 | $0.06 | 128,000 tokens | 估算o200k_base |
| MiniMax M2.5nebius/MiniMaxAI/MiniMax-M2.5 · nebius | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,608 tokens | 估算o200k_base |
| MiniMax M3nebius/MiniMaxAI/MiniMax-M3 · nebius | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| Mistral Nemo Instruct 2407nebius/mistralai/Mistral-Nemo-Instruct-2407 · nebius | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.12 | 128,000 tokens | 估算o200k_base |
| Kimi K2.6nebius/moonshotai/Kimi-K2.6 · nebius | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| Kimi K2.7 Codenebius/moonshotai/Kimi-K2.7-Code · nebius | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| Kimi K3nebius/moonshotai/Kimi-K3 · nebius | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,024,000 tokens | 估算o200k_base |
| Hermes 3 Llama 3.1 405Bnebius/NousResearch/Hermes-3-Llama-3.1-405B · nebius | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.00 | 128,000 tokens | 估算o200k_base |
| Hermes 4 405Bnebius/NousResearch/Hermes-4-405B · nebius | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.00 | 131,072 tokens | 估算o200k_base |
| Hermes 4 70Bnebius/NousResearch/Hermes-4-70B · nebius | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.40 | 131,072 tokens | 估算o200k_base |
| Cosmos3 Super Reasonernebius/nvidia/Cosmos3-Super-Reasoner · nebius | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 262,144 tokens | 估算o200k_base |
| Llama 3 1 Nemotron Ultra 253B v1nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 · nebius | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.80 | 131,072 tokens | 估算o200k_base |
| Llama 3.1 Nemotron Ultra 253B v1nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1 · nebius | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.80 | 128,000 tokens | 估算o200k_base |
| Llama 3.3 Nemotron Super 49B v1nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1 · nebius | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 131,072 tokens | 估算o200k_base |
| Nemotron 3 5 Lightningnebius/nvidia/Nemotron-3_5-Lightning · nebius | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.24 | 1,048,576 tokens | 估算o200k_base |
| Nemotron 3 Nano Omninebius/nvidia/Nemotron-3-Nano-Omni · nebius | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.24 | 262,144 tokens | 估算o200k_base |
| nemotron 3 super 120b a12bnebius/nvidia/nemotron-3-super-120b-a12b · nebius | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.90 | 262,144 tokens | 估算o200k_base |
| Nemotron 3 Ultra 550b a55bnebius/nvidia/Nemotron-3-Ultra-550b-a55b · nebius | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.00 | 1,048,576 tokens | 估算o200k_base |
| NVIDIA Nemotron 3 Nano 30B A3Bnebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B · nebius | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.24 | 262,144 tokens | 估算o200k_base |
| GPT oss 120bnebius/openai/gpt-oss-120b · nebius | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| MiniCPM V 4 5nebius/openbmb/MiniCPM-V-4_5 · nebius | LiteLLM ↗2026-10-25 UTC | $0.658 | $1.11 | 32,000 tokens | 估算o200k_base |
| Qwen2 VL 72B Instructnebius/Qwen/Qwen2-VL-72B-Instruct · nebius | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.40 | 131,072 tokens | 估算o200k_base |
| Qwen2 VL 7B Instructnebius/Qwen/Qwen2-VL-7B-Instruct · nebius | LiteLLM ↗2026-10-25 UTC | $0.02 | $0.06 | 131,072 tokens | 估算o200k_base |
| Qwen2.5 32B Instructnebius/Qwen/Qwen2.5-32B-Instruct · nebius | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.20 | 128,000 tokens | 估算o200k_base |
| Qwen2.5 72B Instructnebius/Qwen/Qwen2.5-72B-Instruct · nebius | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.40 | 128,000 tokens | 估算o200k_base |
| Qwen2.5 Coder 7Bnebius/Qwen/Qwen2.5-Coder-7B · nebius | LiteLLM ↗2026-10-25 UTC | $0.01 | $0.03 | 32,768 tokens | 估算o200k_base |
| Qwen2.5 VL 72B Instructnebius/Qwen/Qwen2.5-VL-72B-Instruct · nebius | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.75 | 32,000 tokens | 估算o200k_base |
| Qwen3 14Bnebius/Qwen/Qwen3-14B · nebius | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.24 | 32,768 tokens | 估算o200k_base |
| Qwen3 235B A22Bnebius/Qwen/Qwen3-235B-A22B · nebius | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 262,144 tokens | 估算o200k_base |
| Qwen3 235B A22B Instruct 2507nebius/Qwen/Qwen3-235B-A22B-Instruct-2507 · nebius | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 262,144 tokens | 估算o200k_base |
| Qwen3 30B A3Bnebius/Qwen/Qwen3-30B-A3B · nebius | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 32,768 tokens | 估算o200k_base |
| Qwen3 30B A3B Instruct 2507nebius/Qwen/Qwen3-30B-A3B-Instruct-2507 · nebius | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 262,144 tokens | 估算o200k_base |
| Qwen3 32Bnebius/Qwen/Qwen3-32B · nebius | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 40,960 tokens | 估算o200k_base |
| Qwen3 4Bnebius/Qwen/Qwen3-4B · nebius | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.24 | 32,768 tokens | 估算o200k_base |
| Qwen3 Next 80B A3B Thinkingnebius/Qwen/Qwen3-Next-80B-A3B-Thinking · nebius | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.20 | 128,000 tokens | 估算o200k_base |
| Qwen3.5 397B A17Bnebius/Qwen/Qwen3.5-397B-A17B · nebius | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.60 | 262,144 tokens | 估算o200k_base |
| Qwen3.8 27Bnebius/Qwen/Qwen3.8-27B · nebius | LiteLLM ↗2026-10-25 UTC | $0.45 | $3.00 | 262,144 tokens | 估算o200k_base |
| QwQ 32Bnebius/Qwen/QwQ-32B · nebius | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.45 | 32,768 tokens | 估算o200k_base |
| beamnebius/reflection/beam · nebius | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.00 | 1,048,576 tokens | 估算o200k_base |
| GLM 5.1nebius/zai-org/GLM-5.1 · nebius | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 202,752 tokens | 估算o200k_base |
| GLM 5.2nebius/zai-org/GLM-5.2 · nebius | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| GLM 5.3nebius/zai-org/GLM-5.3 · nebius | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,024,000 tokens | 估算o200k_base |
| GLM 5.3 Flashnebius/zai-org/GLM-5.3-Flash · nebius | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,024,000 tokens | 估算o200k_base |
| baichuan m2 32bnovita/baichuan/baichuan-m2-32b · novita | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.07 | 131,072 tokens | 估算o200k_base |
| cobuddynovita/baidu/cobuddy · novita | LiteLLM ↗2026-10-25 UTC | $0.28 | $1.13 | 131,072 tokens | 估算o200k_base |
| ernie 4.5 21B a3bnovita/baidu/ernie-4.5-21B-a3b · novita | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.28 | 120,000 tokens | 估算o200k_base |
| ernie 4.5 21B a3b thinkingnovita/baidu/ernie-4.5-21B-a3b-thinking · novita | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.28 | 131,072 tokens | 估算o200k_base |
| ernie 4.5 300b a47b paddlenovita/baidu/ernie-4.5-300b-a47b-paddle · novita | LiteLLM ↗2026-10-25 UTC | $0.28 | $1.10 | 123,000 tokens | 估算o200k_base |
| ernie 4.5 vl 28b a3bnovita/baidu/ernie-4.5-vl-28b-a3b · novita | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.56 | 30,000 tokens | 估算o200k_base |
| ernie 4.5 vl 28b a3b thinkingnovita/baidu/ernie-4.5-vl-28b-a3b-thinking · novita | LiteLLM ↗2026-10-25 UTC | $0.39 | $0.39 | 131,072 tokens | 估算o200k_base |
| ernie 4.5 vl 424b a47bnovita/baidu/ernie-4.5-vl-424b-a47b · novita | LiteLLM ↗2026-10-25 UTC | $0.42 | $1.25 | 123,000 tokens | 估算o200k_base |
| DeepSeek v3novita/deepseek/deepseek_v3 · novita | LiteLLM ↗2026-10-25 UTC | $0.89 | $0.89 | 64,000 tokens | 估算o200k_base |
| DeepSeek ocrnovita/deepseek/deepseek-ocr · novita | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.03 | 8,192 tokens | 估算o200k_base |
| DeepSeek ocr 2novita/deepseek/deepseek-ocr-2 · novita | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.03 | 8,192 tokens | 估算o200k_base |
| DeepSeek prover v2 671bnovita/deepseek/deepseek-prover-v2-671b · novita | LiteLLM ↗2026-10-25 UTC | $0.70 | $2.50 | 160,000 tokens | 估算o200k_base |
| DeepSeek r1novita/deepseek/deepseek-r1 · novita | LiteLLM ↗2026-10-25 UTC | $4.00 | $4.00 | 64,000 tokens | 估算o200k_base |
| DeepSeek r1 0528novita/deepseek/deepseek-r1-0528 · novita | LiteLLM ↗2026-10-25 UTC | $0.70 | $2.50 | 163,840 tokens | 估算o200k_base |
| DeepSeek r1 0528 qwen3 8bnovita/deepseek/deepseek-r1-0528-qwen3-8b · novita | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.09 | 128,000 tokens | 估算o200k_base |
| DeepSeek r1 distill Llama 70bnovita/deepseek/deepseek-r1-distill-llama-70b · novita | LiteLLM ↗2026-10-25 UTC | $0.80 | $0.80 | 8,192 tokens | 估算o200k_base |
| DeepSeek r1 distill Qwen 14bnovita/deepseek/deepseek-r1-distill-qwen-14b · novita | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 32,768 tokens | 估算o200k_base |
| DeepSeek r1 distill Qwen 32bnovita/deepseek/deepseek-r1-distill-qwen-32b · novita | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.30 | 64,000 tokens | 估算o200k_base |
| DeepSeek r1 turbonovita/deepseek/deepseek-r1-turbo · novita | LiteLLM ↗2026-10-25 UTC | $0.70 | $2.50 | 64,000 tokens | 估算o200k_base |
| communitynovita/deepseek/deepseek-r1/community · novita | LiteLLM ↗2026-10-25 UTC | $4.00 | $4.00 | 64,000 tokens | 估算o200k_base |
| DeepSeek v3 0324novita/deepseek/deepseek-v3-0324 · novita | LiteLLM ↗2026-10-25 UTC | $0.27 | $1.12 | 163,840 tokens | 估算o200k_base |
| DeepSeek v3 turbonovita/deepseek/deepseek-v3-turbo · novita | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.30 | 64,000 tokens | 估算o200k_base |
| DeepSeek v3.1novita/deepseek/deepseek-v3.1 · novita | LiteLLM ↗2026-10-25 UTC | $0.27 | $1.00 | 131,072 tokens | 估算o200k_base |
| DeepSeek v3.1 terminusnovita/deepseek/deepseek-v3.1-terminus · novita | LiteLLM ↗2026-10-25 UTC | $0.27 | $1.00 | 131,072 tokens | 估算o200k_base |
| DeepSeek v3.2novita/deepseek/deepseek-v3.2 · novita | LiteLLM ↗2026-10-25 UTC | $0.269 | $0.40 | 163,840 tokens | 估算o200k_base |
| DeepSeek v3.2 expnovita/deepseek/deepseek-v3.2-exp · novita | LiteLLM ↗2026-10-25 UTC | $0.27 | $0.41 | 163,840 tokens | 估算o200k_base |
| communitynovita/deepseek/deepseek-v3/community · novita | LiteLLM ↗2026-10-25 UTC | $0.89 | $0.89 | 64,000 tokens | 估算o200k_base |
| DeepSeek v4 flashnovita/deepseek/deepseek-v4-flash · novita | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 flash 0731novita/deepseek/deepseek-v4-flash-0731 · novita | LiteLLM ↗2026-10-25 UTC | $0.44 | $1.32 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 flash vision expnovita/deepseek/deepseek-v4-flash-vision-exp · novita | LiteLLM ↗2026-10-25 UTC | $0.44 | $1.32 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 pronovita/deepseek/deepseek-v4-pro · novita | LiteLLM ↗2026-10-25 UTC | $1.60 | $3.20 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek v4 pro 0813novita/deepseek/deepseek-v4-pro-0813 · novita | LiteLLM ↗2026-10-25 UTC | $1.32 | $3.96 | 1,048,576 tokens | 估算o200k_base |
| gemma 3 12b itnovita/google/gemma-3-12b-it · novita | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.10 | 131,072 tokens | 估算o200k_base |
| gemma 3 27b itnovita/google/gemma-3-27b-it · novita | LiteLLM ↗2026-10-25 UTC | $0.119 | $0.20 | 98,304 tokens | 估算o200k_base |
| gemma 4 26b a4b itnovita/google/gemma-4-26b-a4b-it · novita | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.40 | 262,144 tokens | 估算o200k_base |
| gemma 4 31b itnovita/google/gemma-4-31b-it · novita | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.40 | 262,144 tokens | 估算o200k_base |
| mythomax l2 13bnovita/gryphe/mythomax-l2-13b · novita | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.09 | 4,096 tokens | 估算o200k_base |
| ling 3.0 flashnovita/inclusionai/ling-3.0-flash · novita | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.18 | 262,144 tokens | 估算o200k_base |
| ling 3.0 flash fastnovita/inclusionai/ling-3.0-flash-fast · novita | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.18 | 262,144 tokens | 估算o200k_base |
| kat coder pronovita/kwaipilot/kat-coder-pro · novita | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 256,000 tokens | 估算o200k_base |
| Llama 3 70b instructnovita/meta-llama/llama-3-70b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.51 | $0.74 | 8,192 tokens | 估算o200k_base |
| Llama 3 8b instructnovita/meta-llama/llama-3-8b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.04 | 8,192 tokens | 估算o200k_base |
| Llama 3.1 8b instructnovita/meta-llama/llama-3.1-8b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.02 | $0.05 | 16,384 tokens | 估算o200k_base |
| Llama 3.2 1b instructnovita/meta-llama/llama-3.2-1b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.02 | $0.02 | 131,000 tokens | 估算o200k_base |
| Llama 3.2 3b instructnovita/meta-llama/llama-3.2-3b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.05 | 32,768 tokens | 估算o200k_base |
| Llama 3.3 70b instructnovita/meta-llama/llama-3.3-70b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.135 | $0.40 | 12,288 tokens | 估算o200k_base |
| Llama 4 maverick 17b 128e instruct fp8novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8 · novita | LiteLLM ↗2026-10-25 UTC | $0.27 | $0.85 | 1,048,576 tokens | 估算o200k_base |
| Llama 4 scout 17b 16e instructnovita/meta-llama/llama-4-scout-17b-16e-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.59 | 131,072 tokens | 估算o200k_base |
| wizardlm 2 8x22bnovita/microsoft/wizardlm-2-8x22b · novita | LiteLLM ↗2026-10-25 UTC | $0.62 | $0.62 | 65,535 tokens | 估算o200k_base |
| macaron v1 tallnovita/mindai/macaron-v1-tall · novita | LiteLLM ↗2026-10-25 UTC | $0.45 | $2.60 | 262,144 tokens | 估算o200k_base |
| macaron v1 ventinovita/mindai/macaron-v1-venti · novita | LiteLLM ↗2026-10-25 UTC | $1.50 | $4.50 | 1,048,576 tokens | 估算o200k_base |
| minimax m2novita/minimax/minimax-m2 · novita | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 204,800 tokens | 估算o200k_base |
| minimax m2.1novita/minimax/minimax-m2.1 · novita | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 204,800 tokens | 估算o200k_base |
| minimax m2.5novita/minimax/minimax-m2.5 · novita | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 204,800 tokens | 估算o200k_base |
| minimax m2.5 highspeednovita/minimax/minimax-m2.5-highspeed · novita | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 204,800 tokens | 估算o200k_base |
| minimax m2.7novita/minimax/minimax-m2.7 · novita | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 204,800 tokens | 估算o200k_base |
| minimax m2.7 highspeednovita/minimax/minimax-m2.7-highspeed · novita | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 204,800 tokens | 估算o200k_base |
| minimax m3novita/minimax/minimax-m3 · novita | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| minimax m1 80knovita/minimaxai/minimax-m1-80k · novita | LiteLLM ↗2026-10-25 UTC | $0.55 | $2.20 | 1,000,000 tokens | 估算o200k_base |
| Mistral nemonovita/mistralai/mistral-nemo · novita | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.17 | 60,288 tokens | 估算o200k_base |
| kimi k2 0905novita/moonshotai/kimi-k2-0905 · novita | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 262,144 tokens | 估算o200k_base |
| kimi k2 instructnovita/moonshotai/kimi-k2-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.57 | $2.30 | 131,072 tokens | 估算o200k_base |
| kimi k2 thinkingnovita/moonshotai/kimi-k2-thinking · novita | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 262,144 tokens | 估算o200k_base |
| kimi k2.5novita/moonshotai/kimi-k2.5 · novita | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.00 | 262,144 tokens | 估算o200k_base |
| kimi k2.6novita/moonshotai/kimi-k2.6 · novita | LiteLLM ↗2026-10-25 UTC | $0.80 | $3.40 | 262,144 tokens | 估算o200k_base |
| kimi k2.7 codenovita/moonshotai/kimi-k2.7-code · novita | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| kimi k3novita/moonshotai/kimi-k3 · novita | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,048,576 tokens | 估算o200k_base |
| hermes 2 pro Llama 3 8bnovita/nousresearch/hermes-2-pro-llama-3-8b · novita | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.14 | 8,192 tokens | 估算o200k_base |
| nemotron 3 nano 30b a3bnovita/nvidia/nemotron-3-nano-30b-a3b · novita | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 262,144 tokens | 估算o200k_base |
| GPT oss 120bnovita/openai/gpt-oss-120b · novita | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.25 | 131,072 tokens | 估算o200k_base |
| GPT oss 20bnovita/openai/gpt-oss-20b · novita | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.15 | 131,072 tokens | 估算o200k_base |
| paddleocr vlnovita/paddlepaddle/paddleocr-vl · novita | LiteLLM ↗2026-10-25 UTC | $0.02 | $0.02 | 16,384 tokens | 估算o200k_base |
| Qwen 2.5 72b instructnovita/qwen/qwen-2.5-72b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.38 | $0.40 | 32,000 tokens | 估算o200k_base |
| Qwen mt plusnovita/qwen/qwen-mt-plus · novita | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.75 | 16,384 tokens | 估算o200k_base |
| qwen2.5 7b instructnovita/qwen/qwen2.5-7b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.07 | 32,000 tokens | 估算o200k_base |
| qwen2.5 vl 72b instructnovita/qwen/qwen2.5-vl-72b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.80 | $0.80 | 32,768 tokens | 估算o200k_base |
| qwen3 235b a22b fp8novita/qwen/qwen3-235b-a22b-fp8 · novita | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.80 | 40,960 tokens | 估算o200k_base |
| qwen3 235b a22b instruct 2507novita/qwen/qwen3-235b-a22b-instruct-2507 · novita | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.58 | 131,072 tokens | 估算o200k_base |
| qwen3 235b a22b thinking 2507novita/qwen/qwen3-235b-a22b-thinking-2507 · novita | LiteLLM ↗2026-10-25 UTC | $0.30 | $3.00 | 131,072 tokens | 估算o200k_base |
| qwen3 30b a3b fp8novita/qwen/qwen3-30b-a3b-fp8 · novita | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.45 | 40,960 tokens | 估算o200k_base |
| qwen3 32b fp8novita/qwen/qwen3-32b-fp8 · novita | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.45 | 40,960 tokens | 估算o200k_base |
| qwen3 4b fp8novita/qwen/qwen3-4b-fp8 · novita | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.03 | 128,000 tokens | 估算o200k_base |
| qwen3 8b fp8novita/qwen/qwen3-8b-fp8 · novita | LiteLLM ↗2026-10-25 UTC | $0.035 | $0.138 | 128,000 tokens | 估算o200k_base |
| qwen3 coder 30b a3b instructnovita/qwen/qwen3-coder-30b-a3b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.27 | 160,000 tokens | 估算o200k_base |
| qwen3 coder 480b a35b instructnovita/qwen/qwen3-coder-480b-a35b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.38 | $1.55 | 262,144 tokens | 估算o200k_base |
| qwen3 coder nextnovita/qwen/qwen3-coder-next · novita | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.50 | 262,144 tokens | 估算o200k_base |
| qwen3 maxnovita/qwen/qwen3-max · novita | LiteLLM ↗2026-10-25 UTC | $2.11 | $8.45 | 262,144 tokens | 估算o200k_base |
| qwen3 next 80b a3b instructnovita/qwen/qwen3-next-80b-a3b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.50 | 131,072 tokens | 估算o200k_base |
| qwen3 next 80b a3b thinkingnovita/qwen/qwen3-next-80b-a3b-thinking · novita | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.50 | 131,072 tokens | 估算o200k_base |
| qwen3 omni 30b a3b instructnovita/qwen/qwen3-omni-30b-a3b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.97 | 65,536 tokens | 估算o200k_base |
| qwen3 omni 30b a3b thinkingnovita/qwen/qwen3-omni-30b-a3b-thinking · novita | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.97 | 65,536 tokens | 估算o200k_base |
| qwen3 vl 235b a22b instructnovita/qwen/qwen3-vl-235b-a22b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.50 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 235b a22b thinkingnovita/qwen/qwen3-vl-235b-a22b-thinking · novita | LiteLLM ↗2026-10-25 UTC | $0.98 | $3.95 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 30b a3b instructnovita/qwen/qwen3-vl-30b-a3b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.70 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 30b a3b thinkingnovita/qwen/qwen3-vl-30b-a3b-thinking · novita | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.00 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 8b instructnovita/qwen/qwen3-vl-8b-instruct · novita | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.50 | 131,072 tokens | 估算o200k_base |
| qwen3.5 122b a10bnovita/qwen/qwen3.5-122b-a10b · novita | LiteLLM ↗2026-10-25 UTC | $0.40 | $3.20 | 262,144 tokens | 估算o200k_base |
| qwen3.5 27bnovita/qwen/qwen3.5-27b · novita | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.40 | 262,144 tokens | 估算o200k_base |
| qwen3.5 35b a3bnovita/qwen/qwen3.5-35b-a3b · novita | LiteLLM ↗2026-10-25 UTC | $0.25 | $2.00 | 262,144 tokens | 估算o200k_base |
| qwen3.5 397b a17bnovita/qwen/qwen3.5-397b-a17b · novita | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.60 | 262,144 tokens | 估算o200k_base |
| qwen3.6 27bnovita/qwen/qwen3.6-27b · novita | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.60 | 262,144 tokens | 估算o200k_base |
| qwen3.6 35b a3bnovita/qwen/qwen3.6-35b-a3b · novita | LiteLLM ↗2026-10-25 UTC | $0.248 | $1.485 | 262,144 tokens | 估算o200k_base |
| qwen3.7 maxnovita/qwen/qwen3.7-max · novita | LiteLLM ↗2026-10-25 UTC | $1.25 | $3.75 | 1,000,000 tokens | 估算o200k_base |
| qwen3.8 maxnovita/qwen/qwen3.8-max · novita | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 1,000,000 tokens | 估算o200k_base |
| l3 70b euryale v2.1novita/sao10k/l3-70b-euryale-v2.1 · novita | LiteLLM ↗2026-10-25 UTC | $1.48 | $1.48 | 8,192 tokens | 估算o200k_base |
| l3 8b lunarisnovita/sao10k/l3-8b-lunaris · novita | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.05 | 8,192 tokens | 估算o200k_base |
| L3 8B Stheno v3.2novita/Sao10K/L3-8B-Stheno-v3.2 · novita | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.05 | 8,192 tokens | 估算o200k_base |
| l31 70b euryale v2.2novita/sao10k/l31-70b-euryale-v2.2 · novita | LiteLLM ↗2026-10-25 UTC | $1.48 | $1.48 | 8,192 tokens | 估算o200k_base |
| r1v4 litenovita/skywork/r1v4-lite · novita | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 262,144 tokens | 估算o200k_base |
| step 3.7 flashnovita/stepfun/step-3.7-flash · novita | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.15 | 262,144 tokens | 估算o200k_base |
| hy3novita/tencent/hy3 · novita | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.58 | 262,144 tokens | 估算o200k_base |
| glm 4 32b 0414novita/thudm/glm-4-32b-0414 · novita | LiteLLM ↗2026-10-25 UTC | $0.55 | $1.66 | 32,000 tokens | 估算o200k_base |
| mimo v2 flashnovita/xiaomimimo/mimo-v2-flash · novita | LiteLLM ↗2026-10-25 UTC | $0.11 | $0.33 | 262,144 tokens | 估算o200k_base |
| mimo v2.5novita/xiaomimimo/mimo-v2.5 · novita | LiteLLM ↗2026-10-25 UTC | $0.168 | $0.336 | 1,048,576 tokens | 估算o200k_base |
| mimo v2.5 pronovita/xiaomimimo/mimo-v2.5-pro · novita | LiteLLM ↗2026-10-25 UTC | $0.522 | $1.044 | 1,048,576 tokens | 估算o200k_base |
| autoglm phone 9b multilingualnovita/zai-org/autoglm-phone-9b-multilingual · novita | LiteLLM ↗2026-10-25 UTC | $0.035 | $0.138 | 65,536 tokens | 估算o200k_base |
| glm 4.5novita/zai-org/glm-4.5 · novita | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 131,072 tokens | 估算o200k_base |
| glm 4.5 airnovita/zai-org/glm-4.5-air · novita | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.85 | 131,072 tokens | 估算o200k_base |
| glm 4.5vnovita/zai-org/glm-4.5v · novita | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.80 | 65,536 tokens | 估算o200k_base |
| glm 4.6novita/zai-org/glm-4.6 · novita | LiteLLM ↗2026-10-25 UTC | $0.55 | $2.20 | 204,800 tokens | 估算o200k_base |
| glm 4.6vnovita/zai-org/glm-4.6v · novita | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.90 | 131,072 tokens | 估算o200k_base |
| glm 4.7novita/zai-org/glm-4.7 · novita | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 204,800 tokens | 估算o200k_base |
| glm 4.7 flashnovita/zai-org/glm-4.7-flash · novita | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.40 | 200,000 tokens | 估算o200k_base |
| glm 4.7 hnovita/zai-org/glm-4.7-h · novita | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 204,800 tokens | 估算o200k_base |
| glm 5novita/zai-org/glm-5 · novita | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.20 | 202,800 tokens | 估算o200k_base |
| glm 5 turbonovita/zai-org/glm-5-turbo · novita | LiteLLM ↗2026-10-25 UTC | $1.20 | $4.00 | 202,800 tokens | 估算o200k_base |
| glm 5.1novita/zai-org/glm-5.1 · novita | LiteLLM ↗2026-10-25 UTC | $1.38 | $4.40 | 204,800 tokens | 估算o200k_base |
| glm 5.2novita/zai-org/glm-5.2 · novita | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| glm 5.3novita/zai-org/glm-5.3 · novita | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| glm 5v turbonovita/zai-org/glm-5v-turbo · novita | LiteLLM ↗2026-10-25 UTC | $1.20 | $4.00 | 204,800 tokens | 估算o200k_base |
| nvidia.nemotron nano 12b v2nvidia.nemotron-nano-12b-v2 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 128,000 tokens | 估算o200k_base |
| nvidia.nemotron nano 3 30bnvidia.nemotron-nano-3-30b · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.24 | 256,000 tokens | 估算o200k_base |
| nvidia.nemotron nano 9b v2nvidia.nemotron-nano-9b-v2 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.23 | 128,000 tokens | 估算o200k_base |
| nvidia.nemotron super 3 120bnvidia.nemotron-super-3-120b · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.65 | 256,000 tokens | 估算o200k_base |
| o1o1 · openai | LiteLLM ↗2026-10-25 UTC | $15.00 | $60.00 | 200,000 tokens | 估算o200k_base |
| o1 2024 12 17o1-2024-12-17 · openai | LiteLLM ↗2026-10-25 UTC | $15.00 | $60.00 | 200,000 tokens | 估算o200k_base |
| o3o3 · openai | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 200,000 tokens | 估算o200k_base |
| o3 2025 04 16o3-2025-04-16 · openai | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 200,000 tokens | 估算o200k_base |
| o3 minio3-mini · openai | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 200,000 tokens | 估算o200k_base |
| o3 mini 2025 01 31o3-mini-2025-01-31 · openai | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 200,000 tokens | 估算o200k_base |
| o4 minio4-mini · openai | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 200,000 tokens | 估算o200k_base |
| o4 mini 2025 04 16o4-mini-2025-04-16 · openai | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 200,000 tokens | 估算o200k_base |
| cohere.command a 03 2025oci/cohere.command-a-03-2025 · oci | LiteLLM ↗2026-10-25 UTC | $1.56 | $1.56 | 256,000 tokens | 估算o200k_base |
| cohere.command a reasoningoci/cohere.command-a-reasoning · oci | LiteLLM ↗2026-10-25 UTC | $1.56 | $1.56 | 256,000 tokens | 估算o200k_base |
| cohere.command a reasoning 08 2025oci/cohere.command-a-reasoning-08-2025 · oci | LiteLLM ↗2026-10-25 UTC | $1.56 | $1.56 | 256,000 tokens | 估算o200k_base |
| cohere.command a translate 08 2025oci/cohere.command-a-translate-08-2025 · oci | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.09 | 256,000 tokens | 估算o200k_base |
| cohere.command a visionoci/cohere.command-a-vision · oci | LiteLLM ↗2026-10-25 UTC | $1.56 | $1.56 | 256,000 tokens | 估算o200k_base |
| cohere.command a vision 07 2025oci/cohere.command-a-vision-07-2025 · oci | LiteLLM ↗2026-10-25 UTC | $1.56 | $1.56 | 128,000 tokens | 估算o200k_base |
| cohere.command latestoci/cohere.command-latest · oci | LiteLLM ↗2026-10-25 UTC | $1.56 | $1.56 | 128,000 tokens | 估算o200k_base |
| cohere.command plus latestoci/cohere.command-plus-latest · oci | LiteLLM ↗2026-10-25 UTC | $1.56 | $1.56 | 128,000 tokens | 估算o200k_base |
| cohere.command r 08 2024oci/cohere.command-r-08-2024 · oci | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 128,000 tokens | 估算o200k_base |
| cohere.command r plus 08 2024oci/cohere.command-r-plus-08-2024 · oci | LiteLLM ↗2026-10-25 UTC | $1.56 | $1.56 | 128,000 tokens | 估算o200k_base |
| google.Gemini 2.5 flashoci/google.gemini-2.5-flash · oci | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 1,048,576 tokens | 估算o200k_base |
| google.Gemini 2.5 flash liteoci/google.gemini-2.5-flash-lite · oci | LiteLLM ↗2026-10-25 UTC | $0.075 | $0.30 | 1,048,576 tokens | 估算o200k_base |
| google.Gemini 2.5 prooci/google.gemini-2.5-pro · oci | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 1,048,576 tokens | 估算o200k_base |
| meta.Llama 3.1 405b instructoci/meta.llama-3.1-405b-instruct · oci | LiteLLM ↗2026-10-25 UTC | $10.68 | $10.68 | 128,000 tokens | 估算o200k_base |
| meta.Llama 3.1 70b instructoci/meta.llama-3.1-70b-instruct · oci | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| meta.Llama 3.1 8b instructoci/meta.llama-3.1-8b-instruct · oci | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| meta.Llama 3.2 11b vision instructoci/meta.llama-3.2-11b-vision-instruct · oci | LiteLLM ↗2026-10-25 UTC | $2.00 | $2.00 | 128,000 tokens | 估算o200k_base |
| meta.Llama 3.2 90b vision instructoci/meta.llama-3.2-90b-vision-instruct · oci | LiteLLM ↗2026-10-25 UTC | $2.00 | $2.00 | 128,000 tokens | 估算o200k_base |
| meta.Llama 3.3 70b instructoci/meta.llama-3.3-70b-instruct · oci | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| meta.Llama 3.3 70b instruct fp8 dynamicoci/meta.llama-3.3-70b-instruct-fp8-dynamic · oci | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| meta.Llama 4 maverick 17b 128e instruct fp8oci/meta.llama-4-maverick-17b-128e-instruct-fp8 · oci | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 1,048,576 tokens | 估算o200k_base |
| meta.Llama 4 scout 17b 16e instructoci/meta.llama-4-scout-17b-16e-instruct · oci | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 10,485,760 tokens | 估算o200k_base |
| openai.GPT 5oci/openai.gpt-5 · oci | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 272,000 tokens | 估算o200k_base |
| openai.GPT 5 minioci/openai.gpt-5-mini · oci | LiteLLM ↗2026-10-25 UTC | $0.25 | $2.00 | 272,000 tokens | 估算o200k_base |
| openai.GPT 5 nanooci/openai.gpt-5-nano · oci | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.40 | 272,000 tokens | 估算o200k_base |
| openai.GPT oss 120boci/openai.gpt-oss-120b · oci | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| openai.GPT oss 20boci/openai.gpt-oss-20b · oci | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.30 | 128,000 tokens | 估算o200k_base |
| xai.grok 3oci/xai.grok-3 · oci | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 131,072 tokens | 估算o200k_base |
| xai.grok 3 fastoci/xai.grok-3-fast · oci | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 131,072 tokens | 估算o200k_base |
| xai.grok 3 minioci/xai.grok-3-mini · oci | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.50 | 131,072 tokens | 估算o200k_base |
| xai.grok 3 mini fastoci/xai.grok-3-mini-fast · oci | LiteLLM ↗2026-10-25 UTC | $0.60 | $4.00 | 131,072 tokens | 估算o200k_base |
| xai.grok 4oci/xai.grok-4 · oci | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 128,000 tokens | 估算o200k_base |
| xai.grok 4 fastoci/xai.grok-4-fast · oci | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 131,072 tokens | 估算o200k_base |
| xai.grok 4.1 fastoci/xai.grok-4.1-fast · oci | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 131,072 tokens | 估算o200k_base |
| xai.grok 4.20oci/xai.grok-4.20 · oci | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 131,072 tokens | 估算o200k_base |
| xai.grok 4.20 0309 non reasoningoci/xai.grok-4.20-0309-non-reasoning · oci | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| xai.grok 4.20 0309 reasoningoci/xai.grok-4.20-0309-reasoning · oci | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| xai.grok 4.20 multi agentoci/xai.grok-4.20-multi-agent · oci | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 131,072 tokens | 估算o200k_base |
| xai.grok 4.20 non reasoningoci/xai.grok-4.20-non-reasoning · oci | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| xai.grok 4.20 reasoningoci/xai.grok-4.20-reasoning · oci | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| xai.grok code fast 1oci/xai.grok-code-fast-1 · oci | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 131,072 tokens | 估算o200k_base |
| codegeex4ollama/codegeex4 · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,768 tokens | 估算o200k_base |
| DeepSeek coder v2 instructollama/deepseek-coder-v2-instruct · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,768 tokens | 估算o200k_base |
| DeepSeek coder v2 lite instructollama/deepseek-coder-v2-lite-instruct · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,768 tokens | 估算o200k_base |
| DeepSeek v3.1:671b cloudollama/deepseek-v3.1:671b-cloud · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 163,840 tokens | 估算o200k_base |
| GPT oss:120b cloudollama/gpt-oss:120b-cloud · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 131,072 tokens | 估算o200k_base |
| GPT oss:20b cloudollama/gpt-oss:20b-cloud · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 131,072 tokens | 估算o200k_base |
| internlm2 5 20b chatollama/internlm2_5-20b-chat · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,768 tokens | 估算o200k_base |
| llama2ollama/llama2 · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 4,096 tokens | 估算o200k_base |
| llama2:13bollama/llama2:13b · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 4,096 tokens | 估算o200k_base |
| llama2:70bollama/llama2:70b · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 4,096 tokens | 估算o200k_base |
| llama2:7bollama/llama2:7b · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 4,096 tokens | 估算o200k_base |
| llama3ollama/llama3 · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 8,192 tokens | 估算o200k_base |
| llama3:70bollama/llama3:70b · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 8,192 tokens | 估算o200k_base |
| llama3:8bollama/llama3:8b · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 8,192 tokens | 估算o200k_base |
| llama3.1ollama/llama3.1 · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 8,192 tokens | 估算o200k_base |
| Mistral 7B Instruct v0.1ollama/mistral-7B-Instruct-v0.1 · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 8,192 tokens | 估算o200k_base |
| Mistral 7B Instruct v0.2ollama/mistral-7B-Instruct-v0.2 · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,768 tokens | 估算o200k_base |
| Mistral large instruct 2407ollama/mistral-large-instruct-2407 · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 65,536 tokens | 估算o200k_base |
| mixtral 8x22B Instruct v0.1ollama/mixtral-8x22B-Instruct-v0.1 · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 65,536 tokens | 估算o200k_base |
| mixtral 8x7B Instruct v0.1ollama/mixtral-8x7B-Instruct-v0.1 · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,768 tokens | 估算o200k_base |
| qwen3 coder:480b cloudollama/qwen3-coder:480b-cloud · ollama | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 262,144 tokens | 估算o200k_base |
| openai.GPT 6 lunaopenai.gpt-6-luna · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 1,050,000 tokens | 估算o200k_base |
| openai.GPT 6 solopenai.gpt-6-sol · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,050,000 tokens | 估算o200k_base |
| openai.GPT oss 120b 1:0openai.gpt-oss-120b-1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| openai.GPT oss 20b 1:0openai.gpt-oss-20b-1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.30 | 128,000 tokens | 估算o200k_base |
| openai.GPT oss safeguard 120bopenai.gpt-oss-safeguard-120b · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| openai.GPT oss safeguard 20bopenai.gpt-oss-safeguard-20b · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.20 | 128,000 tokens | 估算o200k_base |
| beam freeopencode_go/beam-free · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 1,048,576 tokens | 估算o200k_base |
| Claude haiku 5 5opencode_go/claude-haiku-5-5 · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 proopencode_go/deepseek-v4-pro · opencode_go | LiteLLM ↗2026-10-25 UTC | $1.32 | $3.96 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4.1 flashopencode_go/deepseek-v4.1-flash · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| Gemini 4 argonopencode_go/gemini-4-argon · opencode_go | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,048,576 tokens | 估算o200k_base |
| glm 5.2opencode_go/glm-5.2 · opencode_go | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,000,000 tokens | 估算o200k_base |
| glm 5.3opencode_go/glm-5.3 · opencode_go | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,000,000 tokens | 估算o200k_base |
| glm 5.3 flashopencode_go/glm-5.3-flash · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,000,000 tokens | 估算o200k_base |
| hy3opencode_go/hy3 · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.58 | 192,000 tokens | 估算o200k_base |
| hy4 previewopencode_go/hy4-preview · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.834 | $2.501 | 1,024,000 tokens | 估算o200k_base |
| kimi k2.7 codeopencode_go/kimi-k2.7-code · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| kimi k3opencode_go/kimi-k3 · opencode_go | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,048,576 tokens | 估算o200k_base |
| kimi k3.1 proopencode_go/kimi-k3.1-pro · opencode_go | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,048,576 tokens | 估算o200k_base |
| longcat 2.0opencode_go/longcat-2.0 · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| longcat 2.5 preview freeopencode_go/longcat-2.5-preview-free · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 1,000,000 tokens | 估算o200k_base |
| mimo v2.5opencode_go/mimo-v2.5 · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 1,000,000 tokens | 估算o200k_base |
| mimo v2.5 proopencode_go/mimo-v2.5-pro · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.435 | $0.87 | 1,048,576 tokens | 估算o200k_base |
| mimo v2.6 flashopencode_go/mimo-v2.6-flash · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 1,048,576 tokens | 估算o200k_base |
| mimo v2.6 proopencode_go/mimo-v2.6-pro · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.435 | $0.87 | 1,048,576 tokens | 估算o200k_base |
| minimax m3opencode_go/minimax-m3 · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| minimax m3.1 flashopencode_go/minimax-m3.1-flash · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 1,000,000 tokens | 估算o200k_base |
| qwen3.7 plusopencode_go/qwen3.7-plus · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 1,000,000 tokens | 估算o200k_base |
| qwen3.8 flashopencode_go/qwen3.8-flash · opencode_go | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.47 | 1,000,000 tokens | 估算o200k_base |
| qwen3.8 maxopencode_go/qwen3.8-max · opencode_go | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 1,000,000 tokens | 估算o200k_base |
| step 5 previewopencode_go/step-5-preview · opencode_go | LiteLLM ↗2026-10-25 UTC | $1.00 | $2.70 | 1,000,000 tokens | 估算o200k_base |
| GLM 5.3 Flashopeninfer/@oi/GLM-5.3-Flash · openinfer | LiteLLM ↗2026-10-25 UTC | $0.195 | $1.56 | 393,216 tokens | 估算o200k_base |
| Qwen3.5 27Bopeninfer/@oi/Qwen3.5-27B · openinfer | LiteLLM ↗2026-10-25 UTC | $0.195 | $1.56 | 32,768 tokens | 估算o200k_base |
| Qwen3.5 9Bopeninfer/@oi/Qwen3.5-9B · openinfer | LiteLLM ↗2026-10-25 UTC | $5.00 | $0.15 | 100,000 tokens | 估算o200k_base |
| DeepSeek R1 Distill Llama 70Bovhcloud/DeepSeek-R1-Distill-Llama-70B · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.67 | $0.67 | 131,000 tokens | 估算o200k_base |
| GPT oss 120bovhcloud/gpt-oss-120b · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.40 | 131,000 tokens | 估算o200k_base |
| GPT oss 20bovhcloud/gpt-oss-20b · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.15 | 131,000 tokens | 估算o200k_base |
| Llama 3.1 8B Instructovhcloud/Llama-3.1-8B-Instruct · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 131,000 tokens | 估算o200k_base |
| llava v1.6 Mistral 7b hfovhcloud/llava-v1.6-mistral-7b-hf · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.29 | $0.29 | 32,000 tokens | 估算o200k_base |
| mamba codestral 7B v0.1ovhcloud/mamba-codestral-7B-v0.1 · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.19 | $0.19 | 256,000 tokens | 估算o200k_base |
| Meta Llama 3 1 70B Instructovhcloud/Meta-Llama-3_1-70B-Instruct · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.67 | $0.67 | 131,000 tokens | 估算o200k_base |
| Meta Llama 3 3 70B Instructovhcloud/Meta-Llama-3_3-70B-Instruct · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.67 | $0.67 | 131,000 tokens | 估算o200k_base |
| Mistral 7B Instruct v0.3ovhcloud/Mistral-7B-Instruct-v0.3 · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 127,000 tokens | 估算o200k_base |
| Mistral Nemo Instruct 2407ovhcloud/Mistral-Nemo-Instruct-2407 · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.13 | 118,000 tokens | 估算o200k_base |
| Mistral Small 3.2 24B Instruct 2506ovhcloud/Mistral-Small-3.2-24B-Instruct-2506 · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.28 | 128,000 tokens | 估算o200k_base |
| Mixtral 8x7B Instruct v0.1ovhcloud/Mixtral-8x7B-Instruct-v0.1 · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.63 | $0.63 | 32,000 tokens | 估算o200k_base |
| Qwen2.5 Coder 32B Instructovhcloud/Qwen2.5-Coder-32B-Instruct · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.87 | $0.87 | 32,000 tokens | 估算o200k_base |
| Qwen2.5 VL 72B Instructovhcloud/Qwen2.5-VL-72B-Instruct · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.91 | $0.91 | 32,000 tokens | 估算o200k_base |
| Qwen3 32Bovhcloud/Qwen3-32B · ovhcloud | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.23 | 32,000 tokens | 估算o200k_base |
| codellama 34b instructperplexity/codellama-34b-instruct · perplexity | LiteLLM ↗2026-10-25 UTC | $0.35 | $1.40 | 16,384 tokens | 估算o200k_base |
| codellama 70b instructperplexity/codellama-70b-instruct · perplexity | LiteLLM ↗2026-10-25 UTC | $0.70 | $2.80 | 16,384 tokens | 估算o200k_base |
| Llama 2 70b chatperplexity/llama-2-70b-chat · perplexity | LiteLLM ↗2026-10-25 UTC | $0.70 | $2.80 | 4,096 tokens | 估算o200k_base |
| Llama 3.1 70b instructperplexity/llama-3.1-70b-instruct · perplexity | LiteLLM ↗2026-10-25 UTC | $1.00 | $1.00 | 131,072 tokens | 估算o200k_base |
| Llama 3.1 8b instructperplexity/llama-3.1-8b-instruct · perplexity | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 131,072 tokens | 估算o200k_base |
| Mistral 7b instructperplexity/mistral-7b-instruct · perplexity | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.28 | 4,096 tokens | 估算o200k_base |
| mixtral 8x7b instructperplexity/mixtral-8x7b-instruct · perplexity | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.28 | 4,096 tokens | 估算o200k_base |
| pplx 70b chatperplexity/pplx-70b-chat · perplexity | LiteLLM ↗2026-10-25 UTC | $0.70 | $2.80 | 4,096 tokens | 估算o200k_base |
| pplx 70b onlineperplexity/pplx-70b-online · perplexity | LiteLLM ↗2026-10-25 UTC | $0.00 | $2.80 | 4,096 tokens | 估算o200k_base |
| pplx 7b chatperplexity/pplx-7b-chat · perplexity | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.28 | 8,192 tokens | 估算o200k_base |
| pplx 7b onlineperplexity/pplx-7b-online · perplexity | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.28 | 4,096 tokens | 估算o200k_base |
| sonarperplexity/sonar · perplexity | LiteLLM ↗2026-10-25 UTC | $1.00 | $1.00 | 128,000 tokens | 估算o200k_base |
| sonar deep researchperplexity/sonar-deep-research · perplexity | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 128,000 tokens | 估算o200k_base |
| sonar medium chatperplexity/sonar-medium-chat · perplexity | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.80 | 16,384 tokens | 估算o200k_base |
| sonar medium onlineperplexity/sonar-medium-online · perplexity | LiteLLM ↗2026-10-25 UTC | $0.00 | $1.80 | 12,000 tokens | 估算o200k_base |
| sonar properplexity/sonar-pro · perplexity | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| sonar reasoningperplexity/sonar-reasoning · perplexity | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 128,000 tokens | 估算o200k_base |
| sonar reasoning properplexity/sonar-reasoning-pro · perplexity | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 128,000 tokens | 估算o200k_base |
| sonar small chatperplexity/sonar-small-chat · perplexity | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.28 | 16,384 tokens | 估算o200k_base |
| sonar small onlineperplexity/sonar-small-online · perplexity | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.28 | 12,000 tokens | 估算o200k_base |
| DeepSeek v4 flashpinstripes/ps/deepseek-v4-flash · pinstripes | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.20 | 163,840 tokens | 估算o200k_base |
| glm 4.5 airpinstripes/ps/glm-4.5-air · pinstripes | LiteLLM ↗2026-10-25 UTC | $0.125 | $0.45 | 128,000 tokens | 估算o200k_base |
| minimax m2.7pinstripes/ps/minimax-m2.7 · pinstripes | LiteLLM ↗2026-10-25 UTC | $0.255 | $0.55 | 1,000,192 tokens | 估算o200k_base |
| qwen3 30b a3bpinstripes/ps/qwen3-30b-a3b · pinstripes | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.20 | 131,072 tokens | 估算o200k_base |
| qwen3 coder 30b a3bpinstripes/ps/qwen3-coder-30b-a3b · pinstripes | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.60 | 131,072 tokens | 估算o200k_base |
| qwen3.6 35b a3bpinstripes/ps/qwen3.6-35b-a3b · pinstripes | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.45 | 131,072 tokens | 估算o200k_base |
| DeepSeek v4 flashprism/deepseek-v4-flash · prism | LiteLLM ↗2026-10-25 UTC | $0.17 | $0.21 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4.1 flashprism/deepseek-v4.1-flash · prism | LiteLLM ↗2026-10-25 UTC | $0.17 | $0.63 | 1,000,000 tokens | 估算o200k_base |
| Gemma SEA LION v4 27B ITpublicai/aisingapore/Gemma-SEA-LION-v4-27B-IT · publicai | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 8,192 tokens | 估算o200k_base |
| Qwen SEA LION v4 32B ITpublicai/aisingapore/Qwen-SEA-LION-v4-32B-IT · publicai | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,768 tokens | 估算o200k_base |
| Olmo 3 32B Thinkpublicai/allenai/Olmo-3-32B-Think · publicai | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,768 tokens | 估算o200k_base |
| Olmo 3 7B Instructpublicai/allenai/Olmo-3-7B-Instruct · publicai | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,768 tokens | 估算o200k_base |
| Olmo 3 7B Thinkpublicai/allenai/Olmo-3-7B-Think · publicai | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,768 tokens | 估算o200k_base |
| ALIA 40b instruct Q8 0publicai/BSC-LT/ALIA-40b-instruct_Q8_0 · publicai | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 8,192 tokens | 估算o200k_base |
| salamandra 7b instruct tools 16kpublicai/BSC-LT/salamandra-7b-instruct-tools-16k · publicai | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 16,384 tokens | 估算o200k_base |
| apertus 70b instructpublicai/swiss-ai/apertus-70b-instruct · publicai | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 8,192 tokens | 估算o200k_base |
| apertus 8b instructpublicai/swiss-ai/apertus-8b-instruct · publicai | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 8,192 tokens | 估算o200k_base |
| DeepSeek v4 flashqwen_ai_platform/deepseek-v4-flash · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 flash 0731qwen_ai_platform/deepseek-v4-flash-0731 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 proqwen_ai_platform/deepseek-v4-pro · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $2.40 | $4.80 | 1,000,000 tokens | 估算o200k_base |
| glm 5.1qwen_ai_platform/glm-5.1 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 202,745 tokens | 估算o200k_base |
| glm 5.2qwen_ai_platform/glm-5.2 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| kimi k2.7 codeqwen_ai_platform/kimi-k2.7-code · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 229,376 tokens | 估算o200k_base |
| Qwen coderqwen_ai_platform/qwen-coder · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.50 | 1,000,000 tokens | 估算o200k_base |
| Qwen flashqwen_ai_platform/qwen-flash · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen flash 2025 07 28qwen_ai_platform/qwen-flash-2025-07-28 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen maxqwen_ai_platform/qwen-max · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $1.60 | $6.40 | 30,720 tokens | 估算o200k_base |
| Qwen plusqwen_ai_platform/qwen-plus · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 129,024 tokens | 估算o200k_base |
| Qwen plus 2025 01 25qwen_ai_platform/qwen-plus-2025-01-25 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 129,024 tokens | 估算o200k_base |
| Qwen plus 2025 04 28qwen_ai_platform/qwen-plus-2025-04-28 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 129,024 tokens | 估算o200k_base |
| Qwen plus 2025 07 14qwen_ai_platform/qwen-plus-2025-07-14 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 129,024 tokens | 估算o200k_base |
| Qwen plus 2025 07 28qwen_ai_platform/qwen-plus-2025-07-28 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen plus 2025 09 11qwen_ai_platform/qwen-plus-2025-09-11 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen plus latestqwen_ai_platform/qwen-plus-latest · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen turboqwen_ai_platform/qwen-turbo · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 129,024 tokens | 估算o200k_base |
| Qwen turbo 2024 11 01qwen_ai_platform/qwen-turbo-2024-11-01 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 1,000,000 tokens | 估算o200k_base |
| Qwen turbo 2025 04 28qwen_ai_platform/qwen-turbo-2025-04-28 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 1,000,000 tokens | 估算o200k_base |
| Qwen turbo latestqwen_ai_platform/qwen-turbo-latest · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 1,000,000 tokens | 估算o200k_base |
| qwen3 30b a3bqwen_ai_platform/qwen3-30b-a3b · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 129,024 tokens | 估算o200k_base |
| qwen3 coder flashqwen_ai_platform/qwen3-coder-flash · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| qwen3 coder flash 2025 07 28qwen_ai_platform/qwen3-coder-flash-2025-07-28 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| qwen3 coder plusqwen_ai_platform/qwen3-coder-plus · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| qwen3 coder plus 2025 07 22qwen_ai_platform/qwen3-coder-plus-2025-07-22 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| qwen3 maxqwen_ai_platform/qwen3-max · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 258,048 tokens | 估算o200k_base |
| qwen3 max 2026 01 23qwen_ai_platform/qwen3-max-2026-01-23 · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 258,048 tokens | 估算o200k_base |
| qwen3 max previewqwen_ai_platform/qwen3-max-preview · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 258,048 tokens | 估算o200k_base |
| qwen3 next 80b a3b instructqwen_ai_platform/qwen3-next-80b-a3b-instruct · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.20 | 262,144 tokens | 估算o200k_base |
| qwen3 next 80b a3b thinkingqwen_ai_platform/qwen3-next-80b-a3b-thinking · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.20 | 262,144 tokens | 估算o200k_base |
| qwen3 vl 235b a22b instructqwen_ai_platform/qwen3-vl-235b-a22b-instruct · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 235b a22b thinkingqwen_ai_platform/qwen3-vl-235b-a22b-thinking · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.40 | $4.00 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 32b instructqwen_ai_platform/qwen3-vl-32b-instruct · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.16 | $0.64 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 32b thinkingqwen_ai_platform/qwen3-vl-32b-thinking · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.16 | $2.87 | 131,072 tokens | 估算o200k_base |
| qwen3 vl plusqwen_ai_platform/qwen3-vl-plus · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 260,096 tokens | 估算o200k_base |
| qwen3.5 plusqwen_ai_platform/qwen3.5-plus · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 991,808 tokens | 估算o200k_base |
| qwen3.7 maxqwen_ai_platform/qwen3.7-max · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $2.50 | $7.50 | 991,808 tokens | 估算o200k_base |
| qwen3.7 plusqwen_ai_platform/qwen3.7-plus · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 991,808 tokens | 估算o200k_base |
| qwen3.8 flashqwen_ai_platform/qwen3.8-flash · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.47 | 991,808 tokens | 估算o200k_base |
| qwen3.8 maxqwen_ai_platform/qwen3.8-max · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 991,808 tokens | 估算o200k_base |
| qwen3.8 omni flashqwen_ai_platform/qwen3.8-omni-flash · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.47 | 991,808 tokens | 估算o200k_base |
| qwq plusqwen_ai_platform/qwq-plus · qwen_ai_platform | LiteLLM ↗2026-10-25 UTC | $0.80 | $2.40 | 98,304 tokens | 估算o200k_base |
| Qwen.qwen3 235b a22b 2507 v1:0qwen.qwen3-235b-a22b-2507-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.88 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 32b v1:0qwen.qwen3-32b-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 32,768 tokens | 估算o200k_base |
| Qwen.qwen3 coder 30b a3b v1:0qwen.qwen3-coder-30b-a3b-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 coder 480b a35b v1:0qwen.qwen3-coder-480b-a35b-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.45 | $1.80 | 262,144 tokens | 估算o200k_base |
| Qwen.qwen3 coder nextqwen.qwen3-coder-next · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.20 | 256,000 tokens | 估算o200k_base |
| Qwen.qwen3 next 80b a3bqwen.qwen3-next-80b-a3b · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.20 | 256,000 tokens | 估算o200k_base |
| Qwen.qwen3 vl 235b a22bqwen.qwen3-vl-235b-a22b · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.53 | $2.66 | 256,000 tokens | 估算o200k_base |
| DeepSeek v4 flashqwencloud/deepseek-v4-flash · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 flash 0731qwencloud/deepseek-v4-flash-0731 · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 proqwencloud/deepseek-v4-pro · qwencloud | LiteLLM ↗2026-10-25 UTC | $2.40 | $4.80 | 1,000,000 tokens | 估算o200k_base |
| glm 5.1qwencloud/glm-5.1 · qwencloud | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 202,745 tokens | 估算o200k_base |
| glm 5.2qwencloud/glm-5.2 · qwencloud | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,576 tokens | 估算o200k_base |
| kimi k2.7 codeqwencloud/kimi-k2.7-code · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 229,376 tokens | 估算o200k_base |
| Qwen coderqwencloud/qwen-coder · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.50 | 1,000,000 tokens | 估算o200k_base |
| Qwen flashqwencloud/qwen-flash · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen flash 2025 07 28qwencloud/qwen-flash-2025-07-28 · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen maxqwencloud/qwen-max · qwencloud | LiteLLM ↗2026-10-25 UTC | $1.60 | $6.40 | 30,720 tokens | 估算o200k_base |
| Qwen plusqwencloud/qwen-plus · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 129,024 tokens | 估算o200k_base |
| Qwen plus 2025 01 25qwencloud/qwen-plus-2025-01-25 · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 129,024 tokens | 估算o200k_base |
| Qwen plus 2025 04 28qwencloud/qwen-plus-2025-04-28 · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 129,024 tokens | 估算o200k_base |
| Qwen plus 2025 07 14qwencloud/qwen-plus-2025-07-14 · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 129,024 tokens | 估算o200k_base |
| Qwen plus 2025 07 28qwencloud/qwen-plus-2025-07-28 · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen plus 2025 09 11qwencloud/qwen-plus-2025-09-11 · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen plus latestqwencloud/qwen-plus-latest · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| Qwen turboqwencloud/qwen-turbo · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 129,024 tokens | 估算o200k_base |
| Qwen turbo 2024 11 01qwencloud/qwen-turbo-2024-11-01 · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 1,000,000 tokens | 估算o200k_base |
| Qwen turbo 2025 04 28qwencloud/qwen-turbo-2025-04-28 · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 1,000,000 tokens | 估算o200k_base |
| Qwen turbo latestqwencloud/qwen-turbo-latest · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 1,000,000 tokens | 估算o200k_base |
| qwen3 30b a3bqwencloud/qwen3-30b-a3b · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 129,024 tokens | 估算o200k_base |
| qwen3 coder flashqwencloud/qwen3-coder-flash · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| qwen3 coder flash 2025 07 28qwencloud/qwen3-coder-flash-2025-07-28 · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| qwen3 coder plusqwencloud/qwen3-coder-plus · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| qwen3 coder plus 2025 07 22qwencloud/qwen3-coder-plus-2025-07-22 · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 997,952 tokens | 估算o200k_base |
| qwen3 maxqwencloud/qwen3-max · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 258,048 tokens | 估算o200k_base |
| qwen3 max 2026 01 23qwencloud/qwen3-max-2026-01-23 · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 258,048 tokens | 估算o200k_base |
| qwen3 max previewqwencloud/qwen3-max-preview · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 258,048 tokens | 估算o200k_base |
| qwen3 next 80b a3b instructqwencloud/qwen3-next-80b-a3b-instruct · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.20 | 262,144 tokens | 估算o200k_base |
| qwen3 next 80b a3b thinkingqwencloud/qwen3-next-80b-a3b-thinking · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.20 | 262,144 tokens | 估算o200k_base |
| qwen3 vl 235b a22b instructqwencloud/qwen3-vl-235b-a22b-instruct · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 235b a22b thinkingqwencloud/qwen3-vl-235b-a22b-thinking · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.40 | $4.00 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 32b instructqwencloud/qwen3-vl-32b-instruct · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.16 | $0.64 | 131,072 tokens | 估算o200k_base |
| qwen3 vl 32b thinkingqwencloud/qwen3-vl-32b-thinking · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.16 | $2.87 | 131,072 tokens | 估算o200k_base |
| qwen3 vl plusqwencloud/qwen3-vl-plus · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 260,096 tokens | 估算o200k_base |
| qwen3.5 plusqwencloud/qwen3.5-plus · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 991,808 tokens | 估算o200k_base |
| qwen3.7 maxqwencloud/qwen3.7-max · qwencloud | LiteLLM ↗2026-10-25 UTC | $2.50 | $7.50 | 991,808 tokens | 估算o200k_base |
| qwen3.7 plusqwencloud/qwen3.7-plus · qwencloud | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 991,808 tokens | 估算o200k_base |
| qwen3.8 maxqwencloud/qwen3.8-max · qwencloud | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 991,808 tokens | 估算o200k_base |
| qwq plusqwencloud/qwq-plus · qwencloud | LiteLLM ↗2026-10-25 UTC | $0.80 | $2.40 | 98,304 tokens | 估算o200k_base |
| DeepSeek r1replicate/deepseek-ai/deepseek-r1 · replicate | LiteLLM ↗2026-10-25 UTC | $3.75 | $10.00 | 65,536 tokens | 估算o200k_base |
| DeepSeek v3replicate/deepseek-ai/deepseek-v3 · replicate | LiteLLM ↗2026-10-25 UTC | $1.45 | $1.45 | 65,536 tokens | 估算o200k_base |
| DeepSeek v3.1replicate/deepseek-ai/deepseek-v3.1 · replicate | LiteLLM ↗2026-10-25 UTC | $0.672 | $2.016 | 163,840 tokens | 估算o200k_base |
| Llama 2 13breplicate/meta/llama-2-13b · replicate | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 4,096 tokens | 估算o200k_base |
| Llama 2 13b chatreplicate/meta/llama-2-13b-chat · replicate | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 4,096 tokens | 估算o200k_base |
| Llama 2 70breplicate/meta/llama-2-70b · replicate | LiteLLM ↗2026-10-25 UTC | $0.65 | $2.75 | 4,096 tokens | 估算o200k_base |
| Llama 2 70b chatreplicate/meta/llama-2-70b-chat · replicate | LiteLLM ↗2026-10-25 UTC | $0.65 | $2.75 | 4,096 tokens | 估算o200k_base |
| Llama 2 7breplicate/meta/llama-2-7b · replicate | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.25 | 4,096 tokens | 估算o200k_base |
| Llama 2 7b chatreplicate/meta/llama-2-7b-chat · replicate | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.25 | 4,096 tokens | 估算o200k_base |
| Llama 3 70breplicate/meta/llama-3-70b · replicate | LiteLLM ↗2026-10-25 UTC | $0.65 | $2.75 | 8,192 tokens | 估算o200k_base |
| Llama 3 70b instructreplicate/meta/llama-3-70b-instruct · replicate | LiteLLM ↗2026-10-25 UTC | $0.65 | $2.75 | 8,192 tokens | 估算o200k_base |
| Llama 3 8breplicate/meta/llama-3-8b · replicate | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.25 | 8,086 tokens | 估算o200k_base |
| Llama 3 8b instructreplicate/meta/llama-3-8b-instruct · replicate | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.25 | 8,086 tokens | 估算o200k_base |
| Mistral 7b instruct v0.2replicate/mistralai/mistral-7b-instruct-v0.2 · replicate | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.25 | 4,096 tokens | 估算o200k_base |
| Mistral 7b v0.1replicate/mistralai/mistral-7b-v0.1 · replicate | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.25 | 4,096 tokens | 估算o200k_base |
| mixtral 8x7b instruct v0.1replicate/mistralai/mixtral-8x7b-instruct-v0.1 · replicate | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.00 | 4,096 tokens | 估算o200k_base |
| meta textgeneration Llama 2 13b fsagemaker/meta-textgeneration-llama-2-13b-f · sagemaker | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 4,096 tokens | 估算o200k_base |
| meta textgeneration Llama 2 70b b fsagemaker/meta-textgeneration-llama-2-70b-b-f · sagemaker | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 4,096 tokens | 估算o200k_base |
| meta textgeneration Llama 2 7b fsagemaker/meta-textgeneration-llama-2-7b-f · sagemaker | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 4,096 tokens | 估算o200k_base |
| DeepSeek V4 Flash 0731sail/deepseek-ai/DeepSeek-V4-Flash-0731 · sail | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.18 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Pro 0813sail/deepseek-ai/DeepSeek-V4-Pro-0813 · sail | LiteLLM ↗2026-10-25 UTC | $0.92 | $2.77 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4.1 Flashsail/deepseek-ai/DeepSeek-V4.1-Flash · sail | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.30 | 1,048,576 tokens | 估算o200k_base |
| gemma 4 12B itsail/google/gemma-4-12B-it · sail | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.00 | 16,384 tokens | 估算o200k_base |
| gemma 4 31B itsail/google/gemma-4-31B-it · sail | LiteLLM ↗2026-10-25 UTC | $0.40 | $0.60 | 256,000 tokens | 估算o200k_base |
| Kimi K2.6sail/moonshotai/Kimi-K2.6 · sail | LiteLLM ↗2026-10-25 UTC | $1.00 | $4.00 | 262,144 tokens | 估算o200k_base |
| Kimi K3sail/moonshotai/Kimi-K3 · sail | LiteLLM ↗2026-10-25 UTC | $2.50 | $12.50 | 1,048,576 tokens | 估算o200k_base |
| Gemma 4 31B IT NVFP4sail/nvidia/Gemma-4-31B-IT-NVFP4 · sail | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.40 | 262,144 tokens | 估算o200k_base |
| GPT oss 120bsail/openai/gpt-oss-120b · sail | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.40 | 131,072 tokens | 估算o200k_base |
| Qwen3.6 35B A3Bsail/Qwen/Qwen3.6-35B-A3B · sail | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.40 | 262,144 tokens | 估算o200k_base |
| GLM 5.3sail/zai-org/GLM-5.3 · sail | LiteLLM ↗2026-10-25 UTC | $0.98 | $3.08 | 1,048,576 tokens | 估算o200k_base |
| GLM 5.3 Flashsail/zai-org/GLM-5.3-Flash · sail | LiteLLM ↗2026-10-25 UTC | $0.11 | $0.35 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek R1sambanova/DeepSeek-R1 · sambanova | LiteLLM ↗2026-10-25 UTC | $5.00 | $7.00 | 32,768 tokens | 估算o200k_base |
| DeepSeek V3.1sambanova/DeepSeek-V3.1 · sambanova | LiteLLM ↗2026-10-25 UTC | $3.00 | $4.50 | 131,072 tokens | 估算o200k_base |
| DeepSeek V3.2sambanova/DeepSeek-V3.2 · sambanova | LiteLLM ↗2026-10-25 UTC | $3.00 | $4.50 | 32,768 tokens | 估算o200k_base |
| gemma 4 31B itsambanova/gemma-4-31B-it · sambanova | LiteLLM ↗2026-10-25 UTC | $0.38 | $1.15 | 131,072 tokens | 估算o200k_base |
| GPT oss 120bsambanova/gpt-oss-120b · sambanova | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.59 | 131,072 tokens | 估算o200k_base |
| Llama 4 Maverick 17B 128E Instructsambanova/Llama-4-Maverick-17B-128E-Instruct · sambanova | LiteLLM ↗2026-10-25 UTC | $0.63 | $1.80 | 131,072 tokens | 估算o200k_base |
| Meta Llama 3.3 70B Instructsambanova/Meta-Llama-3.3-70B-Instruct · sambanova | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.20 | 131,072 tokens | 估算o200k_base |
| MiniMax M2.7sambanova/MiniMax-M2.7 · sambanova | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.40 | 196,608 tokens | 估算o200k_base |
| sarvam msarvam/sarvam-m · sarvam | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 8,192 tokens | 估算o200k_base |
| DeepSeek v4 flash 0731scaleway/deepseek-v4-flash-0731 · scaleway | LiteLLM ↗2026-10-25 UTC | $0.40 | $0.80 | 256,000 tokens | 估算o200k_base |
| glm 5.2scaleway/glm-5.2 · scaleway | LiteLLM ↗2026-10-25 UTC | $1.80 | $5.50 | 256,000 tokens | 估算o200k_base |
| gemma 4 26b a4b itscaleway/google/gemma-4-26b-a4b-it · scaleway | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.50 | 256,000 tokens | 估算o200k_base |
| Llama 3.3 70b instructscaleway/meta/llama-3.3-70b-instruct · scaleway | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 128,000 tokens | 估算o200k_base |
| Mistral medium 3.5 128bscaleway/mistralai/mistral-medium-3.5-128b · scaleway | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 256,000 tokens | 估算o200k_base |
| Mistral small 3.2 24b instruct 2506scaleway/mistralai/mistral-small-3.2-24b-instruct-2506 · scaleway | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.35 | 128,000 tokens | 估算o200k_base |
| pixtral 12b 2409scaleway/mistralai/pixtral-12b-2409 · scaleway | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 128,000 tokens | 估算o200k_base |
| GPT oss 120bscaleway/openai/gpt-oss-120b · scaleway | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| qwen3 235b a22b instruct 2507scaleway/qwen/qwen3-235b-a22b-instruct-2507 · scaleway | LiteLLM ↗2026-10-25 UTC | $0.75 | $2.25 | 256,000 tokens | 估算o200k_base |
| qwen3 coder 30b a3b instructscaleway/qwen/qwen3-coder-30b-a3b-instruct · scaleway | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.80 | 128,000 tokens | 估算o200k_base |
| qwen3.5 397b a17bscaleway/qwen/qwen3.5-397b-a17b · scaleway | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.60 | 256,000 tokens | 估算o200k_base |
| qwen3.6 35b a3bscaleway/qwen/qwen3.6-35b-a3b · scaleway | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.50 | 256,000 tokens | 估算o200k_base |
| DeepSeek V4.1 flashscx-ai/DeepSeek-V4.1-flash · scx-ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 1,000,000 tokens | 估算o200k_base |
| GLM 5.2scx-ai/GLM-5.2 · scx-ai | LiteLLM ↗2026-10-25 UTC | $0.61 | $1.98 | 1,048,576 tokens | 估算o200k_base |
| GLM 5.3scx-ai/GLM-5.3 · scx-ai | LiteLLM ↗2026-10-25 UTC | $0.98 | $3.08 | 1,000,000 tokens | 估算o200k_base |
| Kimi K3scx-ai/Kimi-K3 · scx-ai | LiteLLM ↗2026-10-25 UTC | $2.83 | $14.13 | 1,000,000 tokens | 估算o200k_base |
| Qwen3.8 Maxscx-ai/Qwen3.8-Max · scx-ai | LiteLLM ↗2026-10-25 UTC | $1.65 | $4.99 | 1,000,000 tokens | 估算o200k_base |
| Claude 3 5 sonnetsnowflake/claude-3-5-sonnet · snowflake | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude 3 7 sonnetsnowflake/claude-3-7-sonnet · snowflake | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude 4 opussnowflake/claude-4-opus · snowflake | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| Claude 4 sonnetsnowflake/claude-4-sonnet · snowflake | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude haiku 4 5snowflake/claude-haiku-4-5 · snowflake | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 4 5snowflake/claude-sonnet-4-5 · snowflake | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 4 6snowflake/claude-sonnet-4-6 · snowflake | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| DeepSeek r1snowflake/deepseek-r1 · snowflake | LiteLLM ↗2026-10-25 UTC | $1.35 | $5.40 | 128,000 tokens | 估算o200k_base |
| gemma 7bsnowflake/gemma-7b · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 8,000 tokens | 估算o200k_base |
| jamba 1.5 largesnowflake/jamba-1.5-large · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 256,000 tokens | 估算o200k_base |
| jamba 1.5 minisnowflake/jamba-1.5-mini · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 256,000 tokens | 估算o200k_base |
| jamba instructsnowflake/jamba-instruct · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 256,000 tokens | 估算o200k_base |
| llama2 70b chatsnowflake/llama2-70b-chat · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 4,096 tokens | 估算o200k_base |
| llama3 70bsnowflake/llama3-70b · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 8,000 tokens | 估算o200k_base |
| llama3 8bsnowflake/llama3-8b · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 8,000 tokens | 估算o200k_base |
| llama3.1 405bsnowflake/llama3.1-405b · snowflake | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 128,000 tokens | 估算o200k_base |
| llama3.1 70bsnowflake/llama3.1-70b · snowflake | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| llama3.1 8bsnowflake/llama3.1-8b · snowflake | LiteLLM ↗2026-10-25 UTC | $0.24 | $0.24 | 128,000 tokens | 估算o200k_base |
| llama3.2 1bsnowflake/llama3.2-1b · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 128,000 tokens | 估算o200k_base |
| llama3.2 3bsnowflake/llama3.2-3b · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 128,000 tokens | 估算o200k_base |
| llama3.3 70bsnowflake/llama3.3-70b · snowflake | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| llama4 mavericksnowflake/llama4-maverick · snowflake | LiteLLM ↗2026-10-25 UTC | $0.24 | $0.97 | 128,000 tokens | 估算o200k_base |
| Mistral 7bsnowflake/mistral-7b · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 32,000 tokens | 估算o200k_base |
| Mistral largesnowflake/mistral-large · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 32,000 tokens | 估算o200k_base |
| Mistral large2snowflake/mistral-large2 · snowflake | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| mixtral 8x7bsnowflake/mixtral-8x7b · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 32,000 tokens | 估算o200k_base |
| openai GPT 4.1snowflake/openai-gpt-4.1 · snowflake | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 300,000 tokens | 估算o200k_base |
| openai GPT 5snowflake/openai-gpt-5 · snowflake | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 300,000 tokens | 估算o200k_base |
| openai GPT 5 minisnowflake/openai-gpt-5-mini · snowflake | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| openai GPT 5 nanosnowflake/openai-gpt-5-nano · snowflake | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 5,000,000 tokens | 估算o200k_base |
| reka coresnowflake/reka-core · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 32,000 tokens | 估算o200k_base |
| reka flashsnowflake/reka-flash · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 100,000 tokens | 估算o200k_base |
| snowflake arcticsnowflake/snowflake-arctic · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 4,096 tokens | 估算o200k_base |
| snowflake Llama 3.1 405bsnowflake/snowflake-llama-3.1-405b · snowflake | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 8,000 tokens | 估算o200k_base |
| snowflake Llama 3.3 70bsnowflake/snowflake-llama-3.3-70b · snowflake | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| DeepSeek v4 flashtencent/deepseek-v4-flash · tencent | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 protencent/deepseek-v4-pro · tencent | LiteLLM ↗2026-10-25 UTC | $1.74 | $3.48 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4 pro 0813tencent/deepseek-v4-pro-0813 · tencent | LiteLLM ↗2026-10-25 UTC | $1.32 | $3.96 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek v4.1 flashtencent/deepseek-v4.1-flash · tencent | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| glm 5.2tencent/glm-5.2 · tencent | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,000,000 tokens | 估算o200k_base |
| glm 5.3tencent/glm-5.3 · tencent | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,000,000 tokens | 估算o200k_base |
| glm 5.3 flashtencent/glm-5.3-flash · tencent | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,000,000 tokens | 估算o200k_base |
| glm 5.3 flashxtencent/glm-5.3-flashx · tencent | LiteLLM ↗2026-10-25 UTC | $0.37 | $1.25 | 1,000,000 tokens | 估算o200k_base |
| kimi k2.7 codetencent/kimi-k2.7-code · tencent | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 256,000 tokens | 估算o200k_base |
| kimi k2.7 code highspeedtencent/kimi-k2.7-code-highspeed · tencent | LiteLLM ↗2026-10-25 UTC | $1.90 | $8.00 | 256,000 tokens | 估算o200k_base |
| kimi k2.8 previewtencent/kimi-k2.8-preview · tencent | LiteLLM ↗2026-10-25 UTC | $1.00 | $4.00 | 1,000,000 tokens | 估算o200k_base |
| kimi k3tencent/kimi-k3 · tencent | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,000,000 tokens | 估算o200k_base |
| minimax m3tencent/minimax-m3 · tencent | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,000,000 tokens | 估算o200k_base |
| DeepSeek V4 Flashtensormesh/deepseek-ai/DeepSeek-V4-Flash · tensormesh | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 32,768 tokens | 估算o200k_base |
| gemma 4 31B ittensormesh/google/gemma-4-31B-it · tensormesh | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.56 | 32,768 tokens | 估算o200k_base |
| GLM 5.1 NVFP4 MTPtensormesh/lukealonso/GLM-5.1-NVFP4-MTP · tensormesh | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 202,752 tokens | 估算o200k_base |
| MiniMax M2.5tensormesh/MiniMaxAI/MiniMax-M2.5 · tensormesh | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,608 tokens | 估算o200k_base |
| Kimi K2.6tensormesh/moonshotai/Kimi-K2.6 · tensormesh | LiteLLM ↗2026-10-25 UTC | $0.96 | $4.00 | 32,768 tokens | 估算o200k_base |
| GPT oss 120btensormesh/openai/gpt-oss-120b · tensormesh | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| GPT oss 20btensormesh/openai/gpt-oss-20b · tensormesh | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.28 | 131,072 tokens | 估算o200k_base |
| Qwen3 Coder 480B A35B Instruct FP8tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 · tensormesh | LiteLLM ↗2026-10-25 UTC | $0.45 | $1.80 | 262,144 tokens | 估算o200k_base |
| Qwen3.5 397B A17B FP8tensormesh/Qwen/Qwen3.5-397B-A17B-FP8 · tensormesh | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.60 | 262,144 tokens | 估算o200k_base |
| Qwen3.6 27B FP8tensormesh/Qwen/Qwen3.6-27B-FP8 · tensormesh | LiteLLM ↗2026-10-25 UTC | $0.32 | $3.20 | 262,144 tokens | 估算o200k_base |
| trinity minitogether_ai/arcee-ai/trinity-mini · together_ai | LiteLLM ↗2026-10-25 UTC | $0.045 | $0.15 | 128,000 tokens | 估算o200k_base |
| Qwen 2 1.5b instructtogether_ai/arize-ai/qwen-2-1.5b-instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 32,768 tokens | 估算o200k_base |
| DeepSeek coder 33b instructtogether_ai/deepseek-ai/deepseek-coder-33b-instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.80 | $0.80 | 16,384 tokens | 估算o200k_base |
| DeepSeek R1 0528together_ai/deepseek-ai/DeepSeek-R1-0528 · together_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $7.00 | 163,840 tokens | 估算o200k_base |
| DeepSeek R1 Distill Llama 70Btogether_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B · together_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $2.00 | 131,072 tokens | 估算o200k_base |
| DeepSeek R1 Distill Qwen 1.5Btogether_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B · together_ai | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.18 | 131,072 tokens | 估算o200k_base |
| DeepSeek R1 Distill Qwen 14Btogether_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B · together_ai | LiteLLM ↗2026-10-25 UTC | $1.60 | $1.60 | 131,072 tokens | 估算o200k_base |
| DeepSeek V3together_ai/deepseek-ai/DeepSeek-V3 · together_ai | LiteLLM ↗2026-10-25 UTC | $1.25 | $1.25 | 65,536 tokens | 估算o200k_base |
| DeepSeek V3.1together_ai/deepseek-ai/DeepSeek-V3.1 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.70 | 131,072 tokens | 估算o200k_base |
| DeepSeek V4 Flash 0731together_ai/deepseek-ai/DeepSeek-V4-Flash-0731 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4 Pro 0813together_ai/deepseek-ai/DeepSeek-V4-Pro-0813 · together_ai | LiteLLM ↗2026-10-25 UTC | $1.32 | $3.96 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4.1 Flashtogether_ai/deepseek-ai/DeepSeek-V4.1-Flash · together_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| DeepSeek V4.1 Flash 1017together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| gemma 2 27b ittogether_ai/google/gemma-2-27b-it · together_ai | LiteLLM ↗2026-10-25 UTC | $0.80 | $0.80 | 8,192 tokens | 估算o200k_base |
| gemma 4 31B ittogether_ai/google/gemma-4-31B-it · together_ai | LiteLLM ↗2026-10-25 UTC | $0.39 | $0.97 | 262,144 tokens | 估算o200k_base |
| Llama 3 8b chat hftogether_ai/meta-llama/Llama-3-8b-chat-hf · together_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| Llama 3.1 405B Instructtogether_ai/meta-llama/Llama-3.1-405B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $3.50 | $3.50 | 4,096 tokens | 估算o200k_base |
| Llama 3.2 1B Instructtogether_ai/meta-llama/Llama-3.2-1B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.06 | 131,072 tokens | 估算o200k_base |
| Llama 3.2 3B Instructtogether_ai/meta-llama/Llama-3.2-3B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.06 | 131,072 tokens | 估算o200k_base |
| Llama 3.3 70B Instruct Turbotogether_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo · together_ai | LiteLLM ↗2026-10-25 UTC | $1.04 | $1.04 | 131,072 tokens | 估算o200k_base |
| Llama 4 Scout 17B 16E Instructtogether_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.59 | 1,048,576 tokens | 估算o200k_base |
| Meta Llama 3 70B Instruct Turbotogether_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo · together_ai | LiteLLM ↗2026-10-25 UTC | $0.88 | $0.88 | 8,192 tokens | 估算o200k_base |
| Meta Llama 3 8B Instructtogether_ai/meta-llama/Meta-Llama-3-8B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| Meta Llama 3.1 70B Instruct Turbotogether_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo · together_ai | LiteLLM ↗2026-10-25 UTC | $0.88 | $0.88 | 131,072 tokens | 估算o200k_base |
| Meta Llama 3.1 8B Instruct Turbotogether_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo · together_ai | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.18 | 131,072 tokens | 估算o200k_base |
| Muse Glimmer 30Btogether_ai/meta-models/Muse-Glimmer-30B · together_ai | LiteLLM ↗2026-10-25 UTC | $0.35 | $1.50 | 131,072 tokens | 估算o200k_base |
| Muse Spark Open 816B A42Btogether_ai/meta-models/Muse-Spark-Open-816B-A42B · together_ai | LiteLLM ↗2026-10-25 UTC | $1.25 | $4.25 | 1,048,576 tokens | 估算o200k_base |
| MiniMax M2.7together_ai/MiniMaxAI/MiniMax-M2.7 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,608 tokens | 估算o200k_base |
| MiniMax M3together_ai/MiniMaxAI/MiniMax-M3 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 524,288 tokens | 估算o200k_base |
| MiniMax M3.1 Flashtogether_ai/MiniMaxAI/MiniMax-M3.1-Flash · together_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 1,048,576 tokens | 估算o200k_base |
| Ministral 3 14B Instruct 2512together_ai/mistralai/Ministral-3-14B-Instruct-2512 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 262,144 tokens | 估算o200k_base |
| Mistral 7B Instruct v0.1together_ai/mistralai/Mistral-7B-Instruct-v0.1 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| Mistral 7B Instruct v0.3together_ai/mistralai/Mistral-7B-Instruct-v0.3 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 32,768 tokens | 估算o200k_base |
| Mistral Small 24B Instruct 2501together_ai/mistralai/Mistral-Small-24B-Instruct-2501 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 32,768 tokens | 估算o200k_base |
| Mixtral 8x7B Instruct v0.1together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $0.60 | 32,768 tokens | 估算o200k_base |
| Kimi K2.5 fp4together_ai/moonshotai/Kimi-K2.5-fp4 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $2.80 | 262,144 tokens | 估算o200k_base |
| Kimi K2.6together_ai/moonshotai/Kimi-K2.6 · together_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $4.50 | 262,144 tokens | 估算o200k_base |
| Kimi K2.7 Codetogether_ai/moonshotai/Kimi-K2.7-Code · together_ai | LiteLLM ↗2026-10-25 UTC | $0.95 | $4.00 | 262,144 tokens | 估算o200k_base |
| Kimi K3together_ai/moonshotai/Kimi-K3 · together_ai | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,048,576 tokens | 估算o200k_base |
| Nous Hermes 2 Mixtral 8x7B DPOtogether_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO · together_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $0.60 | 32,768 tokens | 估算o200k_base |
| Llama 3.1 Nemotron 70B Instruct HFtogether_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF · together_ai | LiteLLM ↗2026-10-25 UTC | $0.88 | $0.88 | 32,768 tokens | 估算o200k_base |
| nemotron 3 ultra 550b a55btogether_ai/nvidia/nemotron-3-ultra-550b-a55b · together_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.60 | 512,288 tokens | 估算o200k_base |
| NVIDIA Nemotron 3.5 Super VLtogether_ai/nvidia/NVIDIA-Nemotron-3.5-Super-VL · together_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 262,144 tokens | 估算o200k_base |
| NVIDIA Nemotron Nano 9B v2together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.25 | 131,072 tokens | 估算o200k_base |
| GPT oss 120btogether_ai/openai/gpt-oss-120b · together_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 131,072 tokens | 估算o200k_base |
| GPT oss 20btogether_ai/openai/gpt-oss-20b · together_ai | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.20 | 131,072 tokens | 估算o200k_base |
| Ternary Bonsai 27Btogether_ai/Prism-ML/Ternary-Bonsai-27B · together_ai | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 262,144 tokens | 估算o200k_base |
| Qwen2 1.5B Instructtogether_ai/Qwen/Qwen2-1.5B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.02 | $0.02 | 32,768 tokens | 估算o200k_base |
| Qwen2 72B Instructtogether_ai/Qwen/Qwen2-72B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 32,768 tokens | 估算o200k_base |
| Qwen2 VL 72B Instructtogether_ai/Qwen/Qwen2-VL-72B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 32,768 tokens | 估算o200k_base |
| Qwen2.5 14B Instructtogether_ai/Qwen/Qwen2.5-14B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.80 | $0.80 | 32,768 tokens | 估算o200k_base |
| Qwen2.5 72B Instructtogether_ai/Qwen/Qwen2.5-72B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 32,768 tokens | 估算o200k_base |
| Qwen2.5 72B Instruct Turbotogether_ai/Qwen/Qwen2.5-72B-Instruct-Turbo · together_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 131,072 tokens | 估算o200k_base |
| Qwen2.5 7B Instruct Turbotogether_ai/Qwen/Qwen2.5-7B-Instruct-Turbo · together_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.30 | 32,768 tokens | 估算o200k_base |
| Qwen2.5 Coder 32B Instructtogether_ai/Qwen/Qwen2.5-Coder-32B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.80 | $0.80 | 16,384 tokens | 估算o200k_base |
| Qwen2.5 VL 72B Instructtogether_ai/Qwen/Qwen2.5-VL-72B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $1.95 | $8.00 | 32,768 tokens | 估算o200k_base |
| Qwen3 Coder 480B A35B Instruct FP8together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 · together_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $2.00 | 262,144 tokens | 估算o200k_base |
| Qwen3 Coder Next FP8together_ai/Qwen/Qwen3-Coder-Next-FP8 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.20 | 262,144 tokens | 估算o200k_base |
| Qwen3 Next 80B A3B Instructtogether_ai/Qwen/Qwen3-Next-80B-A3B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.50 | 262,144 tokens | 估算o200k_base |
| Qwen3 Next 80B A3B Thinkingtogether_ai/Qwen/Qwen3-Next-80B-A3B-Thinking · together_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.50 | 262,144 tokens | 估算o200k_base |
| Qwen3 VL 32B Instructtogether_ai/Qwen/Qwen3-VL-32B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 262,144 tokens | 估算o200k_base |
| Qwen3 VL 8B Instructtogether_ai/Qwen/Qwen3-VL-8B-Instruct · together_ai | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.68 | 262,144 tokens | 估算o200k_base |
| Qwen3.5 397B A17Btogether_ai/Qwen/Qwen3.5-397B-A17B · together_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.60 | 262,144 tokens | 估算o200k_base |
| Qwen3.5 9Btogether_ai/Qwen/Qwen3.5-9B · together_ai | LiteLLM ↗2026-10-25 UTC | $0.17 | $0.25 | 262,144 tokens | 估算o200k_base |
| Qwen3.6 Plustogether_ai/Qwen/Qwen3.6-Plus · together_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $3.00 | 1,000,000 tokens | 估算o200k_base |
| Qwen3.7 Maxtogether_ai/Qwen/Qwen3.7-Max · together_ai | LiteLLM ↗2026-10-25 UTC | $1.50 | $4.50 | 1,000,000 tokens | 估算o200k_base |
| Qwen3.7 Plustogether_ai/Qwen/Qwen3.7-Plus · together_ai | LiteLLM ↗2026-10-25 UTC | $0.32 | $1.28 | 1,000,000 tokens | 估算o200k_base |
| Qwen3.8 2.4T A95Btogether_ai/Qwen/Qwen3.8-2.4T-A95B · together_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 1,010,000 tokens | 估算o200k_base |
| Qwen3.8 Flashtogether_ai/Qwen/Qwen3.8-Flash · together_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.47 | 1,000,000 tokens | 估算o200k_base |
| QwQ 32Btogether_ai/Qwen/QwQ-32B · together_ai | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 131,072 tokens | 估算o200k_base |
| Beam 1.0 501B A23Btogether_ai/reflection/Beam-1.0-501B-A23B · together_ai | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| Inklingtogether_ai/thinkingmachines/Inkling · together_ai | LiteLLM ↗2026-10-25 UTC | $1.00 | $4.05 | 524,288 tokens | 估算o200k_base |
| Tev1 4B experimentaltogether_ai/together/Tev1-4B-experimental · together_ai | LiteLLM ↗2026-10-25 UTC | $0.042 | $0.00 | 32,768 tokens | 估算o200k_base |
| GLM 4.5 Air FP8together_ai/zai-org/GLM-4.5-Air-FP8 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.10 | 131,072 tokens | 估算o200k_base |
| GLM 4.6together_ai/zai-org/GLM-4.6 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 202,752 tokens | 估算o200k_base |
| GLM 4.7together_ai/zai-org/GLM-4.7 · together_ai | LiteLLM ↗2026-10-25 UTC | $0.45 | $2.00 | 202,752 tokens | 估算o200k_base |
| GLM 5together_ai/zai-org/GLM-5 · together_ai | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.20 | 202,752 tokens | 估算o200k_base |
| GLM 5.1together_ai/zai-org/GLM-5.1 · together_ai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 202,752 tokens | 估算o200k_base |
| GLM 5.2together_ai/zai-org/GLM-5.2 · together_ai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,575 tokens | 估算o200k_base |
| GLM 5.3together_ai/zai-org/GLM-5.3 · together_ai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,048,575 tokens | 估算o200k_base |
| GLM 5.3 Flashtogether_ai/zai-org/GLM-5.3-Flash · together_ai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,048,575 tokens | 估算o200k_base |
| together ai 8.1b 21btogether-ai-8.1b-21b · together_ai | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.30 | 1,000 tokens | 估算o200k_base |
| twelvelabs.pegasus 1 5 v1:0twelvelabs.pegasus-1-5-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | $7.50 | 261,120 tokens | 估算o200k_base |
| us gov.anthropic.Claude fable 5 1us-gov.anthropic.claude-fable-5-1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $12.00 | $60.00 | 1,000,000 tokens | 估算o200k_base |
| us gov.anthropic.Claude haiku 5 5us-gov.anthropic.claude-haiku-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.12 | $0.60 | 1,000,000 tokens | 估算o200k_base |
| us gov.anthropic.Claude opus 4 8us-gov.anthropic.claude-opus-4-8 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $6.00 | $30.00 | 1,000,000 tokens | 估算o200k_base |
| us gov.anthropic.Claude opus 5us-gov.anthropic.claude-opus-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $6.00 | $30.00 | 1,000,000 tokens | 估算o200k_base |
| us gov.anthropic.Claude opus 5 5us-gov.anthropic.claude-opus-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $4.80 | $24.00 | 1,000,000 tokens | 估算o200k_base |
| us gov.anthropic.Claude sonnet 4 5 20250929 v1:0us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.60 | $18.00 | 200,000 tokens | 估算o200k_base |
| us gov.anthropic.Claude sonnet 5us-gov.anthropic.claude-sonnet-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.40 | $12.00 | 1,000,000 tokens | 估算o200k_base |
| us gov.anthropic.Claude sonnet 5 5us-gov.anthropic.claude-sonnet-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.40 | $12.00 | 1,000,000 tokens | 估算o200k_base |
| us gov.nvidia.nemotron nano 12b v2us-gov.nvidia.nemotron-nano-12b-v2 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.24 | $0.72 | 128,000 tokens | 估算o200k_base |
| us gov.nvidia.nemotron nano 3 30bus-gov.nvidia.nemotron-nano-3-30b · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.072 | $0.288 | 262,144 tokens | 估算o200k_base |
| us gov.nvidia.nemotron nano 9b v2us-gov.nvidia.nemotron-nano-9b-v2 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.072 | $0.276 | 128,000 tokens | 估算o200k_base |
| us gov.nvidia.nemotron super 3 120bus-gov.nvidia.nemotron-super-3-120b · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.78 | 256,000 tokens | 估算o200k_base |
| us gov.openai.GPT oss 120b 1:0us-gov.openai.gpt-oss-120b-1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.18 | $0.72 | 128,000 tokens | 估算o200k_base |
| us gov.openai.GPT oss 20b 1:0us-gov.openai.gpt-oss-20b-1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.084 | $0.36 | 128,000 tokens | 估算o200k_base |
| us gov.xai.grok 4.6us-gov.xai.grok-4.6 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.64 | $7.92 | 500,000 tokens | 估算o200k_base |
| us.amazon.nova 2 lite v1:0us.amazon.nova-2-lite-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.33 | $2.75 | 1,000,000 tokens | 估算o200k_base |
| us.amazon.nova 2 pro preview 20251202 v1:0us.amazon.nova-2-pro-preview-20251202-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.375 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| us.amazon.nova lite v1:0us.amazon.nova-lite-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.24 | 300,000 tokens | 估算o200k_base |
| us.amazon.nova micro v1:0us.amazon.nova-micro-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.035 | $0.14 | 128,000 tokens | 估算o200k_base |
| us.amazon.nova pro v1:0us.amazon.nova-pro-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.80 | $3.20 | 300,000 tokens | 估算o200k_base |
| us.anthropic.Claude 3 5 haiku 20241022 v1:0us.anthropic.claude-3-5-haiku-20241022-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.80 | $4.00 | 200,000 tokens | 估算o200k_base |
| us.anthropic.Claude 3 5 sonnet 20240620 v1:0us.anthropic.claude-3-5-sonnet-20240620-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| us.anthropic.Claude 3 5 sonnet 20241022 v2:0us.anthropic.claude-3-5-sonnet-20241022-v2:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| us.anthropic.Claude 3 7 sonnet 20250219 v1:0us.anthropic.claude-3-7-sonnet-20250219-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| us.anthropic.Claude 3 opus 20240229 v1:0us.anthropic.claude-3-opus-20240229-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| us.anthropic.Claude fable 5us.anthropic.claude-fable-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $11.00 | $55.00 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude fable 5 1us.anthropic.claude-fable-5-1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $11.00 | $55.00 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude haiku 4 5 20251001 v1:0us.anthropic.claude-haiku-4-5-20251001-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.10 | $5.50 | 200,000 tokens | 估算o200k_base |
| us.anthropic.Claude haiku 5 5us.anthropic.claude-haiku-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.11 | $0.55 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude mythos 5us.anthropic.claude-mythos-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $11.00 | $55.00 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude mythos 5 1us.anthropic.claude-mythos-5-1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $11.00 | $55.00 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude mythos previewus.anthropic.claude-mythos-preview · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $27.50 | $137.50 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude opus 4 1 20250805 v1:0us.anthropic.claude-opus-4-1-20250805-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| us.anthropic.Claude opus 4 20250514 v1:0us.anthropic.claude-opus-4-20250514-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| us.anthropic.Claude opus 4 5 20251101 v1:0us.anthropic.claude-opus-4-5-20251101-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 200,000 tokens | 估算o200k_base |
| us.anthropic.Claude opus 4 6 v1us.anthropic.claude-opus-4-6-v1 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude opus 4 7us.anthropic.claude-opus-4-7 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude opus 4 8us.anthropic.claude-opus-4-8 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude opus 5us.anthropic.claude-opus-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $27.50 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude opus 5 5us.anthropic.claude-opus-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $4.40 | $22.00 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude sonnet 4 20250514 v1:0us.anthropic.claude-sonnet-4-20250514-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| us.anthropic.Claude sonnet 4 5 20250929 v1:0us.anthropic.claude-sonnet-4-5-20250929-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 200,000 tokens | 估算o200k_base |
| us.anthropic.Claude sonnet 4 6us.anthropic.claude-sonnet-4-6 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude sonnet 5us.anthropic.claude-sonnet-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| us.anthropic.Claude sonnet 5 5us.anthropic.claude-sonnet-5-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| us.DeepSeek.r1 v1:0us.deepseek.r1-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.35 | $5.40 | 128,000 tokens | 估算o200k_base |
| us.DeepSeek.v3.2us.deepseek.v3.2 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.62 | $1.85 | 163,840 tokens | 估算o200k_base |
| us.meta.llama3 1 405b instruct v1:0us.meta.llama3-1-405b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $2.40 | $2.40 | 128,000 tokens | 估算o200k_base |
| us.meta.llama3 1 70b instruct v1:0us.meta.llama3-1-70b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| us.meta.llama3 1 8b instruct v1:0us.meta.llama3-1-8b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.22 | 128,000 tokens | 估算o200k_base |
| us.meta.llama3 2 11b instruct v1:0us.meta.llama3-2-11b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.16 | $0.16 | 128,000 tokens | 估算o200k_base |
| us.meta.llama3 2 1b instruct v1:0us.meta.llama3-2-1b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 128,000 tokens | 估算o200k_base |
| us.meta.llama3 2 3b instruct v1:0us.meta.llama3-2-3b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 128,000 tokens | 估算o200k_base |
| us.meta.llama3 2 90b instruct v1:0us.meta.llama3-2-90b-instruct-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| us.meta.llama3 3 70b instruct v1:0us.meta.llama3-3-70b-instruct-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| us.meta.llama4 maverick 17b instruct v1:0us.meta.llama4-maverick-17b-instruct-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.24 | $0.97 | 1,000,000 tokens | 估算o200k_base |
| us.meta.llama4 scout 17b instruct v1:0us.meta.llama4-scout-17b-instruct-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.17 | $0.66 | 10,000,000 tokens | 估算o200k_base |
| us.Mistral.pixtral large 2502 v1:0us.mistral.pixtral-large-2502-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| us.moonshotai.kimi k3us.moonshotai.kimi-k3 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $3.30 | $16.50 | 1,000,000 tokens | 估算o200k_base |
| us.openai.GPT 5.4us.openai.gpt-5.4 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.75 | $16.50 | 1,050,000 tokens | 估算o200k_base |
| us.openai.GPT 5.5us.openai.gpt-5.5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $5.50 | $33.00 | 1,050,000 tokens | 估算o200k_base |
| us.openai.GPT 5.6 lunaus.openai.gpt-5.6-luna · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.22 | $1.32 | 1,050,000 tokens | 估算o200k_base |
| us.openai.GPT 5.6 solus.openai.gpt-5.6-sol · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $4.40 | $22.00 | 1,050,000 tokens | 估算o200k_base |
| us.openai.GPT 5.6 terraus.openai.gpt-5.6-terra · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $13.20 | 1,050,000 tokens | 估算o200k_base |
| us.openai.GPT 6 astraus.openai.gpt-6-astra · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $11.00 | $55.00 | 1,050,000 tokens | 估算o200k_base |
| us.openai.GPT 6 lunaus.openai.gpt-6-luna · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.11 | $0.55 | 1,050,000 tokens | 估算o200k_base |
| us.openai.GPT 6 solus.openai.gpt-6-sol · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,050,000 tokens | 估算o200k_base |
| us.openai.GPT 6.1 solus.openai.gpt-6.1-sol · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $11.00 | 1,000,000 tokens | 估算o200k_base |
| us.twelvelabs.pegasus 1 5 v1:0us.twelvelabs.pegasus-1-5-v1:0 · bedrock | LiteLLM ↗2026-10-25 UTC | 未验证 | $7.50 | 261,120 tokens | 估算o200k_base |
| us.writer.palmyra x4 v1:0us.writer.palmyra-x4-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| us.writer.palmyra x5 v1:0us.writer.palmyra-x5-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.60 | $6.00 | 128,000 tokens | 估算o200k_base |
| us.xai.grok 4.6us.xai.grok-4.6 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $6.60 | 500,000 tokens | 估算o200k_base |
| us.xai.grok 4.7us.xai.grok-4.7 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.20 | $6.60 | 524,288 tokens | 估算o200k_base |
| us.zai.glm 5.3us.zai.glm-5.3 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.848 | $5.808 | 1,000,000 tokens | 估算o200k_base |
| v0 1.0 mdv0/v0-1.0-md · v0 | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 128,000 tokens | 估算o200k_base |
| v0 1.5 lgv0/v0-1.5-lg · v0 | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 512,000 tokens | 估算o200k_base |
| v0 1.5 mdv0/v0-1.5-md · v0 | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 128,000 tokens | 估算o200k_base |
| Qwen 3 14bvercel_ai_gateway/alibaba/qwen-3-14b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.08 | $0.24 | 40,960 tokens | 估算o200k_base |
| Qwen 3 235bvercel_ai_gateway/alibaba/qwen-3-235b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 40,960 tokens | 估算o200k_base |
| Qwen 3 30bvercel_ai_gateway/alibaba/qwen-3-30b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 40,960 tokens | 估算o200k_base |
| Qwen 3 32bvercel_ai_gateway/alibaba/qwen-3-32b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 40,960 tokens | 估算o200k_base |
| qwen3 codervercel_ai_gateway/alibaba/qwen3-coder · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 262,144 tokens | 估算o200k_base |
| nova litevercel_ai_gateway/amazon/nova-lite · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.06 | $0.24 | 300,000 tokens | 估算o200k_base |
| nova microvercel_ai_gateway/amazon/nova-micro · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.035 | $0.14 | 128,000 tokens | 估算o200k_base |
| nova provercel_ai_gateway/amazon/nova-pro · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.80 | $3.20 | 300,000 tokens | 估算o200k_base |
| Claude 3 5 sonnetvercel_ai_gateway/anthropic/claude-3-5-sonnet · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude 3 5 sonnet 20241022vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude 3 7 sonnetvercel_ai_gateway/anthropic/claude-3-7-sonnet · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude 3 haikuvercel_ai_gateway/anthropic/claude-3-haiku · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.25 | 200,000 tokens | 估算o200k_base |
| Claude 3 opusvercel_ai_gateway/anthropic/claude-3-opus · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| Claude 3.5 haikuvercel_ai_gateway/anthropic/claude-3.5-haiku · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.80 | $4.00 | 200,000 tokens | 估算o200k_base |
| Claude 3.5 sonnetvercel_ai_gateway/anthropic/claude-3.5-sonnet · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude 3.7 sonnetvercel_ai_gateway/anthropic/claude-3.7-sonnet · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude 4 opusvercel_ai_gateway/anthropic/claude-4-opus · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| Claude 4 sonnetvercel_ai_gateway/anthropic/claude-4-sonnet · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude haiku 4.5vercel_ai_gateway/anthropic/claude-haiku-4.5 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 4vercel_ai_gateway/anthropic/claude-opus-4 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 4.1vercel_ai_gateway/anthropic/claude-opus-4.1 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 4.5vercel_ai_gateway/anthropic/claude-opus-4.5 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 4.6vercel_ai_gateway/anthropic/claude-opus-4.6 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 4vercel_ai_gateway/anthropic/claude-sonnet-4 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 4.5vercel_ai_gateway/anthropic/claude-sonnet-4.5 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,000,000 tokens | 估算o200k_base |
| command avercel_ai_gateway/cohere/command-a · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 256,000 tokens | 估算o200k_base |
| command rvercel_ai_gateway/cohere/command-r · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| command r plusvercel_ai_gateway/cohere/command-r-plus · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| DeepSeek r1vercel_ai_gateway/deepseek/deepseek-r1 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.55 | $2.19 | 128,000 tokens | 估算o200k_base |
| DeepSeek r1 distill Llama 70bvercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.75 | $0.99 | 131,072 tokens | 估算o200k_base |
| DeepSeek v3vercel_ai_gateway/deepseek/deepseek-v3 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.90 | $0.90 | 128,000 tokens | 估算o200k_base |
| Gemini 2.5 flashvercel_ai_gateway/google/gemini-2.5-flash · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| Gemini 2.5 provercel_ai_gateway/google/gemini-2.5-pro · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $1.25 | $10.00 | 1,048,576 tokens | 估算o200k_base |
| gemma 2 9bvercel_ai_gateway/google/gemma-2-9b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| mercury coder smallvercel_ai_gateway/inception/mercury-coder-small · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.00 | 32,000 tokens | 估算o200k_base |
| Llama 3 70bvercel_ai_gateway/meta/llama-3-70b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.59 | $0.79 | 8,192 tokens | 估算o200k_base |
| Llama 3 8bvercel_ai_gateway/meta/llama-3-8b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.08 | 8,192 tokens | 估算o200k_base |
| Llama 3.1 70bvercel_ai_gateway/meta/llama-3.1-70b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| Llama 3.1 8bvercel_ai_gateway/meta/llama-3.1-8b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.08 | 131,000 tokens | 估算o200k_base |
| Llama 3.2 11bvercel_ai_gateway/meta/llama-3.2-11b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.16 | $0.16 | 128,000 tokens | 估算o200k_base |
| Llama 3.2 1bvercel_ai_gateway/meta/llama-3.2-1b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 128,000 tokens | 估算o200k_base |
| Llama 3.2 3bvercel_ai_gateway/meta/llama-3.2-3b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 128,000 tokens | 估算o200k_base |
| Llama 3.2 90bvercel_ai_gateway/meta/llama-3.2-90b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| Llama 3.3 70bvercel_ai_gateway/meta/llama-3.3-70b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| Llama 4 maverickvercel_ai_gateway/meta/llama-4-maverick · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 131,072 tokens | 估算o200k_base |
| Llama 4 scoutvercel_ai_gateway/meta/llama-4-scout · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 131,072 tokens | 估算o200k_base |
| codestralvercel_ai_gateway/mistral/codestral · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.90 | 256,000 tokens | 估算o200k_base |
| devstral smallvercel_ai_gateway/mistral/devstral-small · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.28 | 128,000 tokens | 估算o200k_base |
| magistral mediumvercel_ai_gateway/mistral/magistral-medium · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $2.00 | $5.00 | 128,000 tokens | 估算o200k_base |
| magistral smallvercel_ai_gateway/mistral/magistral-small · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 128,000 tokens | 估算o200k_base |
| ministral 3bvercel_ai_gateway/mistral/ministral-3b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.04 | $0.04 | 128,000 tokens | 估算o200k_base |
| ministral 8bvercel_ai_gateway/mistral/ministral-8b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 128,000 tokens | 估算o200k_base |
| Mistral largevercel_ai_gateway/mistral/mistral-large · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 32,000 tokens | 估算o200k_base |
| Mistral saba 24bvercel_ai_gateway/mistral/mistral-saba-24b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.79 | $0.79 | 32,768 tokens | 估算o200k_base |
| Mistral smallvercel_ai_gateway/mistral/mistral-small · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 32,000 tokens | 估算o200k_base |
| mixtral 8x22b instructvercel_ai_gateway/mistral/mixtral-8x22b-instruct · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $1.20 | $1.20 | 65,536 tokens | 估算o200k_base |
| pixtral 12bvercel_ai_gateway/mistral/pixtral-12b · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 128,000 tokens | 估算o200k_base |
| pixtral largevercel_ai_gateway/mistral/pixtral-large · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| kimi k2vercel_ai_gateway/moonshotai/kimi-k2 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.55 | $2.20 | 131,072 tokens | 估算o200k_base |
| morph v3 fastvercel_ai_gateway/morph/morph-v3-fast · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.80 | $1.20 | 32,768 tokens | 估算o200k_base |
| morph v3 largevercel_ai_gateway/morph/morph-v3-large · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.90 | $1.90 | 32,768 tokens | 估算o200k_base |
| GPT 3.5 turbovercel_ai_gateway/openai/gpt-3.5-turbo · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.50 | $1.50 | 16,385 tokens | 估算o200k_base |
| GPT 3.5 turbo instructvercel_ai_gateway/openai/gpt-3.5-turbo-instruct · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $1.50 | $2.00 | 8,192 tokens | 估算o200k_base |
| GPT 4 turbovercel_ai_gateway/openai/gpt-4-turbo · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $10.00 | $30.00 | 128,000 tokens | 估算o200k_base |
| GPT 4.1vercel_ai_gateway/openai/gpt-4.1 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 1,047,576 tokens | 估算o200k_base |
| GPT 4.1 minivercel_ai_gateway/openai/gpt-4.1-mini · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.40 | $1.60 | 1,047,576 tokens | 估算o200k_base |
| GPT 4.1 nanovercel_ai_gateway/openai/gpt-4.1-nano · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.40 | 1,047,576 tokens | 估算o200k_base |
| GPT 4overcel_ai_gateway/openai/gpt-4o · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| GPT 4o minivercel_ai_gateway/openai/gpt-4o-mini · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 128,000 tokens | 估算o200k_base |
| o1vercel_ai_gateway/openai/o1 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $15.00 | $60.00 | 200,000 tokens | 估算o200k_base |
| o3vercel_ai_gateway/openai/o3 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 200,000 tokens | 估算o200k_base |
| o3 minivercel_ai_gateway/openai/o3-mini · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 200,000 tokens | 估算o200k_base |
| o4 minivercel_ai_gateway/openai/o4-mini · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.40 | 200,000 tokens | 估算o200k_base |
| sonarvercel_ai_gateway/perplexity/sonar · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $1.00 | $1.00 | 127,000 tokens | 估算o200k_base |
| sonar provercel_ai_gateway/perplexity/sonar-pro · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| sonar reasoningvercel_ai_gateway/perplexity/sonar-reasoning · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 127,000 tokens | 估算o200k_base |
| sonar reasoning provercel_ai_gateway/perplexity/sonar-reasoning-pro · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 127,000 tokens | 估算o200k_base |
| v0 1.0 mdvercel_ai_gateway/vercel/v0-1.0-md · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 128,000 tokens | 估算o200k_base |
| v0 1.5 mdvercel_ai_gateway/vercel/v0-1.5-md · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 128,000 tokens | 估算o200k_base |
| grok 2vercel_ai_gateway/xai/grok-2 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 131,072 tokens | 估算o200k_base |
| grok 2 visionvercel_ai_gateway/xai/grok-2-vision · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 32,768 tokens | 估算o200k_base |
| grok 3vercel_ai_gateway/xai/grok-3 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 131,072 tokens | 估算o200k_base |
| grok 3 fastvercel_ai_gateway/xai/grok-3-fast · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 131,072 tokens | 估算o200k_base |
| grok 3 minivercel_ai_gateway/xai/grok-3-mini · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.50 | 131,072 tokens | 估算o200k_base |
| grok 3 mini fastvercel_ai_gateway/xai/grok-3-mini-fast · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.60 | $4.00 | 131,072 tokens | 估算o200k_base |
| grok 4vercel_ai_gateway/xai/grok-4 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 256,000 tokens | 估算o200k_base |
| glm 4.5vercel_ai_gateway/zai/glm-4.5 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 131,072 tokens | 估算o200k_base |
| glm 4.5 airvercel_ai_gateway/zai/glm-4.5-air · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.10 | 128,000 tokens | 估算o200k_base |
| glm 4.6vercel_ai_gateway/zai/glm-4.6 · vercel_ai_gateway | LiteLLM ↗2026-10-25 UTC | $0.45 | $1.80 | 200,000 tokens | 估算o200k_base |
| Claude 3 5 haikuvertex_ai/claude-3-5-haiku · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| Claude 3 5 haiku@20241022vertex_ai/claude-3-5-haiku@20241022 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| Claude 3 5 sonnetvertex_ai/claude-3-5-sonnet · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude 3 5 sonnet@20240620vertex_ai/claude-3-5-sonnet@20240620 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude 3 haikuvertex_ai/claude-3-haiku · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.25 | 200,000 tokens | 估算o200k_base |
| Claude 3 haiku@20240307vertex_ai/claude-3-haiku@20240307 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.25 | 200,000 tokens | 估算o200k_base |
| Claude 3 opusvertex_ai/claude-3-opus · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| Claude 3 opus@20240229vertex_ai/claude-3-opus@20240229 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $15.00 | $75.00 | 200,000 tokens | 估算o200k_base |
| Claude 3 sonnetvertex_ai/claude-3-sonnet · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude 3 sonnet@20240229vertex_ai/claude-3-sonnet@20240229 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude fable 5vertex_ai/claude-fable-5 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude fable 5 1vertex_ai/claude-fable-5-1 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude fable 5 1@defaultvertex_ai/claude-fable-5-1@default · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude fable 5@defaultvertex_ai/claude-fable-5@default · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $10.00 | $50.00 | 1,000,000 tokens | 估算o200k_base |
| Claude haiku 4 5vertex_ai/claude-haiku-4-5 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| Claude haiku 4 5@20251001vertex_ai/claude-haiku-4-5@20251001 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 200,000 tokens | 估算o200k_base |
| Claude haiku 5 5vertex_ai/claude-haiku-5-5 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 1,000,000 tokens | 估算o200k_base |
| Claude haiku 5 5@defaultvertex_ai/claude-haiku-5-5@default · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.50 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 5vertex_ai/claude-opus-4-5 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 4 5@20251101vertex_ai/claude-opus-4-5@20251101 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 200,000 tokens | 估算o200k_base |
| Claude opus 4 6vertex_ai/claude-opus-4-6 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 6@defaultvertex_ai/claude-opus-4-6@default · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 7vertex_ai/claude-opus-4-7 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 7@defaultvertex_ai/claude-opus-4-7@default · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 8vertex_ai/claude-opus-4-8 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 4 8@defaultvertex_ai/claude-opus-4-8@default · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5vertex_ai/claude-opus-5 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5 5vertex_ai/claude-opus-5-5 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5 5@defaultvertex_ai/claude-opus-5-5@default · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 1,000,000 tokens | 估算o200k_base |
| Claude opus 5@defaultvertex_ai/claude-opus-5@default · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $5.00 | $25.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 4 5vertex_ai/claude-sonnet-4-5 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 4 5@20250929vertex_ai/claude-sonnet-4-5@20250929 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 200,000 tokens | 估算o200k_base |
| Claude sonnet 4 6vertex_ai/claude-sonnet-4-6 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 4 6@defaultvertex_ai/claude-sonnet-4-6@default · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $3.00 | $15.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 5vertex_ai/claude-sonnet-5 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 5 5vertex_ai/claude-sonnet-5-5 · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 5 5@defaultvertex_ai/claude-sonnet-5-5@default · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| Claude sonnet 5@defaultvertex_ai/claude-sonnet-5@default · vertex_ai-anthropic_models | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,000,000 tokens | 估算o200k_base |
| codestral 2vertex_ai/codestral-2 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.90 | 128,000 tokens | 估算o200k_base |
| codestral 2@001vertex_ai/codestral-2@001 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.90 | 128,000 tokens | 估算o200k_base |
| codestral 2501vertex_ai/codestral-2501 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 128,000 tokens | 估算o200k_base |
| codestral@2405vertex_ai/codestral@2405 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 128,000 tokens | 估算o200k_base |
| codestral@latestvertex_ai/codestral@latest · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.60 | 128,000 tokens | 估算o200k_base |
| deep research pro preview 12 2025vertex_ai/deep-research-pro-preview-12-2025 · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 65,536 tokens | 估算o200k_base |
| DeepSeek r1 0528 maasvertex_ai/deepseek-ai/deepseek-r1-0528-maas · vertex_ai-deepseek_models | LiteLLM ↗2026-10-25 UTC | $1.35 | $5.40 | 65,336 tokens | 估算o200k_base |
| DeepSeek v3.1 maasvertex_ai/deepseek-ai/deepseek-v3.1-maas · vertex_ai-deepseek_models | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.70 | 163,840 tokens | 估算o200k_base |
| DeepSeek v3.2 maasvertex_ai/deepseek-ai/deepseek-v3.2-maas · vertex_ai-deepseek_models | LiteLLM ↗2026-10-25 UTC | $0.56 | $1.68 | 163,840 tokens | 估算o200k_base |
| DeepSeek v4.1 flash maasvertex_ai/deepseek-ai/deepseek-v4.1-flash-maas · vertex_ai-deepseek_models | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3 flash previewvertex_ai/gemini-3-flash-preview · vertex_ai | LiteLLM ↗2026-10-25 UTC | $0.50 | $3.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3 pro previewvertex_ai/gemini-3-pro-preview · vertex_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 flash litevertex_ai/gemini-3.1-flash-lite · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 flash lite previewvertex_ai/gemini-3.1-flash-lite-preview · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 pro previewvertex_ai/gemini-3.1-pro-preview · vertex_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.1 pro preview customtoolsvertex_ai/gemini-3.1-pro-preview-customtools · vertex_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $12.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.5 flashvertex_ai/gemini-3.5-flash · vertex_ai | LiteLLM ↗2026-10-25 UTC | $1.50 | $9.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.5 flash litevertex_ai/gemini-3.5-flash-lite · vertex_ai-language-models | LiteLLM ↗2026-10-25 UTC | $0.30 | $2.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.6 flashvertex_ai/gemini-3.6-flash · vertex_ai | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.7 flashvertex_ai/gemini-3.7-flash · vertex_ai | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.8 flashvertex_ai/gemini-3.8-flash · vertex_ai | LiteLLM ↗2026-10-25 UTC | $0.75 | $3.75 | 1,048,576 tokens | 估算o200k_base |
| Gemini 3.8 flash cybervertex_ai/gemini-3.8-flash-cyber · vertex_ai | LiteLLM ↗2026-10-25 UTC | $1.50 | $7.50 | 1,048,576 tokens | 估算o200k_base |
| Gemini 4 argonvertex_ai/gemini-4-argon · vertex_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $10.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini 4 argon cyber permissivevertex_ai/gemini-4-argon-cyber-permissive · vertex_ai | LiteLLM ↗2026-10-25 UTC | $4.00 | $20.00 | 1,048,576 tokens | 估算o200k_base |
| Gemini omni 1.1 flash previewvertex_ai/gemini-omni-1.1-flash-preview · vertex_ai | LiteLLM ↗2026-10-25 UTC | $1.50 | $9.00 | 57,920 tokens | 估算o200k_base |
| Gemini robotics er 2 previewvertex_ai/gemini-robotics-er-2-preview · vertex_ai | LiteLLM ↗2026-10-25 UTC | $1.00 | $5.00 | 131,072 tokens | 估算o200k_base |
| gemma 4 26b a4b it maasvertex_ai/google/gemma-4-26b-a4b-it-maas · vertex_ai-openai_models | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 262,144 tokens | 估算o200k_base |
| jamba 1.5vertex_ai/jamba-1.5 · vertex_ai-ai21_models | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 256,000 tokens | 估算o200k_base |
| jamba 1.5 largevertex_ai/jamba-1.5-large · vertex_ai-ai21_models | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 256,000 tokens | 估算o200k_base |
| jamba 1.5 large@001vertex_ai/jamba-1.5-large@001 · vertex_ai-ai21_models | LiteLLM ↗2026-10-25 UTC | $2.00 | $8.00 | 256,000 tokens | 估算o200k_base |
| jamba 1.5 minivertex_ai/jamba-1.5-mini · vertex_ai-ai21_models | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 256,000 tokens | 估算o200k_base |
| jamba 1.5 mini@001vertex_ai/jamba-1.5-mini@001 · vertex_ai-ai21_models | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.40 | 256,000 tokens | 估算o200k_base |
| Llama 3.1 405b instruct maasvertex_ai/meta/llama-3.1-405b-instruct-maas · vertex_ai-llama_models | LiteLLM ↗2026-10-25 UTC | $5.00 | $16.00 | 128,000 tokens | 估算o200k_base |
| Llama 3.1 70b instruct maasvertex_ai/meta/llama-3.1-70b-instruct-maas · vertex_ai-llama_models | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 128,000 tokens | 估算o200k_base |
| Llama 3.1 8b instruct maasvertex_ai/meta/llama-3.1-8b-instruct-maas · vertex_ai-llama_models | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 128,000 tokens | 估算o200k_base |
| Llama 3.2 90b vision instruct maasvertex_ai/meta/llama-3.2-90b-vision-instruct-maas · vertex_ai-llama_models | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 128,000 tokens | 估算o200k_base |
| Llama 3.3 70b instruct maasvertex_ai/meta/llama-3.3-70b-instruct-maas · vertex_ai-llama_models | LiteLLM ↗2026-10-25 UTC | $0.72 | $0.72 | 128,000 tokens | 估算o200k_base |
| Llama 4 maverick 17b 128e instruct maasvertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas · vertex_ai-llama_models | LiteLLM ↗2026-10-25 UTC | $0.35 | $1.15 | 1,000,000 tokens | 估算o200k_base |
| Llama 4 maverick 17b 16e instruct maasvertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas · vertex_ai-llama_models | LiteLLM ↗2026-10-25 UTC | $0.35 | $1.15 | 1,000,000 tokens | 估算o200k_base |
| Llama 4 scout 17b 128e instruct maasvertex_ai/meta/llama-4-scout-17b-128e-instruct-maas · vertex_ai-llama_models | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.70 | 10,000,000 tokens | 估算o200k_base |
| Llama 4 scout 17b 16e instruct maasvertex_ai/meta/llama-4-scout-17b-16e-instruct-maas · vertex_ai-llama_models | LiteLLM ↗2026-10-25 UTC | $0.25 | $0.70 | 10,000,000 tokens | 估算o200k_base |
| llama3 405b instruct maasvertex_ai/meta/llama3-405b-instruct-maas · vertex_ai-llama_models | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,000 tokens | 估算o200k_base |
| llama3 70b instruct maasvertex_ai/meta/llama3-70b-instruct-maas · vertex_ai-llama_models | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,000 tokens | 估算o200k_base |
| llama3 8b instruct maasvertex_ai/meta/llama3-8b-instruct-maas · vertex_ai-llama_models | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 32,000 tokens | 估算o200k_base |
| minimax m2 maasvertex_ai/minimaxai/minimax-m2-maas · vertex_ai-minimax_models | LiteLLM ↗2026-10-25 UTC | $0.30 | $1.20 | 196,608 tokens | 估算o200k_base |
| Mistral large 2411vertex_ai/mistral-large-2411 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| Mistral large@2407vertex_ai/mistral-large@2407 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| Mistral large@2411 001vertex_ai/mistral-large@2411-001 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| Mistral large@latestvertex_ai/mistral-large@latest · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 128,000 tokens | 估算o200k_base |
| Mistral medium 3vertex_ai/mistral-medium-3 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.40 | $2.00 | 128,000 tokens | 估算o200k_base |
| Mistral medium 3@001vertex_ai/mistral-medium-3@001 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.40 | $2.00 | 128,000 tokens | 估算o200k_base |
| Mistral nemo@2407vertex_ai/mistral-nemo@2407 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $3.00 | $3.00 | 128,000 tokens | 估算o200k_base |
| Mistral nemo@latestvertex_ai/mistral-nemo@latest · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 128,000 tokens | 估算o200k_base |
| Mistral small 2503vertex_ai/mistral-small-2503 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 128,000 tokens | 估算o200k_base |
| Mistral small 2503@001vertex_ai/mistral-small-2503@001 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 32,000 tokens | 估算o200k_base |
| codestral 2vertex_ai/mistralai/codestral-2 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.90 | 128,000 tokens | 估算o200k_base |
| codestral 2@001vertex_ai/mistralai/codestral-2@001 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.30 | $0.90 | 128,000 tokens | 估算o200k_base |
| Mistral medium 3vertex_ai/mistralai/mistral-medium-3 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.40 | $2.00 | 128,000 tokens | 估算o200k_base |
| Mistral medium 3@001vertex_ai/mistralai/mistral-medium-3@001 · vertex_ai-mistral_models | LiteLLM ↗2026-10-25 UTC | $0.40 | $2.00 | 128,000 tokens | 估算o200k_base |
| kimi k2 thinking maasvertex_ai/moonshotai/kimi-k2-thinking-maas · vertex_ai-moonshot_models | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.50 | 256,000 tokens | 估算o200k_base |
| GPT oss 120b maasvertex_ai/openai/gpt-oss-120b-maas · vertex_ai-openai_models | LiteLLM ↗2026-10-25 UTC | $0.09 | $0.36 | 131,072 tokens | 估算o200k_base |
| GPT oss 20b maasvertex_ai/openai/gpt-oss-20b-maas · vertex_ai-openai_models | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.25 | 131,072 tokens | 估算o200k_base |
| qwen3 235b a22b instruct 2507 maasvertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas · vertex_ai-qwen_models | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.88 | 262,144 tokens | 估算o200k_base |
| qwen3 coder 480b a35b instruct maasvertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas · vertex_ai-qwen_models | LiteLLM ↗2026-10-25 UTC | $0.22 | $1.80 | 262,144 tokens | 估算o200k_base |
| qwen3 next 80b a3b instruct maasvertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas · vertex_ai-qwen_models | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.20 | 262,144 tokens | 估算o200k_base |
| qwen3 next 80b a3b thinking maasvertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas · vertex_ai-qwen_models | LiteLLM ↗2026-10-25 UTC | $0.15 | $1.20 | 262,144 tokens | 估算o200k_base |
| grok 4.1 fast non reasoningvertex_ai/xai/grok-4.1-fast-non-reasoning · vertex_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.50 | 128,000 tokens | 估算o200k_base |
| grok 4.1 fast reasoningvertex_ai/xai/grok-4.1-fast-reasoning · vertex_ai | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.50 | 128,000 tokens | 估算o200k_base |
| grok 4.20 non reasoningvertex_ai/xai/grok-4.20-non-reasoning · vertex_ai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 2,000,000 tokens | 估算o200k_base |
| grok 4.20 reasoningvertex_ai/xai/grok-4.20-reasoning · vertex_ai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 2,000,000 tokens | 估算o200k_base |
| grok 4.3vertex_ai/xai/grok-4.3 · vertex_ai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 200,000 tokens | 估算o200k_base |
| grok 4.6vertex_ai/xai/grok-4.6 · vertex_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 524,288 tokens | 估算o200k_base |
| grok 4.7vertex_ai/xai/grok-4.7 · vertex_ai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 524,288 tokens | 估算o200k_base |
| glm 4.7 maasvertex_ai/zai-org/glm-4.7-maas · vertex_ai-zai_models | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 200,000 tokens | 估算o200k_base |
| glm 5 maasvertex_ai/zai-org/glm-5-maas · vertex_ai-zai_models | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.20 | 200,000 tokens | 估算o200k_base |
| glm 5.2 maasvertex_ai/zai-org/glm-5.2-maas · vertex_ai-zai_models | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,000,000 tokens | 估算o200k_base |
| doubao seed 2 0 code preview 260215volcengine/doubao-seed-2-0-code-preview-260215 · volcengine | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 256,000 tokens | 估算o200k_base |
| doubao seed 2 0 lite 260215volcengine/doubao-seed-2-0-lite-260215 · volcengine | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 256,000 tokens | 估算o200k_base |
| doubao seed 2 0 mini 260215volcengine/doubao-seed-2-0-mini-260215 · volcengine | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 256,000 tokens | 估算o200k_base |
| doubao seed 2 0 pro 260215volcengine/doubao-seed-2-0-pro-260215 · volcengine | LiteLLM ↗2026-10-25 UTC | 未验证 | 未验证 | 256,000 tokens | 估算o200k_base |
| doubao seed 2 1 lite 260915volcengine/doubao-seed-2-1-lite-260915 · volcengine | LiteLLM ↗2026-10-25 UTC | $0.115 | $0.388126 | 1,024,000 tokens | 估算o200k_base |
| doubao seed 2 1 pro 260628volcengine/doubao-seed-2-1-pro-260628 · volcengine | LiteLLM ↗2026-10-25 UTC | $0.8625 | $4.3125 | 256,000 tokens | 估算o200k_base |
| doubao seed 2 1 pro 260915volcengine/doubao-seed-2-1-pro-260915 · volcengine | LiteLLM ↗2026-10-25 UTC | $0.8625 | $4.3125 | 1,024,000 tokens | 估算o200k_base |
| doubao seed 2 1 turbo 260628volcengine/doubao-seed-2-1-turbo-260628 · volcengine | LiteLLM ↗2026-10-25 UTC | $0.43125 | $2.15625 | 256,000 tokens | 估算o200k_base |
| DeepSeek V3.1wandb/deepseek-ai/DeepSeek-V3.1 · wandb | LiteLLM ↗2026-10-25 UTC | $0.55 | $1.65 | 161,000 tokens | 估算o200k_base |
| DeepSeek V4 Flashwandb/deepseek-ai/DeepSeek-V4-Flash · wandb | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 1,049,000 tokens | 估算o200k_base |
| DeepSeek V4 Flash 0731wandb/deepseek-ai/DeepSeek-V4-Flash-0731 · wandb | LiteLLM ↗2026-10-25 UTC | $0.13 | $0.28 | 262,000 tokens | 估算o200k_base |
| DeepSeek V4 Prowandb/deepseek-ai/DeepSeek-V4-Pro · wandb | LiteLLM ↗2026-10-25 UTC | $1.15 | $2.55 | 1,049,000 tokens | 估算o200k_base |
| DeepSeek V4 Pro 0813wandb/deepseek-ai/DeepSeek-V4-Pro-0813 · wandb | LiteLLM ↗2026-10-25 UTC | $1.31 | $3.96 | 1,049,000 tokens | 估算o200k_base |
| DeepSeek V4.1 Flashwandb/deepseek-ai/DeepSeek-V4.1-Flash · wandb | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.65 | 1,049,000 tokens | 估算o200k_base |
| gemma 4 26B A4B itwandb/google/gemma-4-26B-A4B-it · wandb | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 262,000 tokens | 估算o200k_base |
| gemma 4 31B itwandb/google/gemma-4-31B-it · wandb | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.34 | 262,000 tokens | 估算o200k_base |
| granite 4.1 8bwandb/ibm-granite/granite-4.1-8b · wandb | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.10 | 131,000 tokens | 估算o200k_base |
| granite 4.2 8bwandb/ibm-granite/granite-4.2-8b · wandb | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.15 | 131,000 tokens | 估算o200k_base |
| Mellum2 12B A2.5B Instructwandb/JetBrains/Mellum2-12B-A2.5B-Instruct · wandb | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.10 | 131,000 tokens | 估算o200k_base |
| Llama 3.1 70B Instructwandb/meta-llama/Llama-3.1-70B-Instruct · wandb | LiteLLM ↗2026-10-25 UTC | $0.80 | $0.80 | 131,000 tokens | 估算o200k_base |
| Llama 3.1 8B Instructwandb/meta-llama/Llama-3.1-8B-Instruct · wandb | LiteLLM ↗2026-10-25 UTC | $0.22 | $0.22 | 131,000 tokens | 估算o200k_base |
| Llama 3.3 70B Instructwandb/meta-llama/Llama-3.3-70B-Instruct · wandb | LiteLLM ↗2026-10-25 UTC | $0.71 | $0.71 | 128,000 tokens | 估算o200k_base |
| MiniMax M3wandb/MiniMaxAI/MiniMax-M3 · wandb | LiteLLM ↗2026-10-25 UTC | $0.23 | $0.96 | 262,000 tokens | 估算o200k_base |
| Kimi K2.5wandb/moonshotai/Kimi-K2.5 · wandb | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.00 | 262,144 tokens | 估算o200k_base |
| Kimi K2.6wandb/moonshotai/Kimi-K2.6 · wandb | LiteLLM ↗2026-10-25 UTC | $0.65 | $3.41 | 262,000 tokens | 估算o200k_base |
| Kimi K2.7 Codewandb/moonshotai/Kimi-K2.7-Code · wandb | LiteLLM ↗2026-10-25 UTC | $0.71 | $3.50 | 262,000 tokens | 估算o200k_base |
| NVIDIA Nemotron 3 Ultra 550B A55Bwandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B · wandb | LiteLLM ↗2026-10-25 UTC | $0.50 | $2.15 | 262,000 tokens | 估算o200k_base |
| NVIDIA Nemotron 3.5 Lightning 30B A3Bwandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B · wandb | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.20 | 262,000 tokens | 估算o200k_base |
| NVIDIA Nemotron 3.5 Super VL 120B A12Bwandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B · wandb | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.75 | 1,049,000 tokens | 估算o200k_base |
| GPT oss 120bwandb/openai/gpt-oss-120b · wandb | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.17 | 131,000 tokens | 估算o200k_base |
| GPT oss 20bwandb/openai/gpt-oss-20b · wandb | LiteLLM ↗2026-10-25 UTC | $0.03 | $0.13 | 131,000 tokens | 估算o200k_base |
| Qwen3 14B Instructwandb/OpenPipe/Qwen3-14B-Instruct · wandb | LiteLLM ↗2026-10-25 UTC | $0.05 | $0.22 | 32,800 tokens | 估算o200k_base |
| Qwen3 30B A3B Instruct 2507wandb/Qwen/Qwen3-30B-A3B-Instruct-2507 · wandb | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 262,000 tokens | 估算o200k_base |
| Qwen3.5 35B A3Bwandb/Qwen/Qwen3.5-35B-A3B · wandb | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.25 | 262,000 tokens | 估算o200k_base |
| Qwen3.6 27Bwandb/Qwen/Qwen3.6-27B · wandb | LiteLLM ↗2026-10-25 UTC | $0.60 | $3.60 | 262,000 tokens | 估算o200k_base |
| Qwen3.6 35B A3Bwandb/Qwen/Qwen3.6-35B-A3B · wandb | LiteLLM ↗2026-10-25 UTC | $0.25 | $1.25 | 262,000 tokens | 估算o200k_base |
| Qwen3.8 27Bwandb/Qwen/Qwen3.8-27B · wandb | LiteLLM ↗2026-10-25 UTC | $0.40 | $3.00 | 262,000 tokens | 估算o200k_base |
| Beam 1.0 501B A23Bwandb/reflection/Beam-1.0-501B-A23B · wandb | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.00 | 1,049,000 tokens | 估算o200k_base |
| GLM 5.2wandb/zai-org/GLM-5.2 · wandb | LiteLLM ↗2026-10-25 UTC | $0.76 | $2.42 | 1,049,000 tokens | 估算o200k_base |
| GLM 5.3wandb/zai-org/GLM-5.3 · wandb | LiteLLM ↗2026-10-25 UTC | $1.20 | $4.00 | 1,049,000 tokens | 估算o200k_base |
| GLM 5.3 Flashwandb/zai-org/GLM-5.3-Flash · wandb | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,049,000 tokens | 估算o200k_base |
| mt0 xxlwatsonx/bigscience/mt0-xxl · watsonx | LiteLLM ↗2026-10-25 UTC | $1.908 | $1.908 | 4,096 tokens | 估算o200k_base |
| mt0 xxl 13bwatsonx/bigscience/mt0-xxl-13b · watsonx | LiteLLM ↗2026-10-25 UTC | $1.908 | $1.908 | 4,096 tokens | 估算o200k_base |
| jais 13b chatwatsonx/core42/jais-13b-chat · watsonx | LiteLLM ↗2026-10-25 UTC | $500.00 | $2,000.00 | 8,192 tokens | 估算o200k_base |
| flan t5 xl 3bwatsonx/google/flan-t5-xl-3b · watsonx | LiteLLM ↗2026-10-25 UTC | $0.60 | $0.60 | 8,192 tokens | 估算o200k_base |
| granite 13b chat v2watsonx/ibm/granite-13b-chat-v2 · watsonx | LiteLLM ↗2026-10-25 UTC | $0.60 | $0.60 | 8,192 tokens | 估算o200k_base |
| granite 13b instruct v2watsonx/ibm/granite-13b-instruct-v2 · watsonx | LiteLLM ↗2026-10-25 UTC | $0.60 | $0.60 | 8,192 tokens | 估算o200k_base |
| granite 3 3 8b instructwatsonx/ibm/granite-3-3-8b-instruct · watsonx | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| granite 3 8b instructwatsonx/ibm/granite-3-8b-instruct · watsonx | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| granite 4 h smallwatsonx/ibm/granite-4-h-small · watsonx | LiteLLM ↗2026-10-25 UTC | $0.0636 | $0.265 | 131,072 tokens | 估算o200k_base |
| granite guardian 3 2 2bwatsonx/ibm/granite-guardian-3-2-2b · watsonx | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 8,192 tokens | 估算o200k_base |
| granite guardian 3 3 8bwatsonx/ibm/granite-guardian-3-3-8b · watsonx | LiteLLM ↗2026-10-25 UTC | $0.20 | $0.20 | 8,192 tokens | 估算o200k_base |
| granite ttm 1024 96 r2watsonx/ibm/granite-ttm-1024-96-r2 · watsonx | LiteLLM ↗2026-10-25 UTC | $0.38 | $0.38 | 512 tokens | 估算o200k_base |
| granite ttm 1536 96 r2watsonx/ibm/granite-ttm-1536-96-r2 · watsonx | LiteLLM ↗2026-10-25 UTC | $0.38 | $0.38 | 512 tokens | 估算o200k_base |
| granite ttm 512 96 r2watsonx/ibm/granite-ttm-512-96-r2 · watsonx | LiteLLM ↗2026-10-25 UTC | $0.38 | $0.38 | 512 tokens | 估算o200k_base |
| granite vision 3 2 2bwatsonx/ibm/granite-vision-3-2-2b · watsonx | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 8,192 tokens | 估算o200k_base |
| Llama 3 2 11b vision instructwatsonx/meta-llama/llama-3-2-11b-vision-instruct · watsonx | LiteLLM ↗2026-10-25 UTC | $0.35 | $0.35 | 128,000 tokens | 估算o200k_base |
| Llama 3 2 1b instructwatsonx/meta-llama/llama-3-2-1b-instruct · watsonx | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 128,000 tokens | 估算o200k_base |
| Llama 3 2 3b instructwatsonx/meta-llama/llama-3-2-3b-instruct · watsonx | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.15 | 128,000 tokens | 估算o200k_base |
| Llama 3 2 90b vision instructwatsonx/meta-llama/llama-3-2-90b-vision-instruct · watsonx | LiteLLM ↗2026-10-25 UTC | $2.00 | $2.00 | 128,000 tokens | 估算o200k_base |
| Llama 3 3 70b instructwatsonx/meta-llama/llama-3-3-70b-instruct · watsonx | LiteLLM ↗2026-10-25 UTC | $0.7526 | $0.7526 | 131,072 tokens | 估算o200k_base |
| Llama 4 maverick 17bwatsonx/meta-llama/llama-4-maverick-17b · watsonx | LiteLLM ↗2026-10-25 UTC | $0.371 | $1.484 | 131,072 tokens | 估算o200k_base |
| Llama 4 maverick 17b 128e instruct fp8watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8 · watsonx | LiteLLM ↗2026-10-25 UTC | $0.371 | $1.484 | 131,072 tokens | 估算o200k_base |
| Llama guard 3 11b visionwatsonx/meta-llama/llama-guard-3-11b-vision · watsonx | LiteLLM ↗2026-10-25 UTC | $0.35 | $0.35 | 128,000 tokens | 估算o200k_base |
| Mistral largewatsonx/mistralai/mistral-large · watsonx | LiteLLM ↗2026-10-25 UTC | $3.00 | $10.00 | 131,072 tokens | 估算o200k_base |
| Mistral medium 2505watsonx/mistralai/mistral-medium-2505 · watsonx | LiteLLM ↗2026-10-25 UTC | $3.00 | $10.00 | 128,000 tokens | 估算o200k_base |
| Mistral small 2503watsonx/mistralai/mistral-small-2503 · watsonx | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.30 | 32,000 tokens | 估算o200k_base |
| Mistral small 3 1 24b instruct 2503watsonx/mistralai/mistral-small-3-1-24b-instruct-2503 · watsonx | LiteLLM ↗2026-10-25 UTC | $0.106 | $0.318 | 131,072 tokens | 估算o200k_base |
| pixtral 12b 2409watsonx/mistralai/pixtral-12b-2409 · watsonx | LiteLLM ↗2026-10-25 UTC | $0.35 | $0.35 | 128,000 tokens | 估算o200k_base |
| GPT oss 120bwatsonx/openai/gpt-oss-120b · watsonx | LiteLLM ↗2026-10-25 UTC | $0.159 | $0.636 | 131,072 tokens | 估算o200k_base |
| allam 1 13b instructwatsonx/sdaia/allam-1-13b-instruct · watsonx | LiteLLM ↗2026-10-25 UTC | $1.80 | $1.80 | 8,192 tokens | 估算o200k_base |
| writer.palmyra vision 7bwriter.palmyra-vision-7b · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.60 | 4,096 tokens | 估算o200k_base |
| writer.palmyra x4 v1:0writer.palmyra-x4-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $2.50 | $10.00 | 128,000 tokens | 估算o200k_base |
| writer.palmyra x5 v1:0writer.palmyra-x5-v1:0 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.60 | $6.00 | 128,000 tokens | 估算o200k_base |
| grok 4.20xai/grok-4.20 · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 0309xai/grok-4.20-0309 · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 0309 non reasoningxai/grok-4.20-0309-non-reasoning · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 0309 reasoningxai/grok-4.20-0309-reasoning · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 betaxai/grok-4.20-beta · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 beta 0309xai/grok-4.20-beta-0309 · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 beta 0309 non reasoningxai/grok-4.20-beta-0309-non-reasoning · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 beta 0309 reasoningxai/grok-4.20-beta-0309-reasoning · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 beta latestxai/grok-4.20-beta-latest · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 beta latest non reasoningxai/grok-4.20-beta-latest-non-reasoning · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 beta latest reasoningxai/grok-4.20-beta-latest-reasoning · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 beta non reasoningxai/grok-4.20-beta-non-reasoning · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 beta reasoningxai/grok-4.20-beta-reasoning · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 experimental beta 0304xai/grok-4.20-experimental-beta-0304 · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 experimental beta 0304 non reasoningxai/grok-4.20-experimental-beta-0304-non-reasoning · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 experimental beta 0304 reasoningxai/grok-4.20-experimental-beta-0304-reasoning · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 experimental beta latestxai/grok-4.20-experimental-beta-latest · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 experimental beta non reasoning latestxai/grok-4.20-experimental-beta-non-reasoning-latest · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 experimental beta reasoning latestxai/grok-4.20-experimental-beta-reasoning-latest · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 non reasoningxai/grok-4.20-non-reasoning · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 non reasoning gv2xai/grok-4.20-non-reasoning-gv2 · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 non reasoning latestxai/grok-4.20-non-reasoning-latest · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 reasoningxai/grok-4.20-reasoning · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 reasoning gv2xai/grok-4.20-reasoning-gv2 · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.20 reasoning latestxai/grok-4.20-reasoning-latest · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.3xai/grok-4.3 · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.3 latestxai/grok-4.3-latest · xai | LiteLLM ↗2026-10-25 UTC | $1.25 | $2.50 | 1,000,000 tokens | 估算o200k_base |
| grok 4.5xai/grok-4.5 · xai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 500,000 tokens | 估算o200k_base |
| grok 4.5 latestxai/grok-4.5-latest · xai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 500,000 tokens | 估算o200k_base |
| grok 4.6xai/grok-4.6 · xai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 500,000 tokens | 估算o200k_base |
| grok 4.7xai/grok-4.7 · xai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 500,000 tokens | 估算o200k_base |
| grok build 0.1xai/grok-build-0.1 · xai | LiteLLM ↗2026-10-25 UTC | $1.00 | $2.00 | 256,000 tokens | 估算o200k_base |
| grok build latestxai/grok-build-latest · xai | LiteLLM ↗2026-10-25 UTC | $2.00 | $6.00 | 500,000 tokens | 估算o200k_base |
| grok code fastxai/grok-code-fast · xai | LiteLLM ↗2026-10-25 UTC | $1.00 | $2.00 | 256,000 tokens | 估算o200k_base |
| grok code fast 1xai/grok-code-fast-1 · xai | LiteLLM ↗2026-10-25 UTC | $1.00 | $2.00 | 256,000 tokens | 估算o200k_base |
| grok code fast 1 0825xai/grok-code-fast-1-0825 · xai | LiteLLM ↗2026-10-25 UTC | $1.00 | $2.00 | 256,000 tokens | 估算o200k_base |
| mimo v2.6 flashxiaomi_mimo/mimo-v2.6-flash · xiaomi_mimo | LiteLLM ↗2026-10-25 UTC | $0.14 | $0.28 | 1,048,576 tokens | 估算o200k_base |
| mimo v2.6 proxiaomi_mimo/mimo-v2.6-pro · xiaomi_mimo | LiteLLM ↗2026-10-25 UTC | $0.435 | $0.87 | 1,048,576 tokens | 估算o200k_base |
| zai.glm 4.7zai.glm-4.7 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 203,000 tokens | 估算o200k_base |
| zai.glm 4.7 flashzai.glm-4.7-flash · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $0.07 | $0.40 | 203,000 tokens | 估算o200k_base |
| zai.glm 5zai.glm-5 · bedrock_converse | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.20 | 200,000 tokens | 估算o200k_base |
| glm 4 32b 0414 128kzai/glm-4-32b-0414-128k · zai | LiteLLM ↗2026-10-25 UTC | $0.10 | $0.10 | 128,000 tokens | 估算o200k_base |
| glm 4.5zai/glm-4.5 · zai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 128,000 tokens | 估算o200k_base |
| glm 4.5 airzai/glm-4.5-air · zai | LiteLLM ↗2026-10-25 UTC | $0.20 | $1.10 | 128,000 tokens | 估算o200k_base |
| glm 4.5 airxzai/glm-4.5-airx · zai | LiteLLM ↗2026-10-25 UTC | $1.10 | $4.50 | 128,000 tokens | 估算o200k_base |
| glm 4.5 flashzai/glm-4.5-flash · zai | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 128,000 tokens | 估算o200k_base |
| glm 4.5 xzai/glm-4.5-x · zai | LiteLLM ↗2026-10-25 UTC | $2.20 | $8.90 | 128,000 tokens | 估算o200k_base |
| glm 4.5vzai/glm-4.5v · zai | LiteLLM ↗2026-10-25 UTC | $0.60 | $1.80 | 128,000 tokens | 估算o200k_base |
| glm 4.6zai/glm-4.6 · zai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 200,000 tokens | 估算o200k_base |
| glm 4.7zai/glm-4.7 · zai | LiteLLM ↗2026-10-25 UTC | $0.60 | $2.20 | 200,000 tokens | 估算o200k_base |
| glm 4.7 flashzai/glm-4.7-flash · zai | LiteLLM ↗2026-10-25 UTC | $0.00 | $0.00 | 200,000 tokens | 估算o200k_base |
| glm 5zai/glm-5 · zai | LiteLLM ↗2026-10-25 UTC | $1.00 | $3.20 | 200,000 tokens | 估算o200k_base |
| glm 5 codezai/glm-5-code · zai | LiteLLM ↗2026-10-25 UTC | $1.20 | $5.00 | 200,000 tokens | 估算o200k_base |
| glm 5.1zai/glm-5.1 · zai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 200,000 tokens | 估算o200k_base |
| glm 5.2zai/glm-5.2 · zai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,000,000 tokens | 估算o200k_base |
| glm 5.3zai/glm-5.3 · zai | LiteLLM ↗2026-10-25 UTC | $1.40 | $4.40 | 1,000,000 tokens | 估算o200k_base |
| glm 5.3 flashzai/glm-5.3-flash · zai | LiteLLM ↗2026-10-25 UTC | $0.15 | $0.50 | 1,048,576 tokens | 估算o200k_base |
没有符合筛选条件的模型。
如何理解这些价格。
价格为构建时从 LiteLLM 获取的每百万输入或输出 Token 美元价格。免费与未验证价格分开显示；缺少任一价格时不能计算完整成本。“精确”表示 tiktoken 映射精确；“估算”表示计数和成本为近似值。
价格为构建时从 LiteLLM 获取的每百万输入或输出 Token 美元价格。免费与未验证价格分开显示；缺少任一价格时不能计算完整成本。“精确”表示 tiktoken 映射精确；“估算”表示计数和成本为近似值。