LLM API pricing calculator
Estimate what 920 AI models cost for your workload, at prices from LiteLLM's price file as of October 27, 2026. Pick a model, then enter tokens per request and requests per day.
- Per request
- $0.014
- Per day
- $140
- Per month (30 days)
- $4,200
Uses each model's headline price: its own lab's API where it sells it, otherwise its cheapest provider. Cached input, batch discounts and long-context tiers aren't included; each model's page lists them.
What 10,000 requests a day cost
Each request with 1,000 input and 500 output tokens, for the models on our comparison pages, cheapest first.
| Model | Per request | Per day | Per month |
|---|---|---|---|
| GPT OSS 20B | $0.0000495 | $0.49 | $14.85 |
| GPT OSS 120B | $0.000115 | $1.15 | $34.50 |
| DeepSeek V4.1 Flash | $0.00024 | $2.40 | $72.00 |
| Llama 3.3 70B Instruct | $0.00027 | $2.70 | $81.00 |
| Mimo V2.6 Flash | $0.00028 | $2.80 | $84.00 |
| Gemini 2.5 Flash Lite | $0.0003 | $3.00 | $90.00 |
| Claude Haiku 5.5 | $0.00035 | $3.50 | $105 |
| GPT-6 Luna | $0.00035 | $3.50 | $105 |
| Qwen3.8 Omni Flash | $0.000385 | $3.85 | $116 |
| GLM 5.3 Flash | $0.0004 | $4.00 | $120 |
| MiniMax M3.1 Flash | $0.00045 | $4.50 | $135 |
| Nvidia Nemotron 3.5 Super VL 120B A12B | $0.000525 | $5.25 | $158 |
| DeepSeek V4.1 Flash Fast | $0.00061 | $6.10 | $183 |
| MiniMax M2.7 | $0.00075 | $7.50 | $225 |
| GPT-5.6 Luna | $0.0008 | $8.00 | $240 |
| DeepSeek V4 Flash | $0.0009 | $9.00 | $270 |
| Longcat 2.0 | $0.0009 | $9.00 | $270 |
| MiniMax M2.5 | $0.0009 | $9.00 | $270 |
| MiniMax M3 | $0.0009 | $9.00 | $270 |
| Mistral Large 3 | $0.00125 | $12.50 | $375 |
| Gemini 3.5 Flash Lite | $0.00155 | $15.50 | $465 |
| Mistral Large 4 | $0.001725 | $17.25 | $518 |
| Hy4 Preview | $0.002084 | $20.84 | $625 |
| Kimi K2.5 | $0.0021 | $21.00 | $630 |
| Gemini 3 Flash | $0.0025 | $25.00 | $750 |
| Gemini 3.7 Flash | $0.002625 | $26.25 | $788 |
| Gemini 3.8 Flash | $0.002625 | $26.25 | $788 |
| Kimi K2.6 | $0.00295 | $29.50 | $885 |
| Kimi K2.7 Code | $0.00295 | $29.50 | $885 |
| DeepSeek V4 Pro | $0.0033 | $33.00 | $990 |
| Muse Spark 1.1 | $0.003375 | $33.75 | $1,013 |
| Muse Spark 1.2 | $0.003375 | $33.75 | $1,013 |
| Muse Spark 1.3 | $0.003375 | $33.75 | $1,013 |
| Muse Spark Open | $0.003375 | $33.75 | $1,013 |
| Claude Haiku 4.5 | $0.0035 | $35.00 | $1,050 |
| GPT-6.1 Terra | $0.0035 | $35.00 | $1,050 |
| GLM 5.1 | $0.0036 | $36.00 | $1,080 |
| GLM 5.2 | $0.0036 | $36.00 | $1,080 |
| GLM 5.3 | $0.0036 | $36.00 | $1,080 |
| Qwen3 Max | $0.0042 | $42.00 | $1,260 |
| Grok 4.5 | $0.005 | $50.00 | $1,500 |
| Grok 4.6 | $0.005 | $50.00 | $1,500 |
| Grok 4.7 | $0.005 | $50.00 | $1,500 |
| Qwen3.8 Max | $0.005 | $50.00 | $1,500 |
| Qwen3.7 Max | $0.00625 | $62.50 | $1,875 |
| Claude Sonnet 5 | $0.007 | $70.00 | $2,100 |
| Claude Sonnet 5.5 | $0.007 | $70.00 | $2,100 |
| Gemini 4 Argon introductory price until November 30, 2026 | $0.007 | $70.00 | $2,100 |
| GPT-6 Sol | $0.007 | $70.00 | $2,100 |
| GPT-6.1 Sol | $0.007 | $70.00 | $2,100 |
| Gemini 3 Pro | $0.008 | $80.00 | $2,400 |
| Gemini 3.1 Pro Preview | $0.008 | $80.00 | $2,400 |
| GPT-5.6 Terra | $0.008 | $80.00 | $2,400 |
| GPT-5.4 | $0.01 | $100 | $3,000 |
| Claude Sonnet 4.6 | $0.0105 | $105 | $3,150 |
| Kimi K3 | $0.0105 | $105 | $3,150 |
| Claude Opus 5.5 | $0.014 | $140 | $4,200 |
| GPT-5.6 | $0.014 | $140 | $4,200 |
| GPT-5.6 Sol | $0.014 | $140 | $4,200 |
| Muse Wonder 1.0 | $0.014 | $140 | $4,200 |
| Claude Opus 4.8 | $0.0175 | $175 | $5,250 |
| Claude Opus 5 | $0.0175 | $175 | $5,250 |
| GPT-5.5 | $0.02 | $200 | $6,000 |
| Claude Fable 5 | $0.035 | $350 | $10,500 |
| Claude Fable 5.1 | $0.035 | $350 | $10,500 |
| GPT-6 Astra | $0.035 | $350 | $10,500 |
