AI API cost calculator
Monthly cost at list price for 211 models, cheapest first.
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Llama 3.2 1B Instruct | $0.02 | $0.02 | $1.20 |
| Llama-3.1-8B-Instruct | $0.02 | $0.05 | $1.50 |
| DeepSeek OCR 2 | $0.03 | $0.03 | $1.80 |
| Qwen3-ASR Flash | $0.035 | $0.035 | $2.10 |
| Voxtral Mini 3B 2507 | $0.04 | $0.04 | $2.40 |
| Gemma 3 4B IT | $0.04 | $0.08 | $2.80 |
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| AutoGLM Phone 9B Multilingual | $0.035 | $0.138 | $3.13 |
| Llama 3.2 1B Instruct | $0.027 | $0.201 | $3.36 |
| Command R7B | $0.0375 | $0.15 | $3.38 |
| Command R7B Arabic | $0.0375 | $0.15 | $3.38 |
| Gemma 3 12B IT | $0.05 | $0.10 | $3.50 |
| DeepSeek R1 0528 Qwen3 8B | $0.06 | $0.09 | $3.90 |
| Qwen Turbo | $0.05 | $0.20 | $4.50 |
| DeepSeek V4 Flash 0731 | $0.06 | $0.18 | $4.80 |
| GPT OSS 120B | $0.05 | $0.25 | $5.00 |
| Qwen-VL OCR | $0.07 | $0.16 | $5.10 |
| GPT OSS Safeguard 20B | $0.07 | $0.20 | $5.50 |
| Gemma 3 27B IT | $0.08 | $0.16 | $5.60 |
| Llama 3.2 3B Instruct | $0.0509 | $0.335 | $5.90 |
| Qwen3 30B A3b fp8 | $0.0509 | $0.335 | $5.90 |
| Ministral 3 3B | $0.10 | $0.10 | $6.00 |
| DeepSeek V4 Flash | $0.09 | $0.18 | $6.30 |
| GPT-5 Nano | $0.05 | $0.40 | $6.50 |
| gpt-oss-20b | $0.07 | $0.30 | $6.50 |
| Qwen Flash | $0.05 | $0.40 | $6.50 |
| Qwen3.5 9B | $0.10 | $0.15 | $6.50 |
| Gemma 4 26B A4B IT | $0.07 | $0.34 | $6.90 |
| GLM-4.7-Flash | $0.0605 | $0.40 | $7.03 |
| GLM-4.7-FlashX | $0.07 | $0.40 | $7.50 |
| Mistral Small 3.1 24B | $0.10 | $0.30 | $8.00 |
| Voxtral Small 24B 2507 | $0.10 | $0.30 | $8.00 |
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | $9.00 |
| Ministral 3 8B | $0.15 | $0.15 | $9.00 |
| Qwen3.5 Flash | $0.10 | $0.40 | $9.00 |
| Voxtral Small | $0.10 | $0.40 | $9.00 |
| Llama 3.2 11B Vision Instruct | $0.0485 | $0.676 | $9.19 |
| Claude Haiku 5.5 | $0.10 | $0.50 | $10.00 |
| GPT-6 Luna | $0.10 | $0.50 | $10.00 |
| Qwen3 235B-A22B Instruct 2507 | $0.09 | $0.55 | $10.00 |
| Llama-3.3-70B-Instruct | $0.135 | $0.40 | $10.75 |
| Gemma 4 31B IT | $0.14 | $0.40 | $11.00 |
| Ministral 3 14B | $0.20 | $0.20 | $12.00 |
| Qwen3.8 Flash | $0.15 | $0.47 | $12.20 |
| Qwen3.8 Omni Flash | $0.15 | $0.47 | $12.20 |
| GLM-5.3-Flash | $0.15 | $0.50 | $12.50 |
| Qwen-MT Turbo | $0.16 | $0.49 | $12.90 |
| Command R | $0.15 | $0.60 | $13.50 |
| GPT OSS Safeguard 120B | $0.15 | $0.60 | $13.50 |
| GPT-4o mini | $0.15 | $0.60 | $13.50 |
| Mistral Small 4 | $0.15 | $0.60 | $13.50 |
| Qwen3 VL 30B A3B Instruct | $0.15 | $0.60 | $13.50 |
| Llama 4 Scout 17B Instruct | $0.18 | $0.59 | $14.90 |
| Qwen2.5 7B Instruct | $0.175 | $0.70 | $15.75 |
| Qwen3 8B | $0.18 | $0.70 | $16.00 |
| Qwen-VL Plus | $0.21 | $0.63 | $16.80 |
| Qwen3-VL 30B-A3B | $0.20 | $0.80 | $18.00 |
| Qwen3 VL 235B A22B Instruct | $0.20 | $0.88 | $18.80 |
| Qwen3.6 Flash | $0.1875 | $1.125 | $20.63 |
| GLM-4.5-Air | $0.20 | $1.10 | $21.00 |
| DeepSeek-V3.1 | $0.25 | $0.95 | $22.00 |
| GPT-5.6 Luna | $0.20 | $1.20 | $22.00 |
| Llama 4 Maverick 17B Instruct | $0.27 | $0.85 | $22.00 |
| Qwen3 Omni 30B A3B Thinking | $0.25 | $0.97 | $22.20 |
| GPT-5.4 nano | $0.20 | $1.25 | $22.50 |
| Codestral 25.08 | $0.30 | $0.90 | $24.00 |
| GLM-4.6V | $0.30 | $0.90 | $24.00 |
| Llama Guard 3 8B | $0.484 | $0.03 | $24.50 |
| DeepSeek-V3 | $0.32 | $0.89 | $24.90 |
| Qwen3-VL Plus | $0.20 | $1.60 | $26.00 |
| MiniMax-M2 | $0.30 | $1.20 | $27.00 |
| MiniMax-M2.1 | $0.30 | $1.20 | $27.00 |
| MiniMax-M2.5 | $0.30 | $1.20 | $27.00 |
| MiniMax-M2.7 | $0.30 | $1.20 | $27.00 |
| MiniMax-M3 | $0.30 | $1.20 | $27.00 |
| Qwen3.6 35B-A3B | $0.248 | $1.485 | $27.25 |
| Gemini 3.1 Flash Lite | $0.25 | $1.50 | $27.50 |
| Qwen2.5-VL 7B Instruct | $0.35 | $1.05 | $28.00 |
| Qwen3 Coder Flash | $0.30 | $1.50 | $30.00 |
| Qwen2.5 14B Instruct | $0.35 | $1.40 | $31.50 |
| Qwen3 14B | $0.35 | $1.40 | $31.50 |
| Qwen Plus | $0.40 | $1.20 | $32.00 |
| GPT-5 Mini | $0.25 | $2.00 | $32.50 |
| Qwen3.5 35B-A3B | $0.25 | $2.00 | $32.50 |
| Qwen3.8 27B | $0.20 | $2.50 | $35.00 |
| DeepSeek V4 Flash Vision Exp | $0.44 | $1.32 | $35.20 |
| GPT-4.1 mini | $0.40 | $1.60 | $36.00 |
| Qwen3.7 Plus | $0.40 | $1.60 | $36.00 |
| Qwen3 Coder Next | $0.50 | $1.20 | $37.00 |
| Qwen Plus Character (Japanese) | $0.50 | $1.40 | $39.00 |
| Qwen3.5 27B | $0.30 | $2.40 | $39.00 |
| Gemini 2.5 Flash | $0.30 | $2.50 | $40.00 |
| Gemini 3.5 Flash Lite | $0.30 | $2.50 | $40.00 |
| Magistral Small 1.2 | $0.50 | $1.50 | $40.00 |
| Mistral Large 3 | $0.50 | $1.50 | $40.00 |
| Qwen2.5 Coder 32B Instruct | $0.66 | $1.00 | $43.00 |
| Qwq 32B | $0.66 | $1.00 | $43.00 |
| Llama 3.1 70B Instruct | $0.72 | $0.72 | $43.20 |
| Qwen3.5 Plus | $0.40 | $2.40 | $44.00 |
| Qwen3-Coder 30B-A3B Instruct | $0.45 | $2.25 | $45.00 |
| Qwen3-Next 80B-A3B Instruct | $0.50 | $2.00 | $45.00 |
| GLM-4.5V | $0.60 | $1.80 | $48.00 |
| DeepSeek V3.2 | $0.62 | $1.85 | $49.50 |
| MiniMax M1 80K | $0.55 | $2.20 | $49.50 |
| Kimi K2 Instruct | $0.57 | $2.30 | $51.50 |
| GLM-4.5 | $0.60 | $2.20 | $52.00 |
| GLM-4.6 | $0.60 | $2.20 | $52.00 |
| GLM-4.7 | $0.60 | $2.20 | $52.00 |
| Qwen3.5 122B-A10B | $0.40 | $3.20 | $52.00 |
| DeepSeek V4 Pro | $0.66 | $1.98 | $52.80 |
| MiniMax-M2.5-highspeed | $0.60 | $2.40 | $54.00 |
| MiniMax-M2.7-highspeed | $0.60 | $2.40 | $54.00 |
| Gemini 3 Flash Preview | $0.50 | $3.00 | $55.00 |
| Kimi K2 Instruct 0905 | $0.60 | $2.50 | $55.00 |
| Kimi K2 Thinking | $0.60 | $2.50 | $55.00 |
| Qwen3.6 Plus | $0.50 | $3.00 | $55.00 |
| DeepSeek R1 (Turbo) | $0.70 | $2.50 | $60.00 |
| Kimi K2.5 | $0.60 | $3.00 | $60.00 |
| Qwen2.5 32B Instruct | $0.70 | $2.80 | $63.00 |
| Qwen3 235B-A22B | $0.70 | $2.80 | $63.00 |
| Qwen3 32B | $0.70 | $2.80 | $63.00 |
| Qwen3-VL 235B-A22B | $0.70 | $2.80 | $63.00 |
| QwQ Plus | $0.80 | $2.40 | $64.00 |
| Qwen3.5 397B-A17B | $0.60 | $3.60 | $66.00 |
| Qwen3.6 27B | $0.60 | $3.60 | $66.00 |
| Grok Build 0.1 | $1.00 | $2.00 | $70.00 |
| Qwen-VL Max | $0.80 | $3.20 | $72.00 |
| Gemini 3.6 Flash | $0.75 | $3.75 | $75.00 |
| Gemini 3.7 Flash | $0.75 | $3.75 | $75.00 |
| Gemini 3.8 Flash | $0.75 | $3.75 | $75.00 |
| GLM-5 | $1.00 | $3.20 | $82.00 |
| GPT-5.4 mini | $0.75 | $4.50 | $82.50 |
| Qwen3-Next 80B-A3B (Thinking) | $0.50 | $6.00 | $85.00 |
| Grok 4.20 (Non-Reasoning) | $1.25 | $2.50 | $87.50 |
| Grok 4.20 (Reasoning) | $1.25 | $2.50 | $87.50 |
| Grok 4.20 Multi-Agent | $1.25 | $2.50 | $87.50 |
| Grok 4.3 | $1.25 | $2.50 | $87.50 |
| Kimi K2.6 | $0.95 | $4.00 | $87.50 |
| Claude Haiku 4.5 | $1.00 | $5.00 | $100 |
| GLM-5-Turbo | $1.20 | $4.00 | $100 |
| GLM-5V-Turbo | $1.20 | $4.00 | $100 |
| Qwen3 Coder Plus | $1.00 | $5.00 | $100 |
| Muse Spark 1.1 | $1.25 | $4.25 | $105 |
| Muse Spark 1.2 | $1.25 | $4.25 | $105 |
| Muse Spark 1.3 | $1.25 | $4.25 | $105 |
| QVQ Max | $1.20 | $4.80 | $108 |
| GLM-5.1 | $1.40 | $4.40 | $114 |
| GLM-5.2 | $1.40 | $4.40 | $114 |
| GLM-5.3 | $1.40 | $4.40 | $114 |
| Qwen3 Max | $1.20 | $6.00 | $120 |
| Qwen2.5 72B Instruct | $1.40 | $5.60 | $126 |
| Qwen3.6 Max Preview | $1.30 | $7.80 | $143 |
| Qwen Max | $1.60 | $6.40 | $144 |
| Mistral Medium 3.5 | $1.50 | $7.50 | $150 |
| Qwen3-Coder 480B-A35B Instruct | $1.50 | $7.50 | $150 |
| Grok 4.5 | $2.00 | $6.00 | $160 |
| Grok 4.6 | $2.00 | $6.00 | $160 |
| Grok 4.7 | $2.00 | $6.00 | $160 |
| Pixtral Large (25.02) | $2.00 | $6.00 | $160 |
| Qwen3.8 2.4T A95B | $2.00 | $6.00 | $160 |
| Qwen3.8 Max | $2.00 | $6.00 | $160 |
| Gemini 2.5 Computer Use Preview 10-2025 | $1.25 | $10.00 | $163 |
| Gemini 2.5 Pro | $1.25 | $10.00 | $163 |
| GPT-5 | $1.25 | $10.00 | $163 |
| GPT-5.1 | $1.25 | $10.00 | $163 |
| GPT-5.1 Codex Max | $1.25 | $10.00 | $163 |
| Gemini 3.5 Flash | $1.50 | $9.00 | $165 |
| Kimi K2.7 Code HighSpeed | $1.90 | $8.00 | $175 |
| GPT-4.1 | $2.00 | $8.00 | $180 |
| o3 | $2.00 | $8.00 | $180 |
| Qwen-MT Plus | $2.46 | $7.37 | $197 |
| Claude Sonnet 5 | $2.00 | $10.00 | $200 |
| Claude Sonnet 5.5 | $2.00 | $10.00 | $200 |
| GPT-6 Sol | $2.00 | $10.00 | $200 |
| GPT-6.1 Sol | $2.00 | $10.00 | $200 |
| Qwen3.7 Max | $2.50 | $7.50 | $200 |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | $220 |
| Gemini 3.1 Pro Preview Custom Tools | $2.00 | $12.00 | $220 |
| GPT-5.6 Terra | $2.00 | $12.00 | $220 |
| Qwen2.5-VL 72B Instruct | $2.80 | $8.40 | $224 |
| Command A | $2.50 | $10.00 | $225 |
| Command A Plus | $2.50 | $10.00 | $225 |
| Command A Reasoning | $2.50 | $10.00 | $225 |
| Command A Translate | $2.50 | $10.00 | $225 |
| Command A Vision | $2.50 | $10.00 | $225 |
| Command R+ | $2.50 | $10.00 | $225 |
| GPT-4o | $2.50 | $10.00 | $225 |
| GPT-5.2 | $1.75 | $14.00 | $228 |
| GPT-5.3 Codex | $1.75 | $14.00 | $228 |
| GPT-5.3 Codex Spark | $1.75 | $14.00 | $228 |
| GPT-5.4 | $2.50 | $15.00 | $275 |
| Claude Sonnet 4.5 | $3.00 | $15.00 | $300 |
| Claude Sonnet 4.6 | $3.00 | $15.00 | $300 |
| Kimi K3 | $3.00 | $15.00 | $300 |
| Claude Opus 5.5 | $4.00 | $20.00 | $400 |
| GPT-5.6 | $4.00 | $20.00 | $400 |
| Claude Opus 4.5 | $5.00 | $25.00 | $500 |
| Claude Opus 4.6 | $5.00 | $25.00 | $500 |
| Claude Opus 4.7 | $5.00 | $25.00 | $500 |
| Claude Opus 4.8 | $5.00 | $25.00 | $500 |
| Claude Opus 5 | $5.00 | $25.00 | $500 |
| GPT-5.5 | $5.00 | $30.00 | $550 |
| Claude Fable 5 | $10.00 | $50.00 | $1,000 |
| Claude Fable 5.1 | $10.00 | $50.00 | $1,000 |
| GPT-6 Astra | $10.00 | $50.00 | $1,000 |
| o3-pro | $20.00 | $80.00 | $1,800 |
| GPT-5 Pro | $15.00 | $120.00 | $1,950 |
| GPT-5.2 Pro | $21.00 | $168.00 | $2,730 |
| GPT-5.4 Pro | $30.00 | $180.00 | $3,300 |
| GPT-5.5 Pro | $30.00 | $180.00 | $3,300 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.