AI API Cost Estimator
Project your monthly AI API spend. Set your average tokens per request, expected volume, and select models to compare.
500
300
1,000
800
Tokens/request
30,000
Requests/month
24.0M
Total tokens/month
| Model | Est. Monthly Cost |
|---|---|
| Mistral Nemo | $0.55 |
| Granite 4.0 Micro | $1.26 |
| Llama 3.1 8B | $1.47 |
| Mistral Small 3 | $1.47 |
| Qwen2.5 7B Instruct | $1.50 |
| gpt-oss-20b | $1.62 |
| Granite 4.1 8B | $1.65 |
| Gemma 3 4B | $1.65 |
| Amazon Nova Micro | $1.79 |
| Command R7B (12-2024) | $1.91 |
| Gemma 3n 4B | $1.98 |
| gpt-oss-120b | $2.08 |
| Gemma 3 12B | $2.10 |
| Llama 3.2 1B | $2.21 |
| Phi-4 | $2.31 |
| Pixtral 12B | $2.40 |
| Reka Edge | $2.40 |
| Ministral 3 3B 2512 | $2.40 |
| Nemotron 3 Nano 30B A3B | $2.55 |
| Hy3 preview | $2.83 |
| Qwen3.5-9B | $2.85 |
| Amazon Nova Lite | $3.06 |
| DeepSeek V4 Flash | $3.23 |
| UI-TARS 7B | $3.30 |
| Reka Flash 3 | $3.30 |
| Qwen3.5-Flash | $3.31 |
| Qwen3 Coder 30B A3B Instruct | $3.48 |
| Ministral 3 8B 2512 | $3.60 |
| Qwen3 32B | $3.72 |
| Llama 3.2 3B | $3.78 |
| Gemini 1.5 Flash | $3.83 |
| Gemini 2.0 Flash Lite | $3.83 |
| Seed 1.6 Flash | $3.83 |
| gpt-oss-safeguard-20b | $3.83 |
| Llama 3.2 11B Vision | $3.84 |
| Qwen3 14B | $3.96 |
| Gemma 4 26B A4B | $4.11 |
| Llama 4 Scout | $4.20 |
| Mistral Small | $4.20 |
| Voxtral Small 24B 2507 | $4.20 |
| Qwen3 30B A3B Instruct 2507 | $4.20 |
| Mistral Small 3.2 24B | $4.20 |
| Gemma 3 27B | $4.20 |
| Llama Guard 4 12B | $4.32 |
| GPT-5 Nano | $4.35 |
| GLM 4.7 Flash | $4.51 |
| Ministral 3 14B 2512 | $4.80 |
| GPT-4.1 nano | $5.10 |
| Gemini 2.0 Flash | $5.10 |
| Seed-2.0-Mini | $5.10 |
| Gemini 2.5 Flash Lite | $5.10 |
| Gemma 4 31B | $5.13 |
| Nemotron 3 Super | $5.25 |
| Qwen3 VL 32B Instruct | $5.30 |
| Llama 3.3 70B | $5.55 |
| Hermes 4 70B | $5.55 |
| Qwen3 VL 8B Instruct | $5.85 |
| Qwen3 8B | $5.85 |
| Qwen3 235B A22B Instruct 2507 | $6.30 |
| Qwen3 VL 30B A3B Instruct | $6.63 |
| Qwen3 30B A3B | $6.63 |
| Olmo 3 32B Think | $6.75 |
| Hunyuan A13B Instruct | $7.23 |
| Hy3 | $7.32 |
| DeepSeek V3.2 | $7.63 |
| GPT-4o mini | $7.65 |
| QwQ 32B | $7.65 |
| Mistral Small 4 | $7.65 |
| Solar Pro 3 | $7.65 |
| GPT-4o-mini Search Preview | $7.65 |
| Command R (08-2024) | $7.65 |
| GPT-4o-mini (2024-07-18) | $7.65 |
| DeepSeek V3.2 Exp | $7.74 |
| Saba | $8.40 |
| Qwen3 Next 80B A3B Thinking | $8.48 |
| Qwen3 Coder Next | $8.85 |
| Grok 3 Mini | $9.00 |
| Qwen 2.5 72B | $9.00 |
| Llama 3.1 70B | $9.60 |
| GLM 4.5 Air | $9.60 |
| Llama 4 Maverick | $10.20 |
| DeepSeek V3 | $10.20 |
| Mistral Small 3.1 24B | $10.26 |
| MiniMax M2.5 | $10.35 |
| Qwen Plus 0728 | $10.92 |
| Qwen-Plus | $10.92 |
| Trinity Large Thinking | $10.95 |
| Qwen3.6 35B A3B | $11.10 |
| Qwen3.5-35B-A3B | $11.10 |
| Qwen3 Next 80B A3B Instruct | $11.40 |
| Qwen3 Coder Flash | $11.70 |
| DeepSeek V3.1 | $12.30 |
| Codestral | $12.60 |
| GLM 4.6V | $12.60 |
| Codestral 2508 | $12.60 |
| MiniMax M2.7 | $12.75 |
| MiniMax-01 | $12.90 |
| Qwen3.6 Flash | $12.94 |
| DeepSeek V3.1 Terminus | $13.05 |
| Qwen3 Coder 480B A35B | $13.50 |
| Qwen3 VL 8B Thinking | $14.04 |
| DeepSeek V3 0324 | $14.13 |
| GPT-5.4 Nano | $14.25 |
| DeepSeek V4 Pro | $14.36 |
| WizardLM-2 8x22B | $14.88 |
| Claude Haiku 4 | $15.00 |
| Claude 3 Haiku | $15.00 |
| MiniMax M3 | $15.30 |
| MiniMax M2-her | $15.30 |
| MiniMax M2.1 | $15.30 |
| MiniMax M2 | $15.30 |
| Gemma 2 27B | $15.60 |
| Qwen3 VL 30B A3B Thinking | $15.99 |
| Qwen3 30B A3B Thinking 2507 | $15.99 |
| Qwen3.7 Plus | $16.32 |
| Hermes 3 70B Instruct | $16.80 |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | $17.25 |
| Gemini 3.1 Flash Lite | $17.25 |
| Gemini 3.1 Flash Lite Preview | $17.25 |
| ERNIE 4.5 VL 424B A47B | $17.55 |
| Qwen3.5 Plus 2026-02-15 | $17.94 |
| Qwen2.5 Coder 32B Instruct | $18.90 |
| R1 Distill Llama 70B | $19.20 |
| Qwen3 VL 235B A22B Instruct | $20.25 |
| GPT-4.1 mini | $20.40 |
| Qwen3.5 Plus 2026-04-20 | $20.70 |
| GPT-3.5 Turbo | $21.00 |
| Command R | $21.00 |
| Mistral Large 3 2512 | $21.00 |
| Qwen2.5 VL 72B Instruct | $21.00 |
| Llama 3.2 90B Vision | $21.60 |
| Seed-2.0-Lite | $21.75 |
| Seed 1.6 | $21.75 |
| GPT-5.1-Codex-Mini | $21.75 |
| GPT-5 Mini | $21.75 |
| GLM 4.7 | $21.75 |
| Virtuoso Large | $22.05 |
| Qwen3.6 Plus | $22.43 |
| Qwen3.5-122B-A10B | $22.62 |
| Qwen3 235B A22B | $23.20 |
| Mistral Medium 3 | $24.00 |
| Devstral 2 2512 | $24.00 |
| Mistral Medium 3.1 | $24.00 |
| Sonar | $24.00 |
| Hermes 3 405B Instruct | $24.00 |
| GLM 4.5V | $25.20 |
| GLM 4.6 | $25.50 |
| R1 0528 | $26.85 |
| Qwen3.5 397B A17B | $26.91 |
| Gemini 2.5 Flash | $27.00 |
| Gemini 3.5 Flash-Lite | $27.00 |
| Nova 2 Lite | $27.00 |
| Nano Banana (Gemini 2.5 Flash Image) | $27.00 |
| Qwen3.5-27B | $27.30 |
| Qwen3 VL 235B A22B Thinking | $27.30 |
| MiniMax M1 | $28.05 |
| GLM 4.5 | $28.80 |
| Kimi K2 0711 | $29.25 |
| GPT Audio Mini | $30.60 |
| Qwen3.6 27B | $31.05 |
| Qwen3 235B A22B Thinking 2507 | $31.50 |
| Kimi K2 Thinking | $31.50 |
| Kimi K2 0905 | $31.50 |
| DeepSeek R1 | $33.00 |
| Grok Build 0.1 | $33.00 |
| GPT-3.5 Turbo (older v0613) | $33.00 |
| Kimi K2.5 | $34.20 |
| Nano Banana 2 (Gemini 3.1 Flash Image) | $34.50 |
| Nano Banana 2 (Gemini 3.1 Flash Image Preview) | $34.50 |
| Gemini 3 Flash Preview | $34.50 |
| GLM 5.2 | $34.66 |
| GLM 5 | $37.20 |
| Qwen3 Coder Plus | $39.00 |
| GPT-3.5 Turbo Instruct | $40.50 |
| Amazon Nova Pro | $40.80 |
| Kimi K2.6 | $41.04 |
| Grok 4.3 | $41.25 |
| Grok 4.20 Multi-Agent | $41.25 |
| Grok 4.20 | $41.25 |
| Nemotron 3 Ultra | $41.40 |
| GLM 5.1 | $41.81 |
| Hermes 4 405B | $42.00 |
| Kimi K2.7 Code | $46.05 |
| Qwen3 Max Thinking | $46.80 |
| Qwen3 Max | $46.80 |
| Claude 3.5 Haiku | $48.00 |
| GPT-5.4 Mini | $51.75 |
| GLM 5V Turbo | $54.00 |
| GLM 5 Turbo | $54.00 |
| GPT-5 Image Mini | $55.50 |
| OpenAI o4-mini | $56.10 |
| OpenAI o1-mini | $56.10 |
| OpenAI o3-mini | $56.10 |
| o4 Mini High | $56.10 |
| o3 Mini High | $56.10 |
| Claude Haiku 4.5 | $60.00 |
| Qwen3.7 Max | $61.95 |
| Palmyra X5 | $63.00 |
| Gemini 1.5 Pro | $63.75 |
| Llama 3.1 405B | $64.80 |
| GPT-5.6 Luna Pro | $69.00 |
| GPT-5.6 Luna | $69.00 |
| Qwen3.6 Max Preview | $71.76 |
| GPT-3.5 Turbo 16k | $81.00 |
| Mistral Large | $84.00 |
| Grok 4.5 | $84.00 |
| Mistral Large 2407 | $84.00 |
| Mixtral 8x22B Instruct | $84.00 |
| Gemini 3.6 Flash | $90.00 |
| Mistral Medium 3.5 | $90.00 |
| OpenAI o3 | $102.00 |
| GPT-4.1 | $102.00 |
| o4 Mini Deep Research | $102.00 |
| Jamba Large 1.7 | $102.00 |
| Sonar Reasoning Pro | $102.00 |
| Sonar Deep Research | $102.00 |
| Gemini 3.5 Flash | $103.50 |
| Gemini 2.5 Pro | $108.75 |
| GPT-5.1-Codex-Max | $108.75 |
| GPT-5.1 | $108.75 |
| GPT-5.1 Chat | $108.75 |
| GPT-5.1-Codex | $108.75 |
| GPT-5 Codex | $108.75 |
| GPT-5 Chat | $108.75 |
| GPT-5 | $108.75 |
| Gemini 2.5 Pro Preview 06-05 | $108.75 |
| Gemini 2.5 Pro Preview 05-06 | $108.75 |
| Claude Sonnet 5 | $120.00 |
| Grok 2 | $120.00 |
| GPT-4o | $127.50 |
| Command R+ | $127.50 |
| GPT Audio | $127.50 |
| Command A | $127.50 |
| GPT-4o Search Preview | $127.50 |
| GPT-4o (2024-11-20) | $127.50 |
| Inflection 3 Pi | $127.50 |
| Inflection 3 Productivity | $127.50 |
| Command R+ (08-2024) | $127.50 |
| GPT-4o (2024-08-06) | $127.50 |
| Nano Banana Pro (Gemini 3 Pro Image) | $138.00 |
| Gemini 3.1 Pro Preview Custom Tools | $138.00 |
| Gemini 3.1 Pro Preview | $138.00 |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | $138.00 |
| Nova Premier 1.0 | $150.00 |
| GPT-5.3 Chat | $152.25 |
| GPT-5.3-Codex | $152.25 |
| GPT-5.2-Codex | $152.25 |
| GPT-5.2 Chat | $152.25 |
| GPT-5.2 | $152.25 |
| GPT-5.6 Terra Pro | $172.50 |
| GPT-5.6 Terra | $172.50 |
| GPT-5.4 | $172.50 |
| Claude Sonnet 4 | $180.00 |
| Claude 3.5 Sonnet | $180.00 |
| Claude 3.7 Sonnet | $180.00 |
| Grok 3 | $180.00 |
| Kimi K3 | $180.00 |
| Claude Sonnet 4.6 | $180.00 |
| Sonar Pro Search | $180.00 |
| Claude Sonnet 4.5 | $180.00 |
| Sonar Pro | $180.00 |
| GPT-4o (2024-05-13) | $210.00 |
| GPT-5 Image | $240.00 |
| GPT-5.4 Image 2 | $255.00 |
| Claude Opus 4.8 | $300.00 |
| Claude Opus 4.7 | $300.00 |
| Claude Opus 4.6 | $300.00 |
| Claude Opus 4.5 | $300.00 |
| GPT-5.6 Sol Pro | $345.00 |
| GPT-5.6 Sol | $345.00 |
| GPT Chat Latest | $345.00 |
| GPT-5.5 | $345.00 |
| GPT-4 Turbo | $420.00 |
| GPT-4 Turbo Preview | $420.00 |
| o3 Deep Research | $510.00 |
| Claude Fable 5 | $600.00 |
| Claude Opus 4.8 (Fast) | $600.00 |
| OpenAI o1 | $765.00 |
| Claude Opus 4 | $900.00 |
| Claude Opus 4.1 | $900.00 |
| GPT-4 | $990.00 |
| o3 Pro | $1,020.00 |
| GPT-5 Pro | $1,305.00 |
| Claude Opus 4.7 (Fast) | $1,800.00 |
| GPT-5.2 Pro | $1,827.00 |
| GPT-5.5 Pro | $2,070.00 |
| GPT-5.4 Pro | $2,070.00 |
| o1-pro | $7,650.00 |
Estimates based on static pricing data. Actual costs may vary. See the calculator for live pricing.