Free tool

LLM API Cost Calculator

Enter tokens per request and requests per day, or start from a preset. The table shows the monthly bill for every ranked model at list price, cheapest first, next to its score.

Last verified

ModelScorePer requestPer month
gpt-oss-20b32.5$0.00$1.89
Granite 4.0 Micro29.0$0.00$2.11
Gemma 3 4B28.1$0.00$2.76
Qwen3.7 Flash39.9$0.00$2.91
Llama 3.1-8B23.0$0.00$3.21
Mistral Small 331.2$0.00$3.21
Amazon Nova Micro30.4$0.00$3.26
Mercury 2.533.5$0.00$3.60
Llama 3.2 1B20.1$0.00$3.63
gpt-oss-120b36.3$0.00$3.71
Gemma 3 12B32.1$0.00$4.05
Nemotron 3 Nano 30B A3B40.6$0.00$4.65
Nemotron 3.5 Lightning40.0$0.00$4.65
Qwen Turbo27.1$0.00$4.65
Phi-431.2$0.00$4.83
Gemma 3 27B30.8$0.00$5.52
Amazon Nova Lite31.9$0.00$5.58
Ministral 3B26.2$0.00$5.70
Granite 4.2 8B40.5$0.00$5.70
Gemma 4 26B A4B IT43.5$0.00$5.74
Llama 3.2 3B28.9$0.00$6.21
Qwen3.5-9B33.8$0.00$6.30
Phi-4 Mini30.9$0.00$6.97
GPT-5 Nano33.5$0.00$7.05
Mistral Small 3.231.2$0.00$7.22
GLM-4.7-Flash38.8$0.00$7.50
Hy344.2$0.00$7.67
Devstral Small 250534.3$0.00$8.10
Llama 4 Scout27.7$0.00$8.10
Step 3.5 Flash42.3$0.00$8.10
Gemma 4 31B IT43.5$0.00$8.13
Llama-3.3-70B-Instruct30.6$0.00$8.34
Ministral 8B28.2$0.00$8.55
Mistral Nemo26.4$0.00$8.55
Nemotron 3 Super40.1$0.00$9.00
Gemini 2.5 Flash-Lite37.0$0.00$9.30
GPT-4.1 nano27.9$0.00$9.30
Qwen3.5-Flash42.5$0.00$9.30
MiMo-V2-Flash41.3$0.00$9.66
MiMo-V2-Omni43.6$0.00$9.66
MiMo-V2.543.4$0.00$9.66
MiMo-V2.6-Flash48.5$0.00$9.66
Claude Haiku 5.549.5$0.00$10.50
GPT-6 Luna53.3$0.00$10.50
Qwen3-30B-A3B38.9$0.00$11.40
GLM-5.3-Flash51.8$0.00$12.75
Command R31.4$0.00$13.95
DeepSeek V4 Flash53.6$0.00$13.95
DeepSeek V4.1 Flash52.8$0.00$13.95
GPT-4o mini25.5$0.00$13.95
Mistral Small33.4$0.00$13.95
Mistral 7B23.0$0.00$14.25
Grok 4.1 Fast41.4$0.00$15.00
Qwen3 Coder Next34.3$0.00$15.00
DeepSeek-V3.2-Exp44.3$0.00$16.26
Llama 4 Maverick30.9$0.00$16.27
Qwen2.5 7B Instruct29.0$0.00$16.27
Qwen3 8B33.7$0.00$16.50
Mercury 239.1$0.00$20.25
Mistral Large 339.1$0.00$20.25
Trinity Large Thinking38.6$0.00$20.85
DeepSeek-V339.5$0.00$21.60
Step 3.7 Flash37.3$0.00$21.65
Qwen3.6 Flash38.8$0.00$21.94
GLM-4.5-Air38.9$0.00$22.20
Mistral Small 3.131.7$0.00$22.45
DeepSeek-V3.142.8$0.00$22.65
Llama 3.1-70B29.6$0.00$22.80
Nvidia Llama 3.3 Nemotron Super 49b v1.540.3$0.00$22.80
GPT-5.6 Luna54.6$0.00$23.40
GPT-5.4 nano41.9$0.00$24.00
DeepSeek-V3.1-Terminus43.1$0.00$24.15
Codestral30.6$0.00$24.30
GLM-4.6V41.3$0.00$24.30
MiniMax-M237.4$0.00$27.90
MiniMax-M2.138.9$0.00$27.90
MiniMax-M2.538.3$0.00$27.90
MiniMax-M2.737.7$0.00$27.90
MiniMax-M343.8$0.00$27.90
Solar Pro442.1$0.00$27.90
Qwen3.6 35B-A3B37.6$0.00$28.98
Gemini 3.1 Flash Lite40.8$0.00$29.25
MiMo-V2-Pro43.0$0.00$30.02
MiMo-V2.5-Pro45.2$0.00$30.02
MiMo-V2.6-Pro50.3$0.00$30.02
Qwen Plus37.1$0.00$32.40
Qwen3 14B35.5$0.00$32.55
Inkling-Small46.5$0.00$34.65
GPT-5 Mini41.8$0.00$35.25
Qwen3.5 35B-A3B42.0$0.00$35.25
Gemma 2 27B29.4$0.00$37.05
GPT-4.1 mini33.6$0.00$37.20
Qwen3.7 Plus45.3$0.00$37.20
Mixtral 8x7B27.1$0.00$39.90
GPT-3.5-turbo23.2$0.00$40.50
Magistral Small30.2$0.00$40.50
Qwen2.5-Coder-32B33.4$0.00$41.70
Mistral Medium 3.131.9$0.00$42.00
Qwen3.5 27B41.9$0.00$42.30
Gemini 2.5 Flash39.3$0.00$43.50
Gemini 3.5 Flash Lite41.5$0.00$43.50
Nova 2 Lite39.7$0.00$43.50
DeepSeek-V3.2-Speciale39.7$0.00$46.26
Qwen3-Next 80B-A3B Instruct43.0$0.00$46.50
Qwen3.5 Plus42.9$0.00$46.80
Kimi K2.548.1$0.00$47.25
DeepSeek-R142.3$0.00$48.30
GLM-4.5V39.8$0.00$48.60
Nemotron 3 Ultra42.5$0.00$48.90
MiniMax M140.3$0.00$51.15
Kimi K2 (Jul 2025)41.2$0.00$53.25
GLM-4.542.0$0.00$53.40
GLM-4.641.4$0.00$53.40
GLM-4.742.0$0.00$53.40
DeepSeek V4 Pro54.3$0.00$53.46
Mistral Large 443.1$0.00$55.68
Qwen3.5 122B-A10B42.1$0.00$56.40
Sonar38.5$0.00$57.00
Gemini 3 Flash Preview52.3$0.00$58.50
Qwen3.6 Plus47.5$0.00$58.50
Seed 2.0 Pro43.2$0.00$58.50
Hy4 preview45.3$0.00$60.79
Qwen3.8 27B46.0$0.00$62.43
Qwen2.5 32B Instruct30.1$0.00$65.10
Qwen3 235B-A22B43.5$0.00$65.10
Qwen3 32B39.2$0.00$65.10
Qwen3-VL 235B-A22B43.2$0.00$65.10
Grok Build 0.136.4$0.00$69.00
Qwen3.5 397B-A17B46.0$0.00$70.20
Qwen3.6 27B42.2$0.00$70.20
Amazon Nova Pro31.0$0.00$74.40
Step 5 Preview47.9$0.00$77.40
Gemini 3.6 Flash54.1$0.00$78.75
Gemini 3.7 Flash59.8$0.00$78.75
Gemini 3.8 Flash61.8$0.00$78.75
GLM-546.1$0.00$83.40
Grok 4.20 (Non-Reasoning)48.6$0.00$86.25
Grok 4.20 Multi-Agent46.2$0.00$86.25
Grok 4.343.8$0.00$86.25
GPT-5.4 mini45.0$0.00$87.75
Kimi K2.647.7$0.00$90.75
Kimi K2.7 Code43.3$0.00$90.75
GLM-5V-Turbo43.8$0.00$102
o3-mini36.7$0.00$102
o4-mini41.6$0.00$102
Claude Haiku 4.539.5$0.00$105
Muse Spark 1.149.9$0.00$107
Muse Spark 1.250.3$0.00$107
Muse Spark 1.354.8$0.00$107
GLM-5.147.8$0.00$116
GLM-5.251.1$0.00$116
GLM-5.354.8$0.00$116
Qwen3 Max43.7$0.00$126
Qwen2.5 72B Instruct31.9$0.00$130
Inkling44.1$0.00$140
Qwen Max34.7$0.00$149
Magistral Medium35.2$0.01$150
Qwen3.6 Max Preview51.5$0.01$152
Mistral Medium36.3$0.01$158
Mistral Medium 3.540.2$0.01$158
Qwen3-Coder 480B-A35B Instruct38.1$0.01$158
Grok 4.555.0$0.01$162
Grok 4.656.9$0.01$162
Grok 4.753.1$0.01$162
Mistral Large31.9$0.01$162
Mixtral 8x22B27.1$0.01$162
Pixtral Large32.2$0.01$162
Qwen3.8 Max56.8$0.01$162
Gemini 3.5 Flash54.2$0.01$176
Gemini 2.5 Pro45.0$0.01$176
GPT-550.9$0.01$176
GPT-5-Codex37.9$0.01$176
GPT-5.149.0$0.01$176
GPT-5.1-Codex38.6$0.01$176
GPT-4.135.9$0.01$186
o347.5$0.01$186
Qwen3.7 Max51.5$0.01$203
Claude Sonnet 554.6$0.01$210
Claude Sonnet 5.561.9$0.01$210
GPT-6 Sol61.8$0.01$210
GPT-6.1 Sol65.6$0.01$210
Qwen2.5-VL 72B Instruct29.9$0.01$227
Command A36.5$0.01$233
Command R+32.4$0.01$233
GPT-4o28.6$0.01$233
Gemini 3.1 Pro Preview56.7$0.01$234
GPT-5.6 Terra59.2$0.01$234
GPT-5.254.1$0.01$247
GPT-5.2 Codex42.6$0.01$247
GPT-5.3 Chat42.8$0.01$247
GPT-5.3 Codex45.8$0.01$247
Nova Premier 1.038.3$0.01$263
GPT-5.459.4$0.01$293
Claude Sonnet 440.8$0.01$315
Claude Sonnet 4.544.1$0.01$315
Claude Sonnet 4.650.3$0.01$315
Kimi K359.5$0.01$315
Claude Opus 5.568.6$0.01$420
GPT-5.6 Sol65.0$0.01$420
Claude Opus 4.550.5$0.02$525
Claude Opus 4.658.2$0.02$525
Claude Opus 4.758.3$0.02$525
Claude Opus 4.860.7$0.02$525
Claude Opus 567.8$0.02$525
GPT-5.563.4$0.02$585
GPT-4 Turbo30.5$0.03$810
Claude Fable 566.8$0.04$1,050
Claude Fable 5.169.0$0.04$1,050
GPT-6 Astra70.8$0.04$1,050
o140.9$0.05$1,395
Claude Opus 443.1$0.05$1,575
Claude Opus 4.141.0$0.05$1,575
o3-pro42.9$0.06$1,860
GPT-429.1$0.07$2,070
GPT-5 Pro46.4$0.07$2,115
GPT-5.2 Pro52.3$0.10$2,961
GPT-5.4 Pro58.9$0.12$3,510
GPT-5.5 Pro64.3$0.12$3,510
o1-pro31.5$0.47$13,950

Frequently asked questions

How is the cost calculated?

Monthly cost = (input tokens × input price + output tokens × output price) × requests per day × 30, using list prices per million tokens. Cached input is billed at the cached rate where the provider offers one.

How many tokens is a word?

About 1.3 tokens per English word, or roughly 4 characters per token. Code and non-English text use more.