Price one workload
LLM cost calculator
One workload, every listed price. Cheapest first. Full price table.
… models with a listed input and output price
| Rank | Model | Cost | In $/M | Out $/M | Cache rd |
|---|---|---|---|---|---|
| 1 | MiMo-V2.5 (Free) | $0 | free | free | free |
| 2 | GPT-5 Nano | $0.09 | $0.05 | $0.40 | $0.005 |
| 3 | GLM-4.7-Flash (Deep Infra) | $0.1 | $0.06 | $0.40 | $0.01 |
| 4 | Qwen3.5 35B-A3B | $0.103 | $0.057 | $0.459 | $0.057 |
| 5 | Qwen3.5 9B | $0.103 | $0.09 | $0.13 | $0.045 |
| 6 | GPT OSS 20B (Groq) | $0.105 | $0.075 | $0.30 | $0.0375 |
| 7 | MiniMax-M3.1-Flash | $0.105 | $0.075 | $0.30 | $0.0075 |
| 8 | Qwen3.6 35B A3B | $0.112 | $0.07 | $0.42 | $0.035 |
| 9 | Gemma 3 27B IT (Nebius) | $0.13 | $0.10 | $0.30 | $0.10 |
| 10 | Gemini 2.5 Flash-Lite | $0.14 | $0.10 | $0.40 | $0.01 |
| 11 | GPT-4.1 nano (Azure) | $0.14 | $0.10 | $0.40 | $0.025 |
| 12 | Claude Haiku 5.5 | $0.15 | $0.10 | $0.50 | $0.01 |
| 13 | GPT-6 Luna | $0.15 | $0.10 | $0.50 | $0.01 |
| 14 | Qwen3.5 27B | $0.155 | $0.086 | $0.688 | $0.086 |
| 15 | DeepSeek V4 Flash 0731 (Nebius) | $0.168 | $0.14 | $0.28 | $0.14 |
| 16 | MiMo V2.6 Flash | $0.168 | $0.14 | $0.28 | $0.14 |
| 17 | Hy3 (Deep Infra) | $0.183 | $0.13 | $0.53 | $0.033 |
| 18 | Qwen3.8 Flash | $0.197 | $0.15 | $0.47 | $0.016 |
| 19 | GLM-5.3-Flash | $0.2 | $0.15 | $0.50 | $0.03 |
| 20 | Qwen3-Next 80B-A3B Instruct (Deep Infra) | $0.2 | $0.09 | $1.10 | $0.015 |
| 21 | Gemma 4 26B A4B IT | $0.201 | $0.144 | $0.575 | $0.05 |
| 22 | Qwen3.5 122B-A10B | $0.207 | $0.115 | $0.917 | $0.115 |
| 23 | GLM-4.5-Air | $0.209 | $0.1195 | $0.8964 | $0.0239 |
| 24 | Qwen/Qwen3-32B | $0.209 | $0.1494 | $0.5978 | $0.05 |
| 25 | DeepSeek V4 Flash Vision Exp | $0.21 | $0.15 | $0.60 | $0.003 |
| 26 | GPT-4o mini | $0.21 | $0.15 | $0.60 | $0.075 |
| 27 | Mistral Small (latest) | $0.21 | $0.15 | $0.60 | $0.015 |
| 28 | Qwen3-30B-A3B | $0.218 | $0.11 | $1.08 | $0.05 |
| 29 | GPT OSS 120B (IONOS) | $0.24 | $0.1676 | $0.7262 | $0.15 |
| 30 | Qwen3 Coder Next (IONOS) | $0.257 | $0.1676 | $0.8938 | $0.07 |
| 31 | Qwen3 235B-A22B Instruct 2507 (Nebius) | $0.26 | $0.20 | $0.60 | $0.20 |
| 32 | Qwen3.5 397B-A17B | $0.275 | $0.172 | $1.032 | $0.172 |
| 33 | Qwen3 VL 235B A22B Instruct (Deep Infra) | $0.288 | $0.20 | $0.88 | $0.11 |
| 34 | Qwen3-Coder 30B-A3B Instruct (Scaleway) | $0.314 | $0.2245 | $0.898 | $0.014 |
| 35 | Step 3.7 Flash (Deep Infra) | $0.315 | $0.20 | $1.15 | $0.04 |
| 36 | GPT-5.6 Luna | $0.32 | $0.20 | $1.20 | $0.02 |
| 37 | GPT-5.4 nano | $0.325 | $0.20 | $1.25 | $0.02 |
| 38 | DeepSeek V3 0324 | $0.385 | $0.275 | $1.10 | $0.0299 |
| 39 | GLM-4.5V | $0.388 | $0.2988 | $0.8964 | $0.0598 |
| 40 | Codestral 25.08 | $0.39 | $0.30 | $0.90 | $0.03 |
| 41 | GLM-4.6V | $0.39 | $0.30 | $0.90 | $0.05 |
| 42 | Gemini 3.1 Flash Lite (Vertex AI) | $0.4 | $0.25 | $1.50 | $0.025 |
| 43 | Qwen3.6 Flash | $0.4 | $0.25 | $1.50 | $0.25 |
| 44 | DeepSeek-V3 (Deep Infra) | $0.409 | $0.32 | $0.89 | $0.135 |
| 45 | DeepSeek V4.1 Flash (Nebius) | $0.42 | $0.30 | $1.20 | $0.30 |
| 46 | MiniMax M2.7 Highspeed | $0.42 | $0.30 | $1.20 | $0.03 |
| 47 | MiniMax-M2 | $0.42 | $0.30 | $1.20 | $0.03 |
| 48 | MiniMax-M2.1 | $0.42 | $0.30 | $1.20 | $0.03 |
| 49 | MiniMax-M2.5 | $0.42 | $0.30 | $1.20 | $0.03 |
| 50 | MiniMax-M2.7 | $0.42 | $0.30 | $1.20 | $0.06 |
| 51 | MiniMax-M3 | $0.42 | $0.30 | $1.20 | $0.06 |
| 52 | Muse Glimmer 30B (Deep Infra) | $0.42 | $0.30 | $1.20 | $0.04 |
| 53 | GPT-5 Mini | $0.45 | $0.25 | $2.00 | $0.025 |
| 54 | GPT-5.1 Codex mini (Azure) | $0.45 | $0.25 | $2.00 | $0.025 |
| 55 | Gemma 4 31B IT | $0.495 | $0.38 | $1.15 | $0.05 |
| 56 | MiMo V2.6 Pro | $0.522 | $0.435 | $0.87 | $0.435 |
| 57 | Gemini 2.5 Flash | $0.55 | $0.30 | $2.50 | $0.03 |
| 58 | Gemini 3.5 Flash Lite (Vertex AI) | $0.55 | $0.30 | $2.50 | $0.03 |
| 59 | GPT-4.1 mini | $0.56 | $0.40 | $1.60 | $0.10 |
| 60 | Qwen3.7 Plus | $0.56 | $0.40 | $1.60 | $0.40 |
| 61 | Qwen3-235B-A22B | $0.576 | $0.29 | $2.86 | $0.018 |
| 62 | Qwen3.5 Plus | $0.581 | $0.36 | $2.21 | $0.36 |
| 63 | MiMo-V2.5-Pro | $0.623 | $0.52 | $1.0286 | free |
| 64 | Mistral Large 3 | $0.65 | $0.50 | $1.50 | $0.05 |
| 65 | Qwen3.6 27B | $0.66 | $0.4126 | $2.4754 | $0.4126 |
| 66 | Kimi K2.5 (TensorX) | $0.78 | $0.50 | $2.80 | $0.125 |
| 67 | Llama-3.3-70B-Instruct (IONOS) | $0.799 | $0.7262 | $0.7262 | $0.20 |
| 68 | Gemini 3 Flash Preview (Vertex AI) | $0.8 | $0.50 | $3.00 | $0.05 |
| 69 | Qwen3.6 Plus | $0.8 | $0.50 | $3.00 | $0.50 |
| 70 | Qwen3.8 27B | $0.8 | $0.50 | $3.00 | $0.10 |
| 71 | GLM-4.5 | $0.82 | $0.60 | $2.20 | $0.11 |
| 72 | GLM-4.6 | $0.82 | $0.60 | $2.20 | $0.11 |
| 73 | GLM-4.7 | $0.82 | $0.60 | $2.20 | $0.11 |
| 74 | Kimi K2 Thinking (Amazon Bedrock) | $0.85 | $0.60 | $2.50 | $0.30 |
| 75 | DeepSeek R1 0528 (TensorX) | $0.92 | $0.66 | $2.60 | $0.165 |
| 76 | Hy4 preview (Deep Infra) | $1.084 | $0.834 | $2.501 | $0.042 |
| 77 | Gemini 3.6 Flash (Vertex AI) | $1.125 | $0.75 | $3.75 | $0.075 |
| 78 | GPT-5.4 mini | $1.2 | $0.75 | $4.50 | $0.075 |
| 79 | Grok Build 0.1 | $1.2 | $1.00 | $2.00 | $0.20 |
| 80 | Step 5 Preview (Deep Infra) | $1.27 | $1.00 | $2.70 | $0.10 |
Common questions
- How do I estimate the cost of an LLM workload?
- Set input tokens, output tokens and optional cache-read tokens. The table multiplies those by each model's listed rates. Cache-read uses the cache price when a host publishes one. It uses the input price if not.
- What token mix should I use?
- The default is 1 million input tokens and 100 thousand output tokens. That matches a long document plus a short answer. Change the fields. The URL keeps the mix so you can share it.