Cheapest reasoning models
Models flagged as reasoning-capable, sorted by input cost, for maths, planning and multi-step debugging.
Current leader: Gemma 4 26b A4b It (Google Gemini). Refreshed 2026-09-13 13:40 UTC.
| # | Model | Provider | Input $/1M | Output $/1M | Cached $/1M | Context |
|---|---|---|---|---|---|---|
| 1 | Gemma 4 26b A4b It | Google Gemini | free | free | — | 262K |
| 2 | Gemma 4 31b It | Google Gemini | free | free | — | 262K |
| 3 | Anthropic.claude Mythos Preview | Amazon Bedrock | free | free | — | 1M |
| 4 | Auto | OpenRouter | free | free | — | 2M |
| 5 | Free | OpenRouter | free | free | — | 200K |
| 6 | Nemotron 3.5 Lightning:free | OpenRouter | free | free | — | 1M |
| 7 | Laguna S 2.1:free | OpenRouter | free | free | — | 262K |
| 8 | Laguna Xs 2.1:free | OpenRouter | free | free | — | 262K |
| 9 | Glm 5.2:free | OpenRouter | free | free | — | 256K |
| 10 | Nemotron 3.5 Content Safety:free | OpenRouter | free | free | — | 128K |
| 11 | Nemotron 3 Ultra 550b A55b:free | OpenRouter | free | free | — | 1M |
| 12 | Minimax M3:free | OpenRouter | free | free | — | 1.0M |
| 13 | Nemotron 3 Nano Omni 30b A3b Reasoning:free | OpenRouter | free | free | — | 256K |
| 14 | Gemma 4 26b A4b It:free | OpenRouter | free | free | — | 262K |
| 15 | Gemma 4 31b It:free | OpenRouter | free | free | — | 262K |
| 16 | Minimax M2.7:free | OpenRouter | free | free | — | 197K |
| 17 | Nemotron 3 Super 120b A12b:free | OpenRouter | free | free | — | 262K |
| 18 | Nemotron 3.5 Lightning 30b A3b | Perplexity | $0.011 | $0.17 | $0.0011 | — |
| 19 | Gemma 4 E4B It | DeepInfra | $0.02 | $0.1 | — | 131K |
| 20 | Qwen3 4b Fp8 | Novita AI | $0.03 | $0.03 | — | 128K |
| 21 | GPT Oss 20b | OpenRouter | $0.03 | $0.13 | — | 131K |
| 22 | Qwen3.7 Flash | OpenRouter | $0.03 | $0.13 | $0.006 | 1M |
| 23 | Qwen3 8b Fp8 | Novita AI | $0.035 | $0.138 | — | 128K |
| 24 | GPT Oss 120b | OpenRouter | $0.037 | $0.17 | — | 131K |
| 25 | GPT Oss 20b | Novita AI | $0.04 | $0.15 | — | 131K |
| 26 | Gemma 4 26b A4b It | OpenRouter | $0.042 | $0.22 | — | 262K |
| 27 | Qwen Turbo | Alibaba DashScope | $0.05 | $0.2 | — | 129K |
| 28 | Qwen Turbo | Alibaba DashScope | $0.05 | $0.2 | — | 1M |
| 29 | Qwen Turbo | Alibaba DashScope | $0.05 | $0.2 | — | 1M |
| 30 | Qwen Turbo | Alibaba DashScope | $0.05 | $0.2 | — | 1M |
| 31 | GPT 5 Nano | OpenAI | $0.05 | $0.4 | $0.005 | 272K |
| 32 | GPT 5 Nano | OpenAI | $0.05 | $0.4 | $0.005 | 272K |
| 33 | GPT 5 Nano | Azure OpenAI | $0.05 | $0.4 | $0.005 | 272K |
| 34 | Nemotron 3 Nano 30B A3B | DeepInfra | $0.05 | $0.2 | $0.025 | 262K |
| 35 | Nemotron Lightning 3p5 30b A3b | Fireworks AI | $0.05 | $0.2 | $0.01 | 262K |
| 36 | GPT Oss 120b | Novita AI | $0.05 | $0.25 | — | 131K |
| 37 | Nemotron 3 Nano 30b A3b | Novita AI | $0.05 | $0.2 | — | 262K |
| 38 | GPT 5 Nano | OpenRouter | $0.05 | $0.4 | $0.005 | 272K |
| 39 | Nemotron 3 Nano 30b A3b | OpenRouter | $0.05 | $0.2 | $0.03 | 262K |
| 40 | Qwen3 30b A3b Fp8 | Cloudflare Workers AI | $0.051 | $0.335 | — | 33K |
| 41 | GPT 5 Nano | Azure OpenAI | $0.055 | $0.44 | $0.0055 | 272K |
| 42 | GLM 4.7 Flash | DeepInfra | $0.06 | $0.4 | $0.01 | 203K |
| 43 | Ling 3.0 Flash | DeepInfra | $0.06 | $0.18 | $0.012 | 131K |
| 44 | NVIDIA Nemotron 3 Nano 30B A3B | Nebius | $0.06 | $0.24 | — | 262K |
| 45 | Nemotron 3 Nano Omni | Nebius | $0.06 | $0.24 | — | 262K |
| 46 | Nemotron 3 5 Lightning | Nebius | $0.06 | $0.24 | — | 1.0M |
| 47 | Deepseek R1 0528 Qwen3 8b | Novita AI | $0.06 | $0.09 | — | 128K |
| 48 | Ling 3.0 Flash Fast | Novita AI | $0.06 | $0.18 | $0.012 | 262K |
| 49 | Ling 3.0 Flash | Novita AI | $0.06 | $0.18 | $0.012 | 262K |
| 50 | Glm 4.7 Flash | OpenRouter | $0.06 | $0.4 | $0.01 | 200K |
| 51 | Laguna Xs 2.1 | OpenRouter | $0.06 | $0.12 | $0.03 | 262K |
| 52 | Glm 4.7 Flash | Cloudflare Workers AI | $0.06 | $0.4 | — | 131K |
| 53 | Qwen3.5 Flash 02 23 | OpenRouter | $0.065 | $0.26 | — | 1M |
| 54 | Deepseek V4 Flash 0731 | OpenRouter | $0.065 | $0.18 | $0.016 | 1.3M |
| 55 | Gemma 4 26B A4B It | DeepInfra | $0.07 | $0.34 | — | 262K |
| 56 | GPT Oss 20b | Fireworks AI | $0.07 | $0.3 | $0.035 | 131K |
| 57 | Ernie 4.5 21B A3b Thinking | Novita AI | $0.07 | $0.28 | — | 131K |
| 58 | Glm 4.7 Flash | Novita AI | $0.07 | $0.4 | $0.01 | 200K |
| 59 | GPT Oss 20b | Groq | $0.075 | $0.3 | $0.037 | 131K |
| 60 | GPT Oss Safeguard 20b | Groq | $0.075 | $0.3 | $0.037 | 131K |
Other use cases
Frequently asked
› Which reasoning model is the cheapest?
Gemma 4 26b A4b It from Google Gemini currently leads this list, at $0/1M input tokens. Rankings are recomputed from the raw dataset on every refresh, so they track price cuts automatically.
› How are these rankings calculated?
Each use case applies a capability filter (context size, vision, tool calling, cache pricing) and then ranks the surviving models by the blended cost that profile actually pays. See the methodology page for the exact formulas.
› Is the cheapest model always the right choice?
No. Check the capability flags and context window, and benchmark quality on your own data — the cheapest model that fails your evals costs more than the second cheapest that passes them.