Cheapest tool-calling models
Models that support function calling, ranked by blended cost — the backbone of agent loops and structured extraction.
Current leader: Gemini Exp 1114 (Google Gemini). Refreshed 2026-09-13 13:40 UTC.
| # | Model | Provider | Input $/1M | Output $/1M | Cached $/1M | Context |
|---|---|---|---|---|---|---|
| 1 | Gemini Exp 1114 | Google Gemini | free | free | — | 1.0M |
| 2 | Gemini Exp 1206 | Google Gemini | free | free | — | 2.1M |
| 3 | Gemma 3 27b It | Google Gemini | free | free | — | 131K |
| 4 | Gemma 4 26b A4b It | Google Gemini | free | free | — | 262K |
| 5 | Gemma 4 31b It | Google Gemini | free | free | — | 262K |
| 6 | Learnlm 1.5 Pro Experimental | Google Gemini | free | free | — | 33K |
| 7 | Labs Leanstral 1 5 | Mistral AI | free | free | — | 262K |
| 8 | Labs Leanstral 1 5 1 | Mistral AI | free | free | — | 262K |
| 9 | Anthropic.claude Mythos Preview | Amazon Bedrock | free | free | — | 1M |
| 10 | Deepseek Coder V2 Base | Ollama | free | free | — | 8K |
| 11 | Deepseek Coder V2 Instruct | Ollama | free | free | — | 33K |
| 12 | Deepseek Coder V2 Lite Base | Ollama | free | free | — | 8K |
| 13 | Deepseek Coder V2 Lite Instruct | Ollama | free | free | — | 33K |
| 14 | Deepseek V3.1:671b Cloud | Ollama | free | free | — | 164K |
| 15 | GPT Oss:120b Cloud | Ollama | free | free | — | 131K |
| 16 | GPT Oss:20b Cloud | Ollama | free | free | — | 131K |
| 17 | Internlm2 5 20b Chat | Ollama | free | free | — | 33K |
| 18 | Llama3.1 | Ollama | free | free | — | 8K |
| 19 | Mistral | Ollama | free | free | — | 8K |
| 20 | Mistral 7B Instruct V0.1 | Ollama | free | free | — | 8K |
| 21 | Mistral 7B Instruct V0.2 | Ollama | free | free | — | 33K |
| 22 | Mistral Large Instruct 2407 | Ollama | free | free | — | 66K |
| 23 | Mixtral 8x22B Instruct V0.1 | Ollama | free | free | — | 66K |
| 24 | Mixtral 8x7B Instruct V0.1 | Ollama | free | free | — | 33K |
| 25 | Qwen3 Coder:480b Cloud | Ollama | free | free | — | 262K |
| 26 | Auto | OpenRouter | free | free | — | 2M |
| 27 | Free | OpenRouter | free | free | — | 200K |
| 28 | Nemotron 3.5 Lightning:free | OpenRouter | free | free | — | 1M |
| 29 | Laguna S 2.1:free | OpenRouter | free | free | — | 262K |
| 30 | Laguna Xs 2.1:free | OpenRouter | free | free | — | 262K |
| 31 | Glm 5.2:free | OpenRouter | free | free | — | 256K |
| 32 | Nemotron 3 Ultra 550b A55b:free | OpenRouter | free | free | — | 1M |
| 33 | Minimax M3:free | OpenRouter | free | free | — | 1.0M |
| 34 | Nemotron 3 Nano Omni 30b A3b Reasoning:free | OpenRouter | free | free | — | 256K |
| 35 | Gemma 4 26b A4b It:free | OpenRouter | free | free | — | 262K |
| 36 | Gemma 4 31b It:free | OpenRouter | free | free | — | 262K |
| 37 | Minimax M2.7:free | OpenRouter | free | free | — | 197K |
| 38 | Nemotron 3 Super 120b A12b:free | OpenRouter | free | free | — | 262K |
| 39 | Llama 3.3 70B Instruct Turbo Free | Together AI | free | free | — | — |
| 40 | Qwen2.5 Coder 7B | Nebius | $0.01 | $0.03 | — | 33K |
| 41 | Llama 3.2 3B Instruct | DeepInfra | $0.02 | $0.02 | — | 131K |
| 42 | Mistral Nemo Instruct 2407 | DeepInfra | $0.019 | $0.03 | — | 131K |
| 43 | Mistral Nemo | OpenRouter | $0.019 | $0.03 | — | 131K |
| 44 | Meta Llama 3.1 8B Instruct Turbo | DeepInfra | $0.02 | $0.04 | — | 131K |
| 45 | Meta Llama 3.1 8B Instruct | Nebius | $0.02 | $0.06 | — | 128K |
| 46 | Qwen3 4b Fp8 | Novita AI | $0.03 | $0.03 | — | 128K |
| 47 | Meta Llama 3.1 8B Instruct | DeepInfra | $0.03 | $0.05 | — | 131K |
| 48 | Llama 3.2 3b Instruct | Novita AI | $0.03 | $0.05 | — | 33K |
| 49 | Meta Llama 3 8B Instruct | DeepInfra | $0.03 | $0.06 | — | 8K |
| 50 | Gemma 4 E4B It | DeepInfra | $0.02 | $0.1 | — | 131K |
| 51 | Granite 4.0 H Micro | Cloudflare Workers AI | $0.017 | $0.112 | — | 131K |
| 52 | L3 8B Stheno V3.2 | Novita AI | $0.05 | $0.05 | — | 8K |
| 53 | Nemotron 3.5 Lightning 30b A3b | Perplexity | $0.011 | $0.17 | $0.0011 | — |
| 54 | GPT Oss 20b | OpenRouter | $0.03 | $0.13 | — | 131K |
| 55 | Qwen3.7 Flash | OpenRouter | $0.03 | $0.13 | $0.006 | 1M |
| 56 | GPT Oss 20b | DeepInfra | $0.03 | $0.14 | — | 131K |
| 57 | Mistral Small 24B Instruct 2501 | DeepInfra | $0.05 | $0.08 | — | 33K |
| 58 | Llama 3.1 8b Instant | Groq | $0.05 | $0.08 | — | 131K |
| 59 | Gemma 7b It | Groq | $0.05 | $0.08 | — | 8K |
| 60 | Llama 3.1 8b Instruct | OpenRouter | $0.05 | $0.08 | $0.025 | 131K |
Other use cases
Frequently asked
› Which model is cheapest for tool calling and agents?
Gemini Exp 1114 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.