Code · best for
Best AI model for Code Documentation (2026)
Writing clear docstrings and READMEs that match the code. Ranked from 346 live models on the OpenRouter catalog, weighted for context window, low cost, reasoning quality.
| # | Model | Score | In / 1M | Out / 1M | Context | |
|---|---|---|---|---|---|---|
| 1 | Auto Routeropenrouter/auto | 400132 | $-1000000.00 | $-1000000.00 | 2,000,000 | Try → |
| 2 | Pareto Code Routeropenrouter/pareto-code | 400120 | $-1000000.00 | $-1000000.00 | 200,000 | Try → |
| 3 | Body Builder (beta)openrouter/bodybuilder | 400117 | $-1000000.00 | $-1000000.00 | 128,000 | Try → |
| 4 | Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | 131 | $0.07 | $0.26 | 1,000,000 | Try → |
| 5 | xAI: Grok 4.1 Fastx-ai/grok-4.1-fast | 131 | $0.20 | $0.50 | 2,000,000 | Try → |
| 6 | Google: Gemini 2.5 Flash Lite Preview 09-2025google/gemini-2.5-flash-lite-preview-09-2025 | 131 | $0.10 | $0.40 | 1,048,576 | Try → |
| 7 | xAI: Grok 4 Fastx-ai/grok-4-fast | 131 | $0.20 | $0.50 | 2,000,000 | Try → |
| 8 | OpenAI: GPT-5 Nanoopenai/gpt-5-nano | 131 | $0.05 | $0.40 | 400,000 | Try → |
| 9 | Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite | 131 | $0.10 | $0.40 | 1,048,576 | Try → |
| 10 | OpenAI: GPT-5.4 Nanoopenai/gpt-5.4-nano | 131 | $0.20 | $1.25 | 400,000 | Try → |
| 11 | Google: Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview | 131 | $0.25 | $1.50 | 1,048,576 | Try → |
| 12 | Qwen: Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15 | 131 | $0.26 | $1.56 | 1,000,000 | Try → |
| 13 | OpenAI: GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-mini | 131 | $0.25 | $2.00 | 400,000 | Try → |
| 14 | OpenAI: GPT-5 Miniopenai/gpt-5-mini | 131 | $0.25 | $2.00 | 400,000 | Try → |
| 15 | Qwen: Qwen3.6 Plusqwen/qwen3.6-plus | 131 | $0.33 | $1.95 | 1,000,000 | Try → |
How we ranked these
For Code Documentation, we weight models on context window, low cost, reasoning quality. Higher means better. Scores combine OpenRouter's model metadata (context length, modality support, tool calling, structured output, reasoning capability) with public pricing. See full methodology →
Related tasks
Code
Best for SQL Generation
Writing correct, performant SQL from natural-language prompts.
Code
Best for Code Review
Spotting bugs, security issues, and style problems in pull requests.
Code
Best for Code Completion
Inline IDE-style autocomplete that has to feel instant.
Code
Best for Code Refactoring
Safely restructuring an existing codebase across many files.
Code
Best for Bug Fixing
Diagnosing root cause and producing a working patch.
Code
Best for Unit Test Generation
Generating thorough test suites for existing functions.