Writing · best for
Best AI model for Long-Document Summarization (2026)
Summarizing books, transcripts, court filings. Ranked from 346 live models on the OpenRouter catalog, weighted for context window, reasoning quality, low cost.
| # | Model | Score | In / 1M | Out / 1M | Context | |
|---|---|---|---|---|---|---|
| 1 | Auto Routeropenrouter/auto | 200138 | $-1000000.00 | $-1000000.00 | 2,000,000 | Try → |
| 2 | Pareto Code Routeropenrouter/pareto-code | 200118 | $-1000000.00 | $-1000000.00 | 200,000 | Try → |
| 3 | Body Builder (beta)openrouter/bodybuilder | 200113 | $-1000000.00 | $-1000000.00 | 128,000 | Try → |
| 4 | Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | 138 | $0.07 | $0.26 | 1,000,000 | Try → |
| 5 | OpenAI: GPT-5 Nanoopenai/gpt-5-nano | 138 | $0.05 | $0.40 | 400,000 | Try → |
| 6 | OpenAI: GPT-5.4 Nanoopenai/gpt-5.4-nano | 137 | $0.20 | $1.25 | 400,000 | Try → |
| 7 | xAI: Grok 4.1 Fastx-ai/grok-4.1-fast | 137 | $0.20 | $0.50 | 2,000,000 | Try → |
| 8 | Google: Gemini 2.5 Flash Lite Preview 09-2025google/gemini-2.5-flash-lite-preview-09-2025 | 137 | $0.10 | $0.40 | 1,048,576 | Try → |
| 9 | xAI: Grok 4 Fastx-ai/grok-4-fast | 137 | $0.20 | $0.50 | 2,000,000 | Try → |
| 10 | Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite | 137 | $0.10 | $0.40 | 1,048,576 | Try → |
| 11 | Qwen: Qwen3.6 Plusqwen/qwen3.6-plus | 137 | $0.33 | $1.95 | 1,000,000 | Try → |
| 12 | Google: Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview | 137 | $0.25 | $1.50 | 1,048,576 | Try → |
| 13 | Qwen: Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15 | 137 | $0.26 | $1.56 | 1,000,000 | Try → |
| 14 | OpenAI: GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-mini | 137 | $0.25 | $2.00 | 400,000 | Try → |
| 15 | OpenAI: GPT-5 Miniopenai/gpt-5-mini | 137 | $0.25 | $2.00 | 400,000 | Try → |
How we ranked these
For Long-Document Summarization, we weight models on context window, reasoning quality, low cost. 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
Writing
Best for Short-Form Summarization
TL;DRs of articles and emails at scale.
Writing
Best for Blog Post Writing
Drafting publishable long-form articles.
Writing
Best for Marketing Copy
Headlines, ad copy, and brand voice.
Writing
Best for Social Media Posts
Tweets, LinkedIn posts, captions in the right voice.
Writing
Best for Email Drafting
Cold emails, replies, and outreach at the right tone.
Writing
Best for Creative Writing
Fiction, poetry, screenplays.