Video · best for
Best AI model for Video Summarization (2026)
Extracting key moments and summaries from video. Ranked from 346 live models on the OpenRouter catalog, weighted for video input, context window, reasoning quality.
| # | Model | Score | In / 1M | Out / 1M | Context | |
|---|---|---|---|---|---|---|
| 1 | Qwen: Qwen3.6 Plusqwen/qwen3.6-plus | 139 | $0.33 | $1.95 | 1,000,000 | Try → |
| 2 | Google: Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview | 139 | $0.25 | $1.50 | 1,048,576 | Try → |
| 3 | Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | 139 | $0.07 | $0.26 | 1,000,000 | Try → |
| 4 | Google: Gemini 3.1 Pro Preview Custom Toolsgoogle/gemini-3.1-pro-preview-customtools | 139 | $2.00 | $12.00 | 1,048,576 | Try → |
| 5 | Google: Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | 139 | $2.00 | $12.00 | 1,048,576 | Try → |
| 6 | Qwen: Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15 | 139 | $0.26 | $1.56 | 1,000,000 | Try → |
| 7 | Google: Gemini 3 Flash Previewgoogle/gemini-3-flash-preview | 139 | $0.50 | $3.00 | 1,048,576 | Try → |
| 8 | Amazon: Nova 2 Liteamazon/nova-2-lite-v1 | 139 | $0.30 | $2.50 | 1,000,000 | Try → |
| 9 | Google: Gemini 2.5 Flash Lite Preview 09-2025google/gemini-2.5-flash-lite-preview-09-2025 | 139 | $0.10 | $0.40 | 1,048,576 | Try → |
| 10 | Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite | 139 | $0.10 | $0.40 | 1,048,576 | Try → |
| 11 | Google: Gemini 2.5 Flashgoogle/gemini-2.5-flash | 139 | $0.30 | $2.50 | 1,048,576 | Try → |
| 12 | Google: Gemini 2.5 Progoogle/gemini-2.5-pro | 139 | $1.25 | $10.00 | 1,048,576 | Try → |
| 13 | Google: Gemini 2.5 Pro Preview 05-06google/gemini-2.5-pro-preview-05-06 | 139 | $1.25 | $10.00 | 1,048,576 | Try → |
| 14 | Auto Routeropenrouter/auto | 139 | $-1000000.00 | $-1000000.00 | 2,000,000 | Try → |
| 15 | Google: Gemma 4 26B A4B (free)google/gemma-4-26b-a4b-it:free | 133 | Free | Free | 262,144 | Try → |
How we ranked these
For Video Summarization, we weight models on video input, context window, 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 →