modelgrep

Most-used AI models for summarization

Match · Updated 2026-08-04

gpt-oss-120b is the most-used model for summarization on OpenRouter, handling 15.9% of requests classified as summarization over the last 7 days.

2.7%of all requests
1.7%of all tokens
7dwindow

This ranks models by how often they are actually chosen for summarization in production traffic, not by benchmark score. Adoption reflects price, latency and availability as much as raw capability — which is exactly why it often disagrees with the benchmark leaderboards, and why it is worth reading alongside them.

#ModelRequest shareToken shareInput /MContext
1openai logogpt-oss-120b15.9%15.8%$0.037131K
2deepseek logoDeepSeek V4 Flash 04239.1%7.8%$0.1401.0M
3ILing-2.6-flash6.0%2.1%$0.010262K
4google logoGemini 2.5 Flash5.9%1.7%$0.3001.0M
5google logoGemini 2.5 Flash Lite5.6%2.0%$0.1001.0M
6google logoGemini 3 Flash Preview4.1%8.8%$0.5001.0M
7openai logoGPT-5.6 Luna3.7%3.8%$0.1001.1M
8google logoGemma 4 26B A4B 3.1%1.3%$0.070262K
9anthropic logoClaude Haiku 4.53.0%1.1%$1.00200K
10google logoGemini 3.1 Flash Lite2.9%0.90%$0.2501.0M

Reading the two columns together: Gemini 3 Flash Preview takes a noticeably larger share of tokens than of requests — meaning it is being used for the longer, heavier summarization jobs rather than quick one-shot calls.

Frequently asked

What is the most-used AI model for summarization?

gpt-oss-120b is the most-used model for summarization on OpenRouter, handling 15.9% of requests classified as summarization over the last 7 days. It is followed by DeepSeek V4 Flash 0423 (9.1%) and Ling-2.6-flash (6.0%).

Is this a benchmark ranking?

No. This ranks by how often each model is actually chosen for summarization in production traffic through OpenRouter — real-world adoption, which reflects price and availability as much as capability. For capability-based rankings, see the benchmark leaderboards.

How much of all AI traffic is summarization?

Summarization accounts for 2.7% of classified requests and 1.7% of classified tokens on OpenRouter over the trailing 7 days.

Other tasks

Source: OpenRouter (openrouter.ai/rankings), as of 2026-08-04. Shares are of classified, sampled traffic over a trailing 7-day window; absolute volumes are not published.