Context Length · Usage rankings

Context Length · 10K bucket

Observed tokens

Observed token floor for daily Top-50 requests in the 10K context bucket, not request count or maximum model context.

7-day observed tokens14.4T

Other outside Top 5011.0%

1
TypeSafe: Jev 1.13typesafe/jev-1.13-20260917
1.7T11.6%
2
TypeSafe: Jev 1.14typesafe/jev-1.14-20261014
1.1T7.8%
3
openai/gpt-6-luna-20260922openai/gpt-6-luna-20260922
1.1T7.5%
4
deepseek/deepseek-v4.1-flash-20261017deepseek/deepseek-v4.1-flash-20261017
929.6B6.5%
5
DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash-20260423
747B5.2%
6
deepseek/deepseek-v4.1-flash-20260910deepseek/deepseek-v4.1-flash-20260910
736.1B5.1%
7
deepseek/deepseek-v4-flash-20260731deepseek/deepseek-v4-flash-20260731
704.1B4.9%
8
z-ai/glm-5.3-flash-20260826z-ai/glm-5.3-flash-20260826
566.5B3.9%

Scope and sources

LastAI uses documented stable APIs only. The 10K context bucket, tool-using requests, and image-input activity are shown as observed token floors. Korean or Python-specific tags, tool-call counts, and image counts lack stable APIs, so proxies are separated and never used in a composite score.

Source: OpenRouter (openrouter.ai/rankings), as of 2026-11-12T05:20:08.915Z.

Methodology · external sources