Tool Calls · Usage rankings

Tool Calls · Tool-using requests

Observed tokens

Observed token floor for daily Top-50 requests recording at least one tool call, not the number of tool calls.

7-day observed tokens200.2T

Other outside Top 504.5%

1
deepseek/deepseek-v4.1-flash-20261017deepseek/deepseek-v4.1-flash-20261017
53.2T26.6%
2
Tencent: Hy4tencent/hy4-20261104
20.2T10.1%
3
deepseek/deepseek-v4.1-flash-20260910deepseek/deepseek-v4.1-flash-20260910
16.3T8.1%
4
z-ai/glm-5.3-flash-20260826z-ai/glm-5.3-flash-20260826
12T6.0%
5
openai/gpt-6-luna-20260922openai/gpt-6-luna-20260922
7.2T3.6%
6
StepFun: Step 5 Previewstepfun/step-5-preview-20261008
6.9T3.4%
7
anthropic/claude-opus-5.5-20260921anthropic/claude-opus-5.5-20260921
6.6T3.3%
8
Crouton Alphastealth/crouton-alpha
4.5T2.3%

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