Skip to content

LLM usage analytics

Token consumption and requests of our locally run models, broken down per month and model – updated continuously.

  • 2026
  • January
  • February
  • March
  • April
  • May
  • June
  • July
  • August
  • September
  • October
  • November
  • December
  • deepseek-ocr
  • deepseek-v4:flash
  • gemma4:12b
  • gemma4:31b
  • gemma4:e4b
  • kimi-linear:48b
  • qwen3-coder:30b
  • qwen3-embedding:4b
  • qwen3-embedding:8b
  • qwen3-vl:32b
  • qwen3-vl:8b
  • qwen3.5:122b
  • qwen3.5:4b
  • qwen3.5:9b
  • qwen3.6:27b
  • qwen3.6:35b
  • qwen3.6:35b-a3b
  • Other
23.2M
October 2026
Input 23.1M
Output 17'224
507.4M
2026
Input 498.7M
Output 8.7M
507.4M
Total
Input 498.7M
Output 8.7M

Last updated on 21.10.2026 1:00 am.

Details

Details
Period Total tokens Requests
October 2026 23'157'569 1'643
September 2026 61'219'497 3'760
August 2026 97'120'270 8'751
July 2026 294'532'294 11'148
June 2026 30'315'709 4'294
May 2026 1'094'465 165
Total 507'439'804 29'761
Back to our LLMs

Discover more

Expertise Four areas, one path.