API usage
The 20 open models served most on OpenRouter, tokens per day over 30 days.
All of them, tokens per day
Last 7 days 56.2T tokens −5% compared with the 7 days before- 1

DeepSeek-V4.1-FlashDeepSeek
15.9T tokens−6% compared with the 7 days before - 2
GLM-5.3-FlashZ.ai11.5T tokens+2% compared with the 7 days before - 3
GLM-5.3Z.ai3.6T tokens−1% compared with the 7 days before - 4

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16NVIDIA
3.4T tokens−8% compared with the 7 days before - 5

Kimi-K3.1-ProMoonshot AI
3.4T tokens−23% compared with the 7 days before - 6

DeepSeek-V4-Flash-0731DeepSeek
3.1T tokens+1% compared with the 7 days before - 7

NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA
3.1T tokens−4% compared with the 7 days before - 8

DeepSeek-V4-FlashDeepSeek
2T tokens−10% compared with the 7 days before - 9
Inkling-2-SmallThinking Machines1.6T tokens+1065% compared with the 7 days before - 10

Hy3Tencent
1.4T tokens−36% compared with the 7 days before - 11

Kimi-K3Moonshot AI
1.2T tokens−25% compared with the 7 days before - 12

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA
1.1T tokens0% compared with the 7 days before - 13
GLM-5.2Z.ai955.5B tokens+5% compared with the 7 days before - 14
MiMo-V2.6-Pro-RLXiaomi MiMo911.4B tokens−20% compared with the 7 days before - 15

Qwen3.8-27BQwen
826.8B tokens+12% compared with the 7 days before - 16

DeepSeek-V4-ProDeepSeek
556.2B tokens+1% compared with the 7 days before - 17

MiniMax-M3MiniMax
508.5B tokens−23% compared with the 7 days before - 18

gemma-4-26B-A4B-itGoogle
447.3B tokens+12% compared with the 7 days before - 19

gemma-4-31B-itGoogle
366.2B tokens−19% compared with the 7 days before - 20
gpt-oss-120bOpenAI80.9B tokens−73% compared with the 7 days before
Source: OpenRouter (openrouter.ai/rankings), as of Nov 17, 2026.