Back to Dashboard
Total Requests
60.69M
Total Tokens
1.96T
Total Cost
$806.02K
Cache Rate
0.3%
Model Usage Over Time
Model Breakdown
| Model | Requests | Share |
|---|---|---|
| google/gemini-3.7-flash | 19.38M | 31.9% |
| google/gemini-2.5-flash | 7.42M | 12.2% |
| openai/gpt-5.6-luna | 3.27M | 5.4% |
| qwen/qwen3.8-max | 2.88M | 4.7% |
| nvidia/nemotron-3-ultra-550b-a55b | 2.49M | 4.1% |
| xiaomi/mimo-v2.5 | 2.29M | 3.8% |
| google/gemini-3.6-flash | 2.13M | 3.5% |
| google/gemini-3-flash-preview | 2.12M | 3.5% |
| typesafe/jev-1.13 | 1.63M | 2.7% |
| deepseek/deepseek-v4-flash-0731 | 1.49M | 2.4% |
| google/gemini-embedding-001 | 1.22M | 2.0% |
| meta/muse-spark-1.3 | 1.12M | 1.8% |
| deepseek/deepseek-v4-pro | 1.07M | 1.8% |
| moonshotai/kimi-k3 | 1.06M | 1.7% |
| anthropic/claude-sonnet-5 | 704.62K | 1.2% |
| google/gemini-3.8-flash | 642.69K | 1.1% |
| google/gemini-3.1-flash-lite | 591.01K | 1.0% |
| deepseek/deepseek-v4-flash | 532.84K | 0.9% |
| tencent/hy3 | 512.84K | 0.8% |
| minimax/minimax-m3 | 494.71K | 0.8% |