Back to Dashboard
Total Requests
156.80M
Total Tokens
4.22T
Total Cost
$2.25M
Cache Rate
1.1%
Model Usage Over Time
Model Breakdown
| Model | Requests | Share |
|---|---|---|
| google/gemini-3.7-flash | 20.29M | 12.9% |
| google/gemini-3.5-flash | 11.91M | 7.6% |
| google/gemini-2.5-flash | 11.75M | 7.5% |
| deepseek/deepseek-v4-pro | 10.35M | 6.6% |
| google/gemini-3.6-flash | 9.80M | 6.3% |
| deepseek/deepseek-v4-flash | 9.64M | 6.2% |
| google/gemini-3-flash-preview | 6.05M | 3.9% |
| openai/gpt-5.6-luna | 4.55M | 2.9% |
| anthropic/claude-sonnet-5 | 4.17M | 2.7% |
| xiaomi/mimo-v2.5 | 3.51M | 2.2% |
| anthropic/claude-haiku-4.5 | 3.39M | 2.2% |
| z-ai/glm-5.2 | 3.27M | 2.1% |
| google/gemini-3.1-flash-lite | 3.19M | 2.0% |
| nvidia/nemotron-3-ultra-550b-a55b | 3.08M | 2.0% |
| qwen/qwen3.8-max | 2.58M | 1.6% |
| anthropic/claude-sonnet-4.6 | 1.83M | 1.2% |
| google/gemini-embedding-001 | 1.79M | 1.1% |
| typesafe/jev-1.13 | 1.63M | 1.0% |
| openai/gpt-4o-mini | 1.60M | 1.0% |
| deepseek/deepseek-v4-flash-0731 | 1.29M | 0.8% |