Back to Dashboard
Total Requests
49.28M
Total Tokens
2.15T
Total Cost
$807.16K
Cache Rate
0.4%
Model Usage Over Time
Model Breakdown
| Model | Requests | Share |
|---|---|---|
| google/gemini-3.7-flash | 20.80M | 42.2% |
| google/gemini-2.5-flash | 3.96M | 8.0% |
| openai/gpt-5.6-luna | 3.24M | 6.6% |
| google/gemini-3.6-flash | 2.93M | 5.9% |
| xiaomi/mimo-v2.5 | 2.42M | 4.9% |
| nvidia/nemotron-3-ultra-550b-a55b | 2.16M | 4.4% |
| qwen/qwen3.8-max | 2.02M | 4.1% |
| anthropic/claude-sonnet-5 | 1.55M | 3.1% |
| google/gemini-3-flash-preview | 1.53M | 3.1% |
| google/gemini-embedding-001 | 1.20M | 2.4% |
| moonshotai/kimi-k3 | 1.12M | 2.3% |
| deepseek/deepseek-v4-pro | 891.11K | 1.8% |
| google/gemini-3.8-flash | 853.14K | 1.7% |
| deepseek/deepseek-v4-flash | 830.45K | 1.7% |
| minimax/minimax-m3 | 817.90K | 1.7% |
| anthropic/claude-haiku-4.5 | 802.54K | 1.6% |
| x-ai/grok-4.6 | 721.93K | 1.5% |
| z-ai/glm-5.2 | 663.73K | 1.3% |
| gpt-5-nano | 532.39K | 1.1% |
| google/gemini-3.1-flash-lite | 481.42K | 1.0% |