Service activity
AI Router Traffic Statistics
A live picture of what actually flows through our gateway — token volume, model mix, provider market share, latency percentiles and workload categories. Refreshed every day.
Tokens processed
181.65B
-3.9%vs previous period
API requests
31.3M
-4.6%vs previous period
Active models
15
Active providers
14
Daily token volume
Aggregate across all models and providers
Provider market share
Share of total token traffic by provider
- google28.5%
- anthropic27.9%
- openai22.7%
- deepseek8.4%
- mistral4.4%
- cerebras3.5%
- xai2.4%
- moonshot2.3%
Workload categories
How our customers actually use the gateway
- Programming63.5% · 23.63B
- General25.4% · 9.46B
- Reasoning6.5% · 2.43B
- Agents / Tool use4.6% · 1.70B
Top models
Ranked by token volume in the selected window
| # | Model | Provider | Requests | Tokens | Share |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 4.6 | anthropic | 830K | 6.95B | 21.4% |
| 2 | Gemini 3 Pro | 558K | 5.25B | 16.2% | |
| 3 | GPT-5.4 | openai | 692K | 3.66B | 11.3% |
| 4 | Gemini 3 Flash | 491K | 3.64B | 11.2% | |
| 5 | GPT-5.5 | openai | 463K | 2.44B | 7.5% |
| 6 | Claude Opus 4.7 | anthropic | 302K | 2.04B | 6.3% |
| 7 | DeepSeek V3.2 | deepseek | 352K | 1.88B | 5.8% |
| 8 | DeepSeek R1.1 | deepseek | 168K | 1.00B | 3.1% |
| 9 | Gemini 3 Flash-Lite | 267K | 929.50M | 2.9% | |
| 10 | Mistral Large 3 | mistral | 152K | 919.59M | 2.8% |
| 11 | Llama 4 Scout (Cerebras) | cerebras | 226K | 876.99M | 2.7% |
| 12 | o4-mini | openai | 155K | 853.81M | 2.6% |
| 13 | Kimi K2 | moonshot | 106K | 792.76M | 2.4% |
| 14 | Claude Haiku 4.5 | anthropic | 138K | 608.72M | 1.9% |
| 15 | Command A | cohere | 118K | 607.68M | 1.9% |
Provider response times
Time-to-first-token (ms) percentiles
| Provider | p50 | p90 | p99 | Tokens/sec |
|---|---|---|---|---|
| cerebras | 117 | 215 | 373 | 1815 |
| groq | 174 | 310 | 543 | 606 |
| fireworks | 377 | 716 | 1373 | 172 |
| deepinfra | 421 | 801 | 1540 | 157 |
| mistral | 428 | 795 | 1549 | 94 |
| together | 446 | 832 | 1583 | 161 |
| 468 | 887 | 1675 | 138 | |
| openai | 510 | 941 | 1785 | 106 |
| cohere | 530 | 962 | 1787 | 98 |
| xai | 563 | 1086 | 2051 | 93 |
| deepseek | 657 | 1237 | 2243 | 60 |
| anthropic | 802 | 1460 | 2715 | 81 |
| moonshot | 847 | 1464 | 2350 | 60 |
| perplexity | 892 | 1624 | 2827 | 66 |
All values are aggregated across the gateway. Individual request content is never exposed. Refreshed every 30 minutes.
Put AI to work for your company
Tell us what you want to achieve. We will help you choose models and a plan.
Connect your company