Skip to content
Refreshed daily

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
144.05B
+13.1%vs previous period
API requests
26.7M
+9.0%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

  • anthropic28.4%
  • google28.0%
  • openai22.6%
  • deepseek8.6%
  • mistral4.1%
  • cerebras3.3%
  • xai2.5%
  • moonshot2.4%

Workload categories

How our customers actually use the gateway

  • Programming62.7% · 19.76B
  • General26.4% · 8.31B
  • Reasoning6.7% · 2.10B
  • Agents / Tool use4.3% · 1.34B

Top models

Ranked by token volume in the selected window

#ModelProviderRequestsTokensShare
1
Claude Sonnet 4.6
anthropic760K5.87B21.2%
2
Gemini 3 Pro
google468K4.31B15.6%
3
Gemini 3 Flash
google459K3.13B11.3%
4
GPT-5.4
openai630K3.03B11.0%
5
GPT-5.5
openai426K2.07B7.5%
6
Claude Opus 4.7
anthropic288K1.80B6.5%
7
DeepSeek V3.2
deepseek320K1.61B5.8%
8
DeepSeek R1.1
deepseek166K909.32M3.3%
9
Gemini 3 Flash-Lite
google244K791.00M2.9%
10
o4-mini
openai154K766.94M2.8%
11
Mistral Large 3
mistral131K727.55M2.6%
12
Llama 4 Scout (Cerebras)
cerebras197K714.68M2.6%
13
Kimi K2
moonshot99K700.29M2.5%
14
Claude Haiku 4.5
anthropic166K674.74M2.4%
15
GPT-5.4 Mini
openai204K556.42M2.0%

Provider response times

Time-to-first-token (ms) percentiles

Providerp50p90p99Tokens/sec
cerebras
1232273921744
groq
176313548599
fireworks
3847281396187
mistral
397738144095
deepinfra
3977571455162
together
4348091540162
google
4708901681145
cohere
521945175692
openai
5299781854104
xai
5571074202989
deepseek
6761273230763
anthropic
7961449269582
perplexity
8591563272264
moonshot
9111573252558

All values are aggregated across the gateway. Individual request content is never exposed. Refreshed every 30 minutes.