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
41.41B
+137.7%vs previous period
API requests
8.5M
+129.5%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

  • anthropic32.4%
  • google26.8%
  • openai22.2%
  • deepseek7.9%
  • mistral4.3%
  • cerebras2.6%
  • moonshot2.0%
  • xai1.8%

Workload categories

How our customers actually use the gateway

  • Programming65.6% · 5.93B
  • General24.4% · 2.21B
  • Reasoning6.5% · 583.52M
  • Agents / Tool use3.5% · 316.63M

Top models

Ranked by token volume in the selected window

#ModelProviderRequestsTokensShare
1
Claude Sonnet 4.6
anthropic266K1.86B23.2%
2
Gemini 3 Pro
google160K1.25B15.6%
3
GPT-5.4
openai231K979.06M12.2%
4
Gemini 3 Flash
google139K828.22M10.3%
5
Claude Opus 4.7
anthropic116K654.29M8.1%
6
GPT-5.5
openai115K487.06M6.1%
7
DeepSeek V3.2
deepseek92K394.29M4.9%
8
DeepSeek R1.1
deepseek56K274.08M3.4%
9
Claude Haiku 4.5
anthropic64K226.23M2.8%
10
o4-mini
openai48K204.73M2.5%
11
Mistral Large 3
mistral40K200.34M2.5%
12
Gemini 3 Flash-Lite
google68K191.38M2.4%
13
Kimi K2
moonshot27K167.85M2.1%
14
Llama 4 Scout (Cerebras)
cerebras51K165.76M2.1%
15
GPT-5.4 Mini
openai62K144.71M1.8%

Provider response times

Time-to-first-token (ms) percentiles

Providerp50p90p99Tokens/sec
cerebras
1152123651766
groq
180320561564
fireworks
3817231387174
deepinfra
4067721485161
mistral
422785153094
together
4247901503162
google
4738971694139
openai
5169531808105
xai
5481058200090
cohere
5551007187198
deepseek
6931306236761
anthropic
7141300241881
moonshot
8661497240358
perplexity
8941628283563

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