api.rate_limit.tokens_per_minute

Tokens per minute

Maximum tokens processed per minute

unit: tokens/minute
providers: 3
facts: 4
highest: Groq · 300,000
lowest: Groq · 6,000

provider	key	value	plan	status	verified	source
Anthropic	api.rate_limit.tokens_per_minute	40,000 tokens/minute“Tier 1 input tokens per minute”	api/standard	stale	2026-10-04	Anthropic models overview
Groq	api.rate_limit.tokens_per_minute	6,000 tokens/minute“6,000 tokens per minute on the free tier”	api/free	stale	2026-10-02	GroqCloud rate limits
Groq	api.rate_limit.tokens_per_minute	300,000 tokens/minute“300,000 tokens per minute on the developer tier”	api/developer	stale	2026-10-02	GroqCloud rate limits
OpenAI	api.rate_limit.tokens_per_minute	30,000 tokens/minute“Tier 1 token-per-minute limit”	api/standard	verified	2026-10-06	OpenAI models

Agent view

GET /api/public/v1/keys/api.rate_limit.tokens_per_minute

{
  "key": "api.rate_limit.tokens_per_minute",
  "unit": "tokens/minute",
  "values": [
    {
      "provider": "anthropic",
      "plan": "api/standard",
      "value": 40000,
      "status": "stale",
      "source": "https://docs.anthropic.com/en/docs/about-claude/models"
    },
    {
      "provider": "groq",
      "plan": "api/free",
      "value": 6000,
      "status": "stale",
      "source": "https://console.groq.com/docs/rate-limits"
    },
    {
      "provider": "groq",
      "plan": "api/developer",
      "value": 300000,
      "status": "stale",
      "source": "https://console.groq.com/docs/rate-limits"
    },
    {
      "provider": "openai",
      "plan": "api/standard",
      "value": 30000,
      "status": "verified",
      "source": "https://platform.openai.com/docs/models"
    }
  ]
}