InferenceFree Tier

Free Tier

Try the gateway without credits. Free tier restricts to cheap, fast models with daily request limits.

Limits

TierDaily limit
Anonymous (no auth)5 req/day
Authenticated (zero credits)20 req/day
Paid (any credits)Unlimited

Credits change the daily cap only. The per-minute limit is set by how you authenticate, not by your balance. See Rate Limiting.

Allowed models

Free tier requests can use:

ModelProvider
openai/gpt-4o-miniOpenAI
anthropic/claude-haiku-4-5-20251001Anthropic
groq/llama-3.1-8b-instantGroq
google/gemini-2.5-flash-liteGoogle
deepseek/deepseek-chatDeepSeek
deepseek/deepseek-v4-flashDeepSeek

Blocked models

These models require credits:

  • OpenAI reasoning: o1, o3, o4 (all variants)
  • OpenAI flagship: gpt-4o, gpt-4, gpt-5 (gpt-4o-mini is allowed)
  • Anthropic flagship: claude-opus, claude-sonnet (haiku is allowed)
  • Google flagship: gemini-2.5-pro, gemini-2.5-ultra
  • xAI flagship: grok-2, grok-3

Requesting a blocked model without credits returns 402:

{
  "error": {
    "message": "Model \"gpt-4o\" requires credits. Free-tier models: openai/gpt-4o-mini, groq/llama-3.1-8b-instant, google/gemini-2.5-flash-lite, anthropic/claude-haiku-4-5-20251001, deepseek/deepseek-chat, deepseek/deepseek-v4-flash. Add credits or pick a free-tier model.",
    "type": "insufficient_funds",
    "code": "free_tier_limit"
  }
}

Response headers

When a request is rejected for free-tier reasons (402), the response reports your quota:

X-Free-Tier-Remaining: 3
X-Free-Tier-Limit: 5