Skip to main content
Rate limits vary by model and tier. The default limits below are a useful reference, but the /api_keys/rate_limits API endpoint is the canonical way to fetch your current limits. You can check your exact limits anytime:

View Your Limits

Interactive playground

Rate Limit Logs

See which requests hit limits

​
Default Limits

​
Text Models

Text models are grouped into tiers based on size. Each model card on the Models page displays its tier badge.
XS qwen3-4b llama-3.2-3bS mistral-31-24b venice-uncensoredM zai-org-glm-5 qwen3-next-80b google-gemma-3-27b-itL qwen3-235b-a22b-instruct-2507 qwen3-235b-a22b-thinking-2507 deepseek-ai-DeepSeek-R1 grok-41-fast kimi-k2-thinking gemini-3-pro-preview hermes-3-llama-3.1-405b qwen3-coder-480b-a35b-instruct zai-org-glm-4.7 openai-gpt-oss-120b

​
Other Models

​
Handling Errors

Failed requests (500, 503, 429) should be retried with exponential backoff. For 429 errors specifically, check the x-ratelimit-reset-requests header for the exact Unix timestamp when you can retry. Most HTTP libraries have built-in retry mechanisms that handle this automatically.

​
Abuse Protection

If you generate more than 20 failed requests in 30 seconds, the API will block further requests for 30 seconds:

​
Response Headers

Every response includes these headers:

​
Partner Tier

Partners get significantly higher rate limits: If you’re consistently hitting your rate limits and your usage patterns show sustained demand over time, reach out to discuss partner access: [email protected]. Partner tier limits can be adjusted based on your specific needs.