For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Fork this repoGet a demo
  • Docs
    • Welcome
    • Quickstart
    • Concepts
    • Search
    • MCP Server
    • CLI
    • Agent Skills
    • Connect
    • Add New Connector
    • Rate Limits
  • API Reference
LogoLogo
Fork this repoGet a demo
On this page
  • Limits by Plan
  • Rate Limit Headers
  • Rate Limit Exceeded
Docs

Rate Limits

Was this page helpful?
Edit this page
Previous

LlamaIndex

Connect your LlamaIndex agent to Airweave for semantic search across all your synced data sources.
Next
Built with

API requests are rate-limited per organization based on your billing plan. Limits are enforced per minute using a sliding window.

Limits by Plan

PlanRequests per Minute
Developer10
Pro100
Team250
EnterpriseUnlimited

Rate Limit Headers

All API responses include rate limit information:

RateLimit-Limit: 100
RateLimit-Remaining: 95
RateLimit-Reset: 1729012345
  • RateLimit-Limit: Maximum requests per minute
  • RateLimit-Remaining: Requests left in current window
  • RateLimit-Reset: Unix timestamp when limit resets

Rate Limit Exceeded

When you exceed your limit, you’ll receive a 429 Too Many Requests response with a Retry-After header indicating seconds until you can retry.

1{
2 "detail": "Rate limit exceeded. Try again in 42 seconds."
3}