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.
Book a demoLog in
DocumentationAPI ReferenceModel VersioningChangelog
DocumentationAPI ReferenceModel VersioningChangelog
    • Studio
    • Support
    • Benchmarks
    • Status
  • Getting Started
    • Overview
    • API Quickstart
    • Dashboard Quickstart
    • Agent Quickstart
  • Dev Tools
    • SDKs
    • CLI
  • Capabilities
      • Supported File Types
      • How Credits Work
      • Rate Limits
      • Async Processing
      • Batch Processing
      • User Roles and Permissions
      • Test Environment Guide
LogoLogo
Book a demoLog in
On this page
  • What counts as a run?
  • Rate limit types
  • Need higher limits?
General

Rate Limits

Was this page helpful?
Previous

Async Processing

Next
Built with

Each plan tier includes rate limits to ensure system stability and fair resource allocation:

PlanQPS (Queries Per Second)Runs Per Minute
Sandbox560
Starter1080
Scale25120
Growth50+180+
Enterprisecustomcustom

What counts as a run?

One run equals processing one file through any of the following operations:

  • Classification
  • Extraction
  • Splitting
  • Parsing

Rate limit types

QPS (Queries Per Second): Global API rate limiting across all endpoints

Runs Per Minute: Maximum number of file processing operations per minute

Need higher limits?

For Growth and Enterprise tiers, custom rate limits are available. Please contact us to discuss your requirements.