KeyPool Integration Guide¶
KeyPool gives your team one stable API surface for AI services that each have their own auth headers, quotas, and SDK quirks.
What You Get¶
- One team token for every supported service.
- Shared service access through one stable endpoint per supported provider.
- Consistent failure handling when a provider is temporarily unavailable or rate-limited.
- Usage controls defined by your KeyPool workspace.
- Service-specific guidance for SDK setup, base URLs, and edge cases.
Start Here¶
- Get your KeyPool Team Token from your workspace admin.
- Pick the service you want to integrate from the navigation.
- Set
KEYPOOL_BASE_URLto the base URL provided by your KeyPool administrator. - Send
Authorization: Bearer <TEAM_TOKEN>on every request to KeyPool. - Use the API Reference page to test the exact service endpoints in-browser.
Base URL Patterns¶
Most services use the same URL pattern:
https://your-keypool.example.com/v1/{service}
Two services use a service header for SDK compatibility:
- Firecrawl SDKs should target the KeyPool origin and use
x-keypool-service: firecrawl. - Tavily examples in this guide use the KeyPool origin plus
x-keypool-service: tavilyfor the same reason.
Availability And Errors¶
KeyPool may retry a request internally when a provider returns a retryable per-key error and the request body can be replayed. If no usable provider credential is available for a service, KeyPool returns a JSON error with HTTP 503. If your team token is rate-limited, KeyPool returns HTTP 429.
For production integrations, treat 429, 502, and 503 as retryable with backoff unless the service-specific guide says otherwise. Contact your workspace admin if one service consistently returns 503; admins can check the pool monitor and credential eligibility without changing client code.