Skip to main content

AI API Overview

The Informer AI API provides comprehensive endpoints for managing AI-powered conversations, models, budget control, and seat assignments. All routes are prefixed with /api.

Features​

  • Chats - Create and manage AI conversations with streaming responses
  • Messages - Access and manipulate chat message history
  • Memories - Store and search conversation context using vector embeddings
  • Models - Configure AI models from multiple providers
  • Providers - Manage AI service provider credentials
  • Seats & Plans - Control user access and budget allocation
  • Budget & Usage - Track costs and consumption across tiers
  • Admin Tools - Tenant-wide configuration and monitoring

Authentication​

All AI API endpoints require authentication via session cookies or API tokens. Most endpoints verify AI entitlements and seat assignments before allowing access.

Common Authorization Patterns​

  • User endpoints - Require active AI seat (verified by ai.verify pre-block)
  • Admin endpoints - Require permission.tenant.superuser
  • Team settings - Require permission.team.manageAi(teamId)
  • Model/Provider management - Require permission.ai.manage

Rate Limiting​

Chat endpoints enforce budget-based rate limiting:

  • Weekly budget - Resets every 7 days from seat assignment
  • Session budget - 6-hour rolling window
  • Tiered models - Costs vary by model tier (everyday, advanced, strategic)
  • Boost budget - Additional one-time budget purchased by admins

Streaming Responses​

Several endpoints return Server-Sent Events (SSE) streams:

  • POST /api/chats/\{id\} - Chat message stream
  • POST /api/models/\{id\}/_chat - Direct model chat stream
  • POST /api/models/\{id\}/_completion - Text completion stream
  • POST /api/chats/\{id\}/messages/\{messageId\}/_explain - Message explanation stream

SSE responses use Content-Type: text/event-stream and support abort signals for cancellation.

Error Responses​

Standard HTTP status codes:

  • 200 - Success
  • 400 - Bad request (validation error)
  • 403 - Forbidden (insufficient permissions or budget)
  • 404 - Resource not found
  • 500 - Internal server error

Error responses include:

{
  "statusCode": 403,
  "error": "Forbidden",
  "message": "Insufficient budget remaining"
}

Common Query Parameters​

Many list endpoints support:

  • limit - Number of results per page (default varies by endpoint)
  • offset - Pagination offset
  • planId - Filter by AI plan
  • assigned - Filter by assignment status

Next Steps​

Explore the specific endpoint categories: