| name | omni-auth |
| description | Manage API key authentication and session tokens. Start here to authenticate requests via Bearer token, obtain session cookies, and configure login requirements for the AIRoute API. |
Overview
Manage API key authentication and session tokens. Start here to authenticate requests via Bearer token, obtain session cookies, and configure login requirements for the AIRoute API.
Authentication
All requests require a valid Bearer token or session cookie. Obtain a token via POST /api/auth/login or configure REQUIRE_API_KEY=false for local development.
Endpoints
POST /api/auth/login
Authenticate user
curl -X POST https://localhost:20128/api/auth/login \
-H "Authorization: Bearer $AIRoute_TOKEN"
-H "Content-Type: application/json" \
-d '{}'
POST /api/auth/logout
Log out
curl -X POST https://localhost:20128/api/auth/logout \
-H "Authorization: Bearer $AIRoute_TOKEN"
-H "Content-Type: application/json" \
-d '{}'
Payloads
See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.
AIRoute
Local/remote AI gateway exposing OpenAI-compatible REST. One key, 207+ providers,
auto-fallback, RTK token saver, MCP server, A2A agents.
Setup
export AIRoute_URL="http://localhost:20128"
export AIRoute_KEY="sk-..."
All requests: ${AIRoute_URL}/v1/... with Authorization: Bearer ${AIRoute_KEY}.
Verify: curl $AIRoute_URL/api/health → {"ok":true}
Discover models
curl $AIRoute_URL/v1/models
curl $AIRoute_URL/v1/models/image
curl $AIRoute_URL/v1/models/tts
curl $AIRoute_URL/v1/models/embedding
curl $AIRoute_URL/v1/models/web
curl $AIRoute_URL/v1/models/stt
Use data[].id as model field in requests. Combos appear with owned_by:"combo".
Capability skills
CLI skills (AIRoute binary)
Errors
401 → set/refresh AIRoute_KEY (Dashboard → API Keys)400 Invalid model format → check model exists in /v1/models/<kind>503 Provider circuit open → upstream provider down; retry after Retry-After seconds429 → rate limited; honor Retry-After
Differentiators vs OpenAI direct
- Auto-fallback combos (14 strategies): never stop coding even if a provider rate-limits
- RTK token saver: tool_result compressed via 47 specialized filters (git-diff, test-jest, terraform-plan, docker-logs…) — 20-40% token reduction
- Caveman mode: optional terse system prompt injection (LITE/FULL/ULTRA) — 15-25% completion reduction
- MCP + A2A servers built-in (this is the only AI router that exposes both protocols)
- Memory with FTS5 + Qdrant for persistent agent context
- Guardrails for PII masking, prompt injection detection, vision policies
