omni-inference

Overview

The core OpenAI-compatible inference endpoints: chat completions, embeddings, images, audio (TTS/STT), moderations, rerank, and the Responses API. The primary integration surface for AI agents.

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/v1/session-leases
• GET /api/v1/search
• POST /api/v1/search
• POST /api/v1/chat/completions
• GET /api/v1/ws
• POST /api/v1/providers/{provider}/chat/completions
• POST /api/v1/api/chat
• POST /api/v1/messages
• POST /api/v1/messages/count_tokens
• POST /api/v1/responses
• POST /api/v1/embeddings
• GET /api/v1/multimodal-embeddings
• POST /api/v1/multimodal-embeddings
• POST /api/v1/providers/{provider}/embeddings
• POST /api/v1/images/generations
• POST /api/v1/providers/{provider}/images/generations
• POST /api/v1/audio/speech
• POST /api/v1/audio/transcriptions
• POST /api/v1/moderations
• POST /api/v1/rerank
• GET /api/v1
• GET /api/v1/providers/{provider}/models
• GET /api/v1/management/proxy-subscriptions
• POST /api/v1/management/proxy-subscriptions
• GET /api/v1/management/proxy-subscriptions/{id}
• PATCH /api/v1/management/proxy-subscriptions/{id}
• DELETE /api/v1/management/proxy-subscriptions/{id}
• GET /api/v1/management/proxy-subscriptions/{id}/nodes
• POST /api/v1/management/proxy-subscriptions/{id}/refresh
• POST /api/v1/ocr
• POST /api/v1/audio/translations
• GET /api/v1/voices
• POST /api/v1/speech-to-text
• POST /api/v1/text-to-speech/{voiceId}
• GET /api/v1/explain/routing
• GET /api/v1/providers/suggested-models
• GET /api/v1/provider-plugin-manifest
• GET /api/v1/{omnirouteCatchAll}
• POST /api/v1/{omnirouteCatchAll}
• PUT /api/v1/{omnirouteCatchAll}
• PATCH /api/v1/{omnirouteCatchAll}
• DELETE /api/v1/{omnirouteCatchAll}
• GET /api/v1/accounts/{id}/limits
• PUT /api/v1/accounts/{id}/limits
• GET /api/v1/agents/credentials
• POST /api/v1/agents/credentials
• GET /api/v1/agents/health
• GET /api/v1/agents/tasks
• POST /api/v1/agents/tasks
• DELETE /api/v1/agents/tasks
• GET /api/v1/agents/tasks/{id}
• POST /api/v1/agents/tasks/{id}
• DELETE /api/v1/agents/tasks/{id}
• POST /api/v1/antigravity
• GET /api/v1/auto-combo/{channel}/candidates
• GET /api/v1/batches
• POST /api/v1/batches
• GET /api/v1/batches/{id}
• DELETE /api/v1/batches/{id}
• POST /api/v1/batches/{id}/cancel
• DELETE /api/v1/batches/delete-completed
• POST /api/v1/classify
• GET /api/v1/combos
• POST /api/v1/completions
• GET /api/v1/files
• POST /api/v1/files
• GET /api/v1/files/{id}
• DELETE /api/v1/files/{id}
• GET /api/v1/files/{id}/content
• POST /api/v1/images/edits
• GET /api/v1/images/upscale
• POST /api/v1/images/upscale
• GET /api/v1/media/{id}
• POST /api/v1/issues/report
• GET /api/v1/management/proxies
• POST /api/v1/management/proxies
• PATCH /api/v1/management/proxies
• DELETE /api/v1/management/proxies
• GET /api/v1/management/proxies/assignments
• PUT /api/v1/management/proxies/assignments
• PUT /api/v1/management/proxies/bulk-assign
• GET /api/v1/management/proxies/health
• GET /api/v1/me/status
• GET /api/v1/muse-code/models
• GET /api/v1/music/generations
• POST /api/v1/music/generations
• GET /api/v1/providers/{provider}/limits
• PUT /api/v1/providers/{provider}/limits
• GET /api/v1/quotas/check
• GET /api/v1/registered-keys
• POST /api/v1/registered-keys
• GET /api/v1/registered-keys/{id}
• DELETE /api/v1/registered-keys/{id}
• POST /api/v1/registered-keys/{id}/revoke
• POST /api/v1/relay/chat/completions
• POST /api/v1/relay/chat/completions/bifrost
• POST /api/v1/responses/{path}
• GET /api/v1/search/analytics
• POST /api/v1/segment
• GET /api/v1/video-bridge/drilldown
• DELETE /api/v1/video-bridge/drilldown
• GET /api/v1/videos/generations
• POST /api/v1/videos/generations
• GET /api/v1/vscode/{token}
• POST /api/v1/vscode/{token}/api/chat
• POST /api/v1/vscode/{token}/api/show
• GET /api/v1/vscode/{token}/api/tags
• GET /api/v1/vscode/{token}/api/version
• POST /api/v1/vscode/{token}/chat/completions
• GET /api/v1/vscode/{token}/combos
• GET /api/v1/vscode/{token}/models
• POST /api/v1/vscode/{token}/responses
• POST /api/v1/vscode/{token}/v1/chat/completions
• GET /api/v1/vscode/{token}/v1/models
• GET /api/v1/vscode/combos/{token}/{{slug}}
• POST /api/v1/vscode/combos/{token}/{{slug}}
• GET /api/v1/vscode/raw/{token}
• POST /api/v1/vscode/raw/{token}/api/chat
• POST /api/v1/vscode/raw/{token}/api/show
• GET /api/v1/vscode/raw/{token}/api/tags
• GET /api/v1/vscode/raw/{token}/api/version
• POST /api/v1/vscode/raw/{token}/chat/completions
• GET /api/v1/vscode/raw/{token}/combos
• GET /api/v1/vscode/raw/{token}/models
• POST /api/v1/vscode/raw/{token}/responses
• POST /api/v1/vscode/raw/{token}/v1/chat/completions
• GET /api/v1/vscode/raw/{token}/v1/models
• POST /api/v1/web/fetch

Payloads

See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.

Chat completions

Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.

Endpoints

• POST $OMNIROUTE_URL/v1/chat/completions — OpenAI format
• POST $OMNIROUTE_URL/v1/messages — Anthropic Messages format
• POST $OMNIROUTE_URL/v1/responses — OpenAI Responses API

Discover

curl $OMNIROUTE_URL/v1/models | jq '.data[].id'

Combos (e.g. auto, cost-optimized, subscription) auto-fallback through multiple providers.

OpenAI format example

curl -X POST $OMNIROUTE_URL/v1/chat/completions \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-7",
    "messages": [{"role": "user", "content": "Refactor this function"}],
    "stream": true
  }'

Anthropic format example

curl -X POST $OMNIROUTE_URL/v1/messages \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-7",
    "max_tokens": 4096,
    "messages": [{"role": "user", "content": "Hi"}]
  }'

Tool use

Supports OpenAI tools array and Anthropic tools block. Tool results auto-compressed via RTK (47 filters: git-diff, grep, test-jest, terraform-plan, docker-logs, etc.) — 20-40% token savings. Disable per-request with X-Omniroute-Rtk: off header.

Reasoning / thinking

Anthropic extended thinking and OpenAI Responses reasoning blocks are forwarded verbatim. Cached automatically via reasoning cache.

Errors

• 401 → invalid API key
• 400 invalid_model → model not in registry; check /v1/models
• 503 circuit_open → provider circuit breaker tripped; retry later or use combo
• 429 rate_limited → honor Retry-After; consider using a combo for auto-fallback

Image generation

Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.

Endpoints

• POST $OMNIROUTE_URL/v1/images/generations — Text-to-image
• POST $OMNIROUTE_URL/v1/images/edits — Image edit (mask)
• POST $OMNIROUTE_URL/v1/images/variations — Variations

Discover

curl $OMNIROUTE_URL/v1/models/image | jq '.data[]'

Returns { id, owned_by, sizes:[...], capabilities:[...] } per model.

...