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.

<! generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten 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 Acquire, renew, or release an exclusive managed connection lease Requires an API key with lease:exclusive and an explicit non empty allowedConnections policy. The opaque owner is bound to the authenticated API key; the lease owns an eligible connection, not a provider or model. Managed inference requests present the owner and exact generation headers. Temporary foreign occupancy returns 429 WAITING FOR CAPACITY with Retry After . POST /api/v1/chat/completions Create chat completion OpenAI compatible chat completions endpoint. Routes to configured providers. GET /api/v1/ws Chat completion over WebSocket (handshake + upgrade) OpenAI compatible chat over a WebSocket connection. GET with ?handshake=1 returns the connection descriptor (auth path, message protocol and live event channels) as JSON; a plain GET without an Upgrade returns 426 Upgrade Required . After upgrading, the client exchanges JSON frames — {type:"request", id, payload:{model, messages}} to start a completion and {type:"cancel", id} to abort it. A separate live channel (default port LIVE WS PORT=20129 , path /live ) streams dashboard events on the requests , combo and credentials topics with a 15s heartbeat. Requires an API key. POST /api/v1/providers/{provider}/chat/completions Create chat completion (provider specific) Routes to a specific provider by name. POST /api/v1/api/chat Ollama compatible chat endpoint Provides compatibility with Ollama's /api/chat format. POST /api/v1/messages Create message (Anthropic compatible) Anthropic Messages API endpoint. Routes to Claude providers. POST /api/v1/messages/count tokens Count tokens for a message POST /api/v1/responses Create response (OpenAI Responses API) OpenAI Responses API endpoint. POST /api/v1/embeddings Create embeddings GET /api/v1/multimodal embeddings List embedding models (Jina multimodal embeddings alias) POST /api/v1/multimodal embeddings Create embeddings (Jina multimodal embeddings alias) Same handler as POST /api/v1/embeddings . Provided so Jina compatible clients that call /v1/multimodal embeddings do not receive HTTP 404 unknown route . POST /api/v1/providers/{provider}/embeddings Create embeddings (provider specific) POST /api/v1/images/generations Generate images POST /api/v1/providers/{provider}/images/generations Generate images (provider specific) POST /api/v1/audio/speech Generate speech audio Text to speech endpoint. Routes to configured TTS providers. POST /api/v1/audio/transcriptions Transcribe audio Audio to text transcription endpoint. POST /api/v1/moderations Create moderation Content moderation endpoint. Routes to configured moderation providers. POST /api/v1/rerank Rerank documents Document reranking endpoint. GET /api/v1 API v1 root endpoint Returns basic API info and status. GET /api/v1/providers/{provider}/models List models for a specific provider Returns only models for the selected provider with provider prefix removed from each model id. GET /api/v1/management/proxy subscriptions List proxy subscriptions Lists all operator supplied proxy subscription links. Also starts the background auto refresh scheduler (idempotent) so enabled subscriptions stay in sync. Credentials embedded in url are redacted in the response. POST /api/v1/management/proxy subscriptions Create a proxy subscription Creates a subscription record. If mode is rule , at least one entry in ruleProviders is required. updateIntervalMinutes defaults to 60 and enabled defaults to false when omitted or not exactly true . GET /api/v1/management/proxy subscriptions/{id} Get a proxy subscription PATCH /api/v1/management/proxy subscriptions/{id} Update a proxy subscription Partial update — only fields present in the body are changed (name/url/mode/ruleProviders/localCoreEndpoint/updateIntervalMinutes/enabled). DELETE /api/v1/management/proxy subscriptions/{id} Delete a proxy subscription Removes the subscription record and unbinds/drops its synced proxy registry rows. GET /api/v1/management/proxy subscriptions/{id}/nodes Get a subscription's last parsed node summary Returns the last parsed node list without re fetching the (possibly slow) subscription URL. POST /api/v1/management/proxy subscriptions/{id}/refresh Refresh a proxy subscription Re fetches and re parses the subscription URL, syncs its nodes into proxy registry , and (re)binds the pool. POST /api/v1/ocr Document OCR Multi provider document OCR endpoint (Mistral OCR–compatible request and response shape). Accepts a JSON body referencing a document/image and returns extracted text. model selects the provider via a provider/model prefix (e.g. mistral/mistral ocr latest , azure document intelligence/prebuilt read , vertex deepseek ocr/deepseek ocr maas ); a bare model id (e.g. mistral ocr latest ) resolves to its registered provider, and an omitted model defaults to Mistral. Azure Document Intelligence is asynchronous upstream — the handler polls the returned operation until it succeeds or fails before responding, so this endpoint can take longer to return for that provider. Success responses carry the X OmniRoute cost telemetry headers. POST /api/v1/audio/translations Translate audio to English OpenAI Whisper–compatible audio translation (multipart/form data). Unlike /api/v1/audio/transcriptions , output is always English regardless of the source language. Success responses carry the X OmniRoute cost telemetry headers. GET /api/v1/voices List ElevenLabs voices Proxies GET https://api.elevenlabs.io/v1/voices using the stored elevenlabs provider credentials (the caller never sends xi api key ). The incoming query string is forwarded unchanged. POST /api/v1/speech to text ElevenLabs speech to text Streams the request body to POST https://api.elevenlabs.io/v1/speech to text using the stored elevenlabs provider credentials. content type and accept are forwarded; the upstream body is relayed unchanged. POST /api/v1/text to speech/{voiceId} ElevenLabs text to speech Streams the request body to POST https://api.elevenlabs.io/v1/text to speech/{voiceId} using the stored elevenlabs provider credentials. voiceId must match ^[A Za z0 9 ]+$ or the request is rejected with 400 before any upstream call. GET /api/v1/explain/routing Routing explainability snapshot Returns the most recent routing events (bounded in memory ring buffer) plus the per provider/model quality snapshot from open sse/services/routing . Routing metadata only — never prompts, bodies, headers or credentials. Auth mirrors /api/v1/combos : a valid Bearer API key or a dashboard session; with REQUIRE API KEY=false anonymous reads are allowed. GET /api/v1/providers/suggested models Suggested media models Read only server side proxy to the public HuggingFace Hub models search API, used by the dashboard to suggest models for a media provider kind without exposing an HF token client side. Never accepts or returns credentials. GET /api/v1/provider plugin manifest Provider plugin manifest Returns the manifest describing installed provider plugins. Payloads See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas. <! skill:custom start <! Aggregated from: omniroute chat, omniroute image, omniroute tts, omniroute stt, omniroute embeddings, omniroute web search, omniroute web fetch Chat completions Requires OMNIROUTE URL and OMNIROUTE KEY . See [entry point SKILL](https://raw.githubusercontent.com/diegosouzapw/OmniRoute/main/skills/omniroute/SKILL.md) 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 Combos (e.g. auto , cost optimized , subscription ) auto fallback through multiple providers. OpenAI format example Anthropic format example 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](https://raw.githubusercontent.com/diegosouzapw/OmniRoute/main/skills/omniroute/SKILL.md) 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 Returns { id, owned by, sizes:[...], capabilities:[...] } per model. Generate example Response: { created, data: [{ url? or b64 json, revised prompt }] } Errors 400 invalid size → not supported by this model; check /v1/models/image 400 content policy violation → blocked by provider safety 503 → provider unavailable; try another model in /v1/models/image Text to speech Requires OMNIROUTE URL and OMNIROUTE KEY . See [entry point SKILL](https://raw.githubusercontent.com/diegosouzapw/OmniRoute/main/skills/omniroute/SKILL.md) for setup. Endpoint POST $OMNIROUTE URL/v1/audio/speech — returns binary audio (mp3/opus/wav/flac) Discover Each entry includes voices:[...] for the available voice names per provider. Example Voices Voice names vary by provider. Check /v1/models/tts — each entry has voices:[...] . Common OpenAI voices: alloy , echo , fable , onyx , nova , shimmer . Errors 400 invalid voice → voice not supported by this model 400 input too long → input exceeds model character limit 503 → provider unavailable; try another model in /v1/models/tts Speech to text Requires OMNIROUTE URL and OMNIROUTE KEY . See [entry point SKILL](https://raw.githubusercontent.com/diegosouzapw/OmniRoute/main/skills/omniroute/SKILL.md) for setup. Endpoints POST $OMNIROUTE URL/v1/audio/transcriptions — multipart upload, returns text POST $OMNIROUTE URL/v1/audio/translations — transcribe + translate to English Discover Example Response: { text, language, duration, segments?:[{ start, end, text }] } Supported formats Audio: mp3 , mp4 , mpeg , mpga , m4a , wav , webm . Response formats: json , text , srt , verbose json , vtt . Errors 400 invalid file format → unsupported audio format 400 file too large → exceeds provider limit (usually 25MB) 503 → provider unavailable; try another model in /v1/models/stt Embeddings Requires OMNIROUTE URL and OMNIROUTE KEY . See [entry point SKILL](https://raw.githubusercontent.com/diegosouzapw/OmniRoute/main/skills/omniroute/SKILL.md) for setup. Endpoint P

omni-inference