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}
• POST /api/v1/sound-generation
• POST /api/v1/music
• POST /api/v1/music/stream
• POST /api/v1/music/detailed
• POST /api/v1/music/detailed/stream
• POST /api/v1/music/plan
• 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.

Generate example

curl -X POST $OMNIROUTE_URL/v1/images/generations \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dall-e-3",
    "prompt": "a red bicycle on a wet street, photoreal",
    "n": 1,
    "size": "1024x1024",
    "response_format": "b64_json"
  }'

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 for setup.

Endpoint

• POST $OMNIROUTE_URL/v1/audio/speech — returns binary audio (mp3/opus/wav/flac)

Discover

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

Each entry includes voices:[...] for the available voice names per provider.

Example

curl -X POST $OMNIROUTE_URL/v1/audio/speech \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "Hello from OmniRoute.",
    "voice": "alloy",
    "response_format": "mp3"
  }' --output speech.mp3

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 for setup.

Endpoints

• POST $OMNIROUTE_URL/v1/audio/transcriptions — multipart upload, returns text
• POST $OMNIROUTE_URL/v1/audio/translations — transcribe + translate to English

Discover

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

Example

curl -X POST $OMNIROUTE_URL/v1/audio/transcriptions \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -F "file=@audio.mp3" \
  -F "model=whisper-1" \
  -F "response_format=verbose_json"

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 for setup.

Endpoint

• POST $OMNIROUTE_URL/v1/embeddings

Discover

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

Each entry: { id, owned_by, dimensions, max_input_tokens }.

Example

curl -X POST $OMNIROUTE_URL/v1/embeddings \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-large",
    "input": ["first text", "second text"],
    "encoding_format": "float"
  }'

Response: { data:[{ embedding:[...], index }], usage:{ prompt_tokens, total_tokens } }

Batch input

input accepts a string or array of strings (up to provider batch limit, typically 2048 items).

Errors

• 400 input_too_long → input exceeds max_input_tokens for this model
• 400 invalid_encoding_format → use float or base64
• 503 → provider unavailable; try another model in /v1/models/embedding

Web search

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

Endpoint

• POST $OMNIROUTE_URL/v1/web/search — unified search format

Discover

curl $OMNIROUTE_URL/v1/models/web | jq '.data[] | select(.kind == "webSearch")'

Example

curl -X POST $OMNIROUTE_URL/v1/web/search \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tavily/search",
    "query": "OmniRoute github latest release",
    "max_results": 5,
    "include_answer": true
  }'

Response: { answer?, results:[{ url, title, content, score }] }

Parameters

Errors

• 400 query_too_long → shorten the search query
• 503 → provider unavailable; try another model in /v1/models/web

Web fetch

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

Endpoint

• POST $OMNIROUTE_URL/v1/web/fetch

Discover

curl $OMNIROUTE_URL/v1/models/web | jq '.data[] | select(.kind == "webFetch")'

Example

curl -X POST $OMNIROUTE_URL/v1/web/fetch \
  -H "Authorization: Bearer $OMNIROUTE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jina/reader",
    "url": "https://anthropic.com",
    "format": "markdown"
  }'

Response: { url, title, markdown, links?:[...], images?:[...] }

Parameters

Errors

• 400 invalid_url → URL must be http/https
• 403 blocked → provider blocked by target site; try a different model
• 503 → provider unavailable; try another model in /v1/models/web