Languages: 🇺🇸 English | 🇧🇷 Português (Brasil) | 🇪🇸 Español | 🇫🇷 Français | 🇮🇹 Italiano | 🇷🇺 Русский | 🇨🇳 中文 (简体) | 🇩🇪 Deutsch | 🇮🇳 हिन्दी | 🇹🇭 ไทย | 🇺🇦 Українська | 🇸🇦 العربية | 🇯🇵 日本語 | 🇻🇳 Tiếng Việt | 🇧🇬 Български | 🇩🇰 Dansk | 🇫🇮 Suomi | 🇮🇱 עברית | 🇭🇺 Magyar | 🇮🇩 Bahasa Indonesia | 🇰🇷 한국어 | 🇲🇾 Bahasa Melayu | 🇳🇱 Nederlands | 🇳🇴 Norsk | 🇵🇹 Português (Portugal) | 🇷🇴 Română | 🇵🇱 Polski | 🇸🇰 Slovenčina | 🇸🇪 Svenska | 🇵🇭 Filipino | 🇨🇿 Čeština

---

Chat Completions
• Embeddings
• Image Generation
• List Models
• Compatibility Endpoints
• Files API
• Batches API
• Search API
• WebSocket Streaming
• Quotas & Issues Reporting
• Semantic Cache
• Dashboard & Management
• Combo Management
• Webhooks
• Registered Keys (Auto-Management)
• Agents Protocol
• Management Proxies
• Resilience (extended)
• Skills
• Memory
• MCP Server
• A2A Server
• Cloud, Evals & Assess
• Request Processing
• Authentication

---

POST /v1/chat/completions
Authorization: Bearer your-api-key
Content-Type: application/json

{
  "model": "cc/claude-opus-4-6",
  "messages": [
    {"role": "user", "content": "Write a function to..."}
  ],
  "stream": true
}

		to bypass cache
		for progress events
		or (non-streaming)
		if deduplicated
		if progress tracking on

), enable .

---

POST /v1/embeddings
Authorization: Bearer your-api-key
Content-Type: application/json

{
  "model": "nebius/Qwen/Qwen3-Embedding-8B",
  "input": "The food was delicious"
}

OpenRouter, GitHub Models.

# List all embedding models
GET /v1/embeddings

---

POST /v1/images/generations
Authorization: Bearer your-api-key
Content-Type: application/json

{
  "model": "openai/gpt-image-2",
  "prompt": "A beautiful sunset over mountains",
  "size": "1024x1024"
}

OpenRouter, SD WebUI (local), ComfyUI (local).

# List all image models
GET /v1/images/generations

---

GET /v1/models
Authorization: Bearer your-api-key

→ Returns all chat, embedding, and image models + combos in OpenAI format

---

+ Zod-validated JSON body (, , , etc., see ). 4xx is returned on schema failure.

# Rerank
POST /v1/rerank      { "model": "cohere/rerank-3", "query": "...", "documents": ["..."] }

# Moderations
POST /v1/moderations { "model": "omni-moderation-latest", "input": "..." }

# TTS — returns audio/mpeg (or requested format) body
POST /v1/audio/speech { "model": "openai/tts-1", "input": "Hello", "voice": "alloy" }

# Image edit (multipart)
POST /v1/images/edits  -F image=@input.png -F prompt="..." -F mask=@mask.png

# Video / music generation (provider-prefixed model id)
POST /v1/videos/generations { "model": "runway/gen-3", "prompt": "..." }
POST /v1/music/generations  { "model": "suno/v3.5",   "prompt": "..." }

POST /v1/providers/{provider}/chat/completions
POST /v1/providers/{provider}/embeddings
POST /v1/providers/{provider}/images/generations

.

---

		, , , ) — 512 MiB max

Auth: Bearer API key — files are scoped per-API-key via .

---

		(, , )

Auth: Bearer API key. Batches are scoped per-API-key.

---

		, supports caching/coalescing

Auth: Bearer API key ( + ). Search policy enforced via .

---

GET /v1/ws?handshake=1

, ). Actual WS frames are handled by the bundled WS server outside the Next.js route table.

Auth: Bearer API key during handshake.

---

		+ before issuing a registered key
		+ token)

Auth: Bearer API key ().

---

# Get cache stats
GET /api/cache/stats

# Clear all caches
DELETE /api/cache/stats

{
  "semanticCache": {
    "memorySize": 42,
    "memoryMaxSize": 500,
    "dbSize": 128,
    "hitRate": 0.65
  },
  "idempotency": {
    "activeKeys": 3,
    "windowMs": 5000
  }
}

---

		, , , )

		)
		)

, , , , , .

		query param

(id, name, binary, version, installed, protocol, isCustom) and (total, installed, notFound, builtIn, custom).

		or to wipe everything

routes require management auth (). See Resilience (extended) for a full breakdown of provider breaker vs connection cooldown vs model lockout.

		endpoint

Note: These endpoints are used internally by the system or for Ollama client compatibility. They are not typically called by end users.

(v3.6.1+)

POST /api/system/env/repair
Content-Type: application/json

{
  "provider": "claude-code"
}

{
  "success": true,
  "repaired": ["CLAUDE_CODE_OAUTH_CLIENT_ID", "CLAUDE_CODE_OAUTH_CLIENT_SECRET"],
  "backupPath": "/home/user/.omniroute/backups/env-repair-2026-04-11.bak"
}

---

POST /v1/audio/transcriptions
Authorization: Bearer your-api-key
Content-Type: multipart/form-data

Request:

curl -X POST http://localhost:20128/v1/audio/transcriptions \
  -H "Authorization: Bearer your-api-key" \
  -F "file=@recording.mp3" \
  -F "model=deepgram/nova-3"

Response:

{
  "text": "Hello, this is the transcribed audio content.",
  "task": "transcribe",
  "language": "en",
  "duration": 12.5
}

Supported providers: , .

Supported formats: , , , , , .

---

# Chat endpoint (Ollama format)
POST /v1/api/chat

# Model listing (Ollama format)
GET /api/tags

---

# Get latency telemetry summary (p50/p95/p99 per provider)
GET /api/telemetry/summary

Response:

{
  "providers": {
    "claudeCode": { "p50": 245, "p95": 890, "p99": 1200, "count": 150 },
    "github": { "p50": 180, "p95": 620, "p99": 950, "count": 320 }
  }
}

---

# Get budget status for all API keys
GET /api/usage/budget

# Set or update a budget
POST /api/usage/budget
Content-Type: application/json

{
  "apiKeyId": "key-123",
  "dailyLimitUsd": 5.00,
  "weeklyLimitUsd": 30.00,
  "monthlyLimitUsd": 100.00,
  "warningThreshold": 0.8,
  "resetInterval": "monthly"
}

Schema notes (): is required; at least one of , , or must be greater than zero. Optional fields: (0–1), ( | | ), (). The legacy shape returns .

1. , , , or
4. checks semantic/signature cache and resolves combo compression settings
5. , Caveman, RTK, or stacked)

---

) can also be mapped 1:1 from a model id pattern, allowing transparent redirection of an OpenAI-style model id to a combo.

Auth: management session/API key ().

---

		)

Auth: management session/API key ().

---

		. Returns the raw key once. Returns on quota refusal.

Auth: Bearer API key (). See also and .

---

		, , (1–500, default 50)
		(, , , ). Returns with task envelope
		is set
		, , or

Auth: management auth required on every method (). Prior to v3.8.0 these were unauthenticated — see commit for the breaking change.

# Create a Claude Code cloud task
curl -X POST http://localhost:20128/api/v1/agents/tasks \
  -H "Authorization: Bearer your-management-key" \
  -H "Content-Type: application/json" \
  -d '{"providerId":"claude-code-cloud","prompt":"Fix the failing test","source":{"repo":"...","branch":"..."}}'

---

		returns one; with returns the assignment graph)
		(requires )
		to detach assignments)
		, , ; pass to resolve the active proxy for a connection
		(). Clears dispatcher cache
		()

Auth: management session/API key on every route ().

and are served by the flat and routes shown above — there are no per-id subroutes in the codebase.

---

	+ in-memory
	on provider connections	,

# Clear a single model lockout
curl -X DELETE http://localhost:20128/api/resilience/model-cooldowns \
  -H "Cookie: auth_token=..." \
  -H "Content-Type: application/json" \
  -d '{"provider":"openai","model":"gpt-4o-mini"}'

# Wipe every lockout
curl -X DELETE http://localhost:20128/api/resilience/model-cooldowns \
  -H "Cookie: auth_token=..." \
  -d '{"all":true}'

→ "Resilience Runtime State".

---

		, , , paginated
		setting)

Auth: management session/API key. Marketplace search routes accept either management auth or a Bearer API key ().

---

		, , , , with or pagination

Auth: management session/API key (). enum: , , , (see in ).

---

| Heartbeat, transport, online state, last call, top tools, 24h success rate | | GET | | List of MCP tools with , , , , , | | GET | | Open SSE stream for the SSE transport (returns if MCP disabled or transport mismatch) | | POST | | Send JSON-RPC frame on the SSE transport | | GET | | Open SSE side of the Streamable HTTP transport (server-initiated messages) | | POST | | Send JSON-RPC frame on the Streamable HTTP transport | | DELETE | | End a Streamable HTTP session | | GET | | Query audit log — , , , , | | GET | | Aggregate audit stats (totals, success rate, avg duration, top tools) |

Auth: the / transports honor the MCP-specific auth surface (Bearer API key with scope); the // routes are readable from the dashboard (no extra auth required beyond reaching the dashboard host).

and — a transport mismatch returns , an MCP disabled state returns .

---

POST /a2a
Authorization: Bearer your-api-key   # optional unless OMNIROUTE_API_KEY is set
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "message/send",
  "params": {
    "skill": "smart-routing",
    "messages": [{"role": "user", "content": "Route this coding task"}]
  }
}

):

, , , , .

GET /.well-known/agent.json

		, , (≤200),
		)

Auth: the REST helpers run without management auth (dashboard-readable); the JSON-RPC route uses Bearer if configured.

---

| Verify a Bearer key and return masked provider connections + model aliases for cloud sync clients | | POST | | Update encrypted credentials for a cloud-synced provider | | POST | | Resolve a logical model id to a concrete provider/model using the local routing table | | GET | | List model aliases as exposed to cloud sync | | GET | | Read latest assessment categorizations (per-provider/model) | | POST | | Run an assessment — body: | | GET | | List built-in eval suites + most recent runs | | POST | | Trigger an eval run | | POST | | Create a custom eval suite — body validated by | | GET | | Retrieve a custom eval suite |

Auth: validates a Bearer key directly; the other , , and routes require management session/API key. POST uses with a discriminated-union scope schema.

---

) use cookie
• toggleable via
• routes optionally require Bearer API key when

Breaking change (v3.8.0) — and the cooldown management endpoints now require management auth (dashboard cookie or a management-scoped API key). Clients that previously called these routes unauthenticated will receive . See commit ().