Skip to content

Documentation — v1.4.3

OmniRoute Docs

AI gateway for multi-provider LLMs. One endpoint for OpenAI, Anthropic, Gemini, GitHub Copilot, Claude Code, Cursor, and 20+ more providers.

Open DashboardEndpoint PageGitHub open_in_newReport Issue

Quick Start

  1. 1. Install & run

    npx omniroute or clone from GitHub and run npm start.

  2. 2. Create API key

    Go to Endpoint → Registered Keys. Generate one key per environment.

  3. 3. Connect providers

    Add provider accounts via OAuth login, API key, or free-tier auto-connect.

  4. 4. Set client base URL

    Point your IDE or API client to https://<host>/v1. Use provider prefix, e.g. gh/gpt-5.1-codex.

Features

hub

Multi-Provider Routing

Route requests to 30+ AI providers through a single OpenAI-compatible endpoint. Supports chat, responses, audio, and image APIs.

layers

Combos & Balancing

Create model combos with fallback chains and balancing strategies: round-robin, priority, random, least-used, and cost-optimized.

bar_chart

Usage & Cost Tracking

Real-time token counting, cost calculation per provider/model, and detailed usage breakdown by API key and account.

analytics

Analytics Dashboard

Visual analytics with charts for requests, tokens, errors, latency, costs, and model popularity over time.

health_and_safety

Health Monitoring

Live health checks, provider status, circuit breaker states, and automatic rate limit detection with exponential backoff.

terminal

CLI Tools

Manage IDE configurations, export/import backups, discover codex profiles, and configure settings from the dashboard.

shield

Security & Policies

API key authentication, IP filtering, prompt injection guard, domain policies, session management, and audit logging.

cloud_sync

Cloud Sync

Sync your configuration to Cloudflare Workers for remote access with encrypted credentials and automatic failover.

Supported Providers

36 providers across three connection types.

Manage Providers

Free Tier

4 providers
iFlow AIif/
Qwen Codeqw/
Gemini CLIgc/
Kiro AIkr/

OAuth

8 providers
Claude Codecc/
Antigravityag/
OpenAI Codexcx/
GitHub Copilotgh/
Cursor IDEcu/
Kimi Codingkmc/
Kilo Codekc/
Clinecl/

API Key

24 providers
OpenRouteropenrouter/
GLM Codingglm/
Kimikimi/
Minimax Codingminimax/
Minimax (China)minimax-cn/
OpenAIopenai/
Anthropicanthropic/
Geminigemini/
DeepSeekds/
Groqgroq/
xAI (Grok)xai/
Mistralmistral/
Perplexitypplx/
Together AItogether/
Fireworks AIfireworks/
Cerebrascerebras/
Coherecohere/
NVIDIA NIMnvidia/
Nebius AInebius/
SiliconFlowsiliconflow/
Hyperbolichyp/
Deepgramdg/
AssemblyAIaai/
NanoBanananb/

Common Use Cases

Single endpoint for many providers

Point clients to one base URL and route by model prefix (for example: gh/, cc/, kr/, openai/).

Fallback and model switching with combos

Create combo models in Dashboard and keep client config stable while providers rotate internally.

Usage, cost and debug visibility

Track tokens/cost by provider, account and API key in Usage + Analytics tabs.

Client Compatibility

Cherry Studio

  • Base URL: https://<host>/v1
  • Chat endpoint: /chat/completions
  • Model recommendation: explicit prefix (gh/..., cc/...)

Codex / GitHub Copilot Models

  • Use model IDs with gh/ prefix.
  • Codex-family models auto-route to /responses.
  • Non-Codex models continue on /chat/completions.

Cursor IDE

  • Use cu/ prefix for Cursor models.
  • OAuth connection — login from the Providers page.
  • Supports both chat and responses endpoints.

Claude Code / Antigravity

  • Use cc/ (Claude) or ag/ (Antigravity) prefix.
  • OAuth connection with automatic token refresh.
  • Full streaming support for all models.

API Reference

MethodPathNotes
POST/v1/chat/completionsOpenAI-compatible chat endpoint (default).
POST/v1/responsesResponses API endpoint (Codex, o-series).
GET/v1/modelsModel catalog for all connected providers.
POST/v1/audio/transcriptionsAudio transcription (Deepgram, AssemblyAI).
POST/v1/images/generationsImage generation (NanoBanana).
POST/chat/completionsRewrite helper for clients without /v1.
POST/responsesRewrite helper for Responses without /v1.
GET/modelsRewrite helper for model discovery without /v1.

Model Prefixes

Use the provider prefix before the model name to route to a specific provider. Example: gh/gpt-5.1-codex routes to GitHub Copilot.

PrefixProviderType
if/iFlow AIFree
qw/Qwen CodeFree
gc/Gemini CLIFree
kr/Kiro AIFree
cc/Claude CodeOAuth
ag/AntigravityOAuth
cx/OpenAI CodexOAuth
gh/GitHub CopilotOAuth
cu/Cursor IDEOAuth
kmc/Kimi CodingOAuth
kc/Kilo CodeOAuth
cl/ClineOAuth
openrouter/OpenRouterAPI Key
glm/GLM CodingAPI Key
kimi/KimiAPI Key
minimax/Minimax CodingAPI Key
minimax-cn/Minimax (China)API Key
openai/OpenAIAPI Key
anthropic/AnthropicAPI Key
gemini/GeminiAPI Key
ds/DeepSeekAPI Key
groq/GroqAPI Key
xai/xAI (Grok)API Key
mistral/MistralAPI Key
pplx/PerplexityAPI Key
together/Together AIAPI Key
fireworks/Fireworks AIAPI Key
cerebras/CerebrasAPI Key
cohere/CohereAPI Key
nvidia/NVIDIA NIMAPI Key
nebius/Nebius AIAPI Key
siliconflow/SiliconFlowAPI Key
hyp/HyperbolicAPI Key
dg/DeepgramAPI Key
aai/AssemblyAIAPI Key
nb/NanoBananaAPI Key

Troubleshooting

  • If the client fails with model routing, use explicit provider/model (for example: gh/gpt-5.1-codex).
  • If you receive ambiguous model errors, pick a provider prefix instead of a bare model ID.
  • For GitHub Codex-family models, keep model as gh/<codex-model>; router selects /responses automatically.
  • Use Dashboard > Providers > Test Connection before testing from IDEs or external clients.
  • If a provider shows circuit breaker open, wait for the cooldown or check Health page for details.
  • For OAuth providers, re-authenticate if tokens expire. Check the provider card status indicator.