Skip to content

Documentation - v1.7.1

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 and run

    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, for example 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 and Balancing

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

bar_chart

Usage and 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 and 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 and cost by provider, account, and API key in Usage and 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/.
  • 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 Tier
qw/Qwen CodeFree Tier
gc/Gemini CLIFree Tier
kr/Kiro AIFree Tier
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.