Integrations
Connect your coding agent, SDK, or chat client with a Router One key. Start by matching its URL field and protocol below, then open the client guide for its exact configuration, a compatible model ID, and how to verify the first request in the dashboard.
Which URL should I enter?
OpenAI-compatible SDKs and Codex use the /v1 base URL; Claude Code uses the host root; Immersive Translate needs the full /v1/chat/completions URL. Check the configured protocol and model support.
| Client / setting | Value to enter | API used |
|---|---|---|
SDK Chat Completions setupbase_url / baseURL / apiBase | https://api.router.one/v1 | Chat CompletionsPOST /v1/chat/completions |
Codex CLIbase_url; wire_api = "responses" | https://api.router.one/v1 | ResponsesPOST /v1/responses |
Claude CodeANTHROPIC_BASE_URL | https://api.router.one | Anthropic MessagesPOST /v1/messages |
Immersive TranslateCustom endpoint | https://api.router.one/v1/chat/completions | Chat CompletionsPOST /v1/chat/completions |
GitHub Copilot (VS Code)chatLanguageModels.json → models[].url; apiType: "chat-completions" | https://api.router.one/v1/chat/completions | Chat CompletionsPOST /v1/chat/completions |
OpenHandsBase URL (Advanced) / LLM_BASE_URL (GPT-5-family IDs use /v1/responses; see the guide) | https://api.router.one/v1 | Chat CompletionsPOST /v1/chat/completions |
NextChatBASE_URL / OpenAI Endpoint | https://api.router.one | Chat CompletionsPOST /v1/chat/completions |
CrewAIbase_url; custom_openai=True (or OPENAI_API_BASE) | https://api.router.one/v1 | Chat CompletionsPOST /v1/chat/completions |
Spring AIspring.ai.openai.base-url (2.0.x; 1.x uses the host root) | https://api.router.one/v1 | Chat CompletionsPOST /v1/chat/completions |
These are the configurations documented in the linked guides. A client can support other providers or APIs; verify the actual request path before changing the URL.
Cline
Connect Cline to Router One with an OpenAI-compatible provider
Setup guide →Aider
Configure Aider's model and OpenAI-compatible endpoint
Setup guide →LangChain
Configure LangChain ChatOpenAI for Router One
Setup guide →LlamaIndex
Configure LlamaIndex OpenAILike for Router One
Setup guide →Vercel AI SDK
Use Router One with the AI SDK's Chat Completions API
Setup guide →OpenAI SDK
Use the OpenAI SDK with Router One Chat Completions
Setup guide →Dify
Give every Dify app one model provider
Setup guide →Roo Code
Connect Roo Code through an OpenAI-compatible provider
Setup guide →OpenCode
Configure OpenCode's Router One provider and model IDs
Setup guide →Kilo Code
Connect Kilo Code through an OpenAI-compatible provider
Setup guide →Cursor
Bring your own key to Cursor through one endpoint
Setup guide →OpenClaw
Run OpenClaw on one endpoint with a hard spend cap
Setup guide →Zed
Add Router One models to Zed's Agent Panel
Setup guide →Continue
Configure Router One models in Continue's config.yaml
Setup guide →Open WebUI
Back Open WebUI with the whole catalog through one connection
Setup guide →LibreChat
Put the whole catalog behind one LibreChat endpoint
Setup guide →n8n
Configure n8n's OpenAI credential and model endpoint
Setup guide →Immersive Translate
Configure Immersive Translate's custom Chat Completions API
Setup guide →Pydantic AI
Connect Pydantic AI to Router One with an explicit chat model
Setup guide →GitHub Copilot
Bring Router One models into GitHub Copilot Chat in VS Code
Setup guide →OpenHands
Connect the OpenHands agent to Router One through its OpenAI-compatible provider
Setup guide →NextChat
Connect NextChat to Router One with a host-root BASE_URL
Setup guide →CrewAI
Connect CrewAI agents to Router One through one custom OpenAI-compatible endpoint
Setup guide →Spring AI
Connect Spring AI's OpenAI starter to Router One
Setup guide →Coding agents & desktop chat clients
Claude Code
Point Claude Code at the gateway and pay per token — reachable from mainland China without a VPN.
Read the guide →Codex CLI
Run OpenAI's Codex CLI on one Router One key, billed per token instead of per seat.
Read the guide →Cursor
Override Cursor's OpenAI base URL and keep every model family reachable from China.
Read the guide →Chatbox & Cherry Studio
One key in either desktop chat client reaches the whole model catalog.
Read the guide →All AI coding tools
Why one gateway sits behind every coding tool: one key to rotate, one place to see what each tool spent.
Read the guide →one-api / new-api relay stations
Running a relay station? Add Router One as a single OpenAI-compatible upstream channel.
Read the guide →A client that isn't listed here
Check which provider and API the client uses, and whether its URL field expects a base URL or a full request endpoint. Copy an exact model ID that supports that API from the catalog, then verify a simple request before enabling streaming or tools. The API reference documents the available endpoints.