Integrations
Use Rapid Router with the tools you already have
Every tool here speaks the OpenAI request shape, so the recipe is three facts: the base URL, a key, a model string. One connection, every model in the catalog, one balance.
Cursor can route its chat and composer through any OpenAI-compatible endpoint. Point it at Rapid Router and every model in the catalog is available inside the editor.
Cline has a built-in "OpenAI Compatible" provider. Three fields and every model on Rapid Router is available to the agent, with the spend visible in your dashboard per key.
Roo Code is a Cline fork with the same provider list. Choose OpenAI Compatible, enter the base URL and key, and switch models per mode (code, architect, ask) from the catalog.
Continue reads its models from a config file. Add one block per Rapid Router model you want in the picker; the provider is "openai" with an apiBase.
Aider talks to any OpenAI-compatible endpoint through environment variables. Prefix the model with openai/ so aider routes it to the OpenAI-shaped client.
ChatOpenAI takes a base_url. Nothing else in a LangChain app changes: chains, tools and agents run against Rapid Router models with the same code.
LlamaIndex's OpenAILike class exists for exactly this: an OpenAI-shaped endpoint that serves models OpenAI does not. Set api_base and the model string.
The AI SDK's OpenAI provider accepts a baseURL. Create one provider instance for Rapid Router and pass model strings from the catalog to streamText, generateText and the React hooks.
n8n's OpenAI credential has a Base URL field. Create one credential for Rapid Router and every OpenAI node, AI Agent node and chat model node in your workflows can use catalog models.
Open WebUI connects to OpenAI-compatible endpoints from its admin panel. Add Rapid Router as a connection and the whole catalog appears in the model selector for every user of your instance.
LibreChat supports custom endpoints in librechat.yaml. One block adds Rapid Router with its own name in the endpoint menu and a default model list.
Dify's "OpenAI-API-compatible" model provider takes a base URL, a key and a model name per model. Add each Rapid Router model you want available to app builders.
In Flowise, the ChatOpenAI Custom node (or ChatOpenAI with a BasePath) runs against any OpenAI-shaped endpoint. Set the base path and model name on the node.