Integrations

Every tool, app and SDK with a Modellane setup guide, grouped by kind, with the API format and the endpoint each one uses.

Modellane speaks three API formats: OpenAI Chat Completions, OpenAI Responses and Anthropic Messages. Most coding agents, chat apps and SDKs connect with a base URL and a key.

Modellane serves three request formats on the same models, keys and prices. Each tool below uses one of them; the guide for each tool lists the exact settings.

Formats and endpoints#

The label under each tool's name above is the format it uses: chat is Chat Completions, responses is Responses and messages is Messages.

FormatBase URLEndpoint
OpenAI Chat Completionshttps://usemodellane.com/v1POST /v1/chat/completions
OpenAI Responseshttps://usemodellane.com/v1POST /v1/responses
Anthropic Messageshttps://usemodellane.comPOST /v1/messages

Every setup needs the same three things: the base URL, a key from API keys and a model id such as lane-1 from Models & pricing. Most tools cannot read a model's context length from the API, so set it by hand from the models table when a tool asks for it.

Coding agents depend on tool calls. Pick a model that lists Tool calls in Models & pricing, and one with a long context, since agents send whole files and tool results with every turn.

Images in every tool#

Another tool#

Any tool that lets you set a custom OpenAI base URL works with the Chat Completions values above, and any tool built on the Anthropic SDKs works with the Messages values. Send one short prompt after you save the settings: a reply means the base URL, key and model id are right. A 401 means the key is wrong, and a 404 with model_not_found means the model id is not in Models & pricing.