Laras RouterDocs
Console

Integrations

Integrations

Use Laras Router from coding agents, editors, and SDKs that support an OpenAI-compatible or Anthropic Messages base URL, with a verified setup guide for each.

On this page

Laras Router implements the OpenAI Chat Completions API and the Anthropic Messages API. If a tool lets you set a custom OpenAI-compatible or Anthropic base URL, it can send its requests here. Each guide below was checked against the tool's own documentation.

Connection details

In almost every tool, the setup comes down to the same values:

SettingValue
Base URLhttps://api.larasrouter.com/v1 (OpenAI format) · https://api.larasrouter.com (Anthropic format, which adds /v1/messages itself)
API formatOpenAI Chat Completions, or Anthropic Messages
API keyYour key from the console (lr_live_…), sent as Authorization: Bearer; x-api-key is also accepted
Modeldeepseek-flash
Per-key limits300 requests / min · 16 concurrent (rate limits)
SupportedStreaming, tool calling
Not supportedImage input

Create a separate API key for each tool, with a monthly budget, so you can see and cap what each one spends.

Agents

Claude Code

Anthropic's coding agent for the terminal, through the Anthropic Messages API.

OpenCode

Open-source coding agent for the terminal.

Aider

AI pair programming in your terminal, working on your git repo.

Goose

Open-source agent with a desktop app and a CLI.

Hermes Agent

Open-source agent from Nous Research that runs in your terminal.

OpenClaw

Self-hosted personal AI assistant with a gateway and chat apps.

Pi

Terminal coding agent with custom providers in models.json.

Oh My Pi

Terminal coding agent (omp) with custom providers in models.yml.

Editors and extensions

Cline

Coding agent extension for VS Code and other editors.

Kilo Code

Open-source coding agent for VS Code, JetBrains, and the CLI.

Continue

Open-source AI coding extension for VS Code and JetBrains.

Zed

Code editor with a built-in AI agent panel.

SDKs

OpenAI SDKs

The official OpenAI libraries for Python and Node.js.

Vercel AI SDK

TypeScript toolkit for AI apps, through its OpenAI-compatible provider.

LangChain (Python)

ChatOpenAI from the langchain-openai package.

In development

  • Codex CLI uses the OpenAI Responses API.

Laras Router does not implement the Responses API yet, so Codex CLI cannot connect. Support is in development.

Not covered

  • Cursor does not document a way to point its models at a custom OpenAI-compatible base URL, so there is no guide we can verify.
  • Roo Code has been discontinued.

Your tool is not listed?

Look for a setting named "OpenAI-compatible provider", "custom endpoint", or "custom base URL" (sometimes OPENAI_BASE_URL) and use the connection details above. Keep in mind that deepseek-flash accepts text only, so turn off image or vision features. A tool that only speaks the Responses API will not work yet.

Stuck on a setup? Email [email protected] with the tool name and the X-Laras-Request-ID of a failed request.