Skip to main content
Open Connect your coding tool in the Limitless console. Choose your tool to see its setup instructions and current availability.

​
Connect a terminal tool

OpenCode, Claude Code, and Codex use a terminal command with browser approval. You need the selected tool and Node.js 22 or newer installed, plus owner or admin access to a Limitless workspace. Cursor and Cline use the guided settings flow below; they do not require Node.js or a terminal command. The Claude Code and Codex flows are enabled per deployment. The setup page shows which connections are available. Live model checks used Claude Code 2.1.226 and Codex CLI 0.162.1 on macOS; Windows setup has not been qualified.
  1. Choose your tool in the console and copy its setup command.
  2. Run it in your terminal. A browser window opens to Limitless; sign in if prompted.
  3. Match the connection code in your browser with the one in your terminal.
  4. Choose the workspace and project that should pay for requests, then select Approve connection.
  5. Return to the terminal and wait for setup to finish. Follow its instructions to start a coding session.
Automatic setup configures a dedicated API key, the Limitless endpoint, and GLM 5.3 Flash Unrestricted. The console only offers automatic setup when that integration is enabled. Tools marked Coming soon do not yet have an available setup command.

​
OpenCode

OpenCode uses its native provider login:
See the OpenCode guide for versions, configuration precedence, and troubleshooting.

​
Claude Code

When enabled, run:
Approve the connection in your browser, then start a new session with claude. Setup configures your global Claude Code user settings for Limitless, retaining unrelated settings and making a backup of the previous file. It respects CLAUDE_CONFIG_DIR when set; otherwise it uses ~/.claude/settings.json. A local credential helper supplies the API key. The key is kept separately from the settings file and is not placed in the setup command or browser URL. Project or managed settings can override user settings. The model is GLM 5.3 Flash Unrestricted, including requests made through Claude Code’s small-model setting. This connection does not provide a Claude model.

​
Codex CLI

When enabled, run:
Codex setup requires Codex CLI 0.162.1 or newer. After browser approval, it creates a named Limitless profile, a local model catalog, and a command-based credential helper. It respects CODEX_HOME and preserves your existing default configuration. Start a session with:
The profile disables hosted web search and multi-agent delegation (multi_agent = false). Text, function tools, and Codex’s custom apply_patch tool are supported. Setup targets Codex CLI; desktop setup is not included in this flow.

​
Connect Cursor or Cline

Choose Cursor or Cline on the connection page. Select the workspace and project in the console, then create a dedicated key or use an existing project key. New keys expire after 90 days. Copy a newly created key before leaving the page; it cannot be displayed again later. Copy the base URL and model ID into your tool’s settings as described below. These guided flows use the tools’ supported settings interfaces. They do not import settings automatically. The instructions are checked against official documentation; a live Limitless coding task in Cursor or Cline has not yet been qualified.

​
Cursor

  1. Open Cursor Settings → Models → API Keys.
  2. Paste your Limitless key into OpenAI API Key, save it, and enable Use OpenAI API Key.
  3. Enable Override OpenAI Base URL and set it to https://trylimitless.ai/v1.
  4. Add and enable a custom model with the exact ID glm-5.3-flash-unrestricted.
  5. Restart Cursor, open a new chat, and select that custom model.
This follows Cursor’s custom-model setup instructions. Use the exact Limitless ID above, rather than a built-in GLM entry. You need a Cursor plan that supports custom API keys. Organization administrators can restrict personal keys or the OpenAI provider; see Cursor’s model access controls. Turn off the base URL override when returning to Cursor’s built-in OpenAI models. Tab completion continues to use Cursor’s own models. Cursor routes custom-key requests through its backend; its current API-key guidance explains billing and data handling. Limitless’s 512K server context does not establish that Cursor uses the full window or supports every Agent feature.

​
Cline

  1. Open the Cline extension → Settings and choose OpenAI Compatible as the API Provider.
  2. Paste your Limitless key into the API-key field.
  3. Set Base URL to https://trylimitless.ai/v1 and Model ID to glm-5.3-flash-unrestricted.
  4. Open Model Configuration and set the values below explicitly.
  5. If you use separate models for Plan and Act, select and configure this model in both modes. Save the settings and start a new task.
Cline’s custom-model defaults can differ from these limits and may enable images. This model accepts text only. See Cline’s OpenAI Compatible guide. A separate proxy, Cline CLI installation, or Node.js installation is not needed for these settings.

​
Kilo

Kilo remains marked Coming soon until its connection is qualified. Use the connection page for current availability.

​
Supported coding features

The self-hosted GLM model supports text, streaming, and tool calls. Claude Code uses SGLang’s native Messages API; Codex uses its native Responses API. Messages token counting is also available when these integrations are enabled. No separate local proxy is required. The model has a combined 524,288-token context and an 8,192-token output limit. These are server limits; a coding tool may use a smaller context. Hosted web search/fetch, images and other multimodal inputs, and stored server-side sessions are not supported. Coding tools send conversation history with each request. See API compatibility.

​
Keys and usage

Each new key created by a connection flow is named after the tool. It expires after 90 days and uses the selected workspace’s credits, spending caps, and request limits. It has normal project inference permissions; it is not limited to a single model. Reusing an existing key retains that key’s current expiry and permissions. Manage or revoke connection keys in API keys. To replace a revoked or expired key, repeat your tool’s connection flow and update its saved key. Terminal connection codes expire after ten minutes. If automatic setup is interrupted after browser approval, check API keys and revoke any unused key before retrying. Creating a key does not confirm that an IDE is configured. Send a request from your tool and check Activity for its outcome. Connecting does not start or reserve model capacity. GLM Flash must be online and ready to accept requests, and does not automatically fall back to another provider.

​
Other OpenAI-compatible tools

For tools with a custom OpenAI-compatible provider setting, create a project API key and use: Check that your tool supports Chat Completions, streaming, and function tools. A custom base URL alone does not guarantee compatibility with every API feature. See Compatibility.