Skip to main content
Connect OpenCode to GLM 5.3 Flash Unrestricted without copying an API key or editing a configuration file. Using another coding tool? Open Connect your coding tool to see the available setup options. You need OpenCode 1.x installed, Node.js 22 or newer available as node, and a Limitless account with owner or admin access to a workspace. Local integration testing used OpenCode v1.18.21; the upstream integration contract was also checked against v1.19.0.

​
Connect

Run this in your terminal:
  1. Your browser opens Limitless. Sign in if needed. If it does not open, follow the link printed in your terminal.
  2. Check that the browser shows the same connection code as your terminal. Only approve a connection you started yourself.
  3. Select the workspace and active project that should pay for requests, then choose Approve connection.
  4. Return to the terminal and wait for OpenCode to confirm the connection. Start a new OpenCode session to load the configuration.
Limitless supplies the endpoint, glm-5.3-flash-unrestricted model, and its token limits. Both OpenCode’s main model and its small model use this GLM model. Your existing user or project OpenCode configuration can override these defaults; if another model remains selected, check those settings or select Limitless / GLM 5.3 Flash Unrestricted through /models.

​
Your key and usage

The connection creates a dedicated key named OpenCode, valid for 90 days. It has the same inference permissions as a normal project API key; it is not restricted to GLM. Usage belongs to your selected project and uses the workspace’s credits, spending caps and request limits. In the sandbox, add sandbox credits before making requests. Real model inference still runs even though payments use test money. See Billing. Manage or revoke the key in API keys. After revoking or expiring a key, run the connection command again to create a replacement.

​
If connection or inference fails

  • Expired code: run the command again and use the new browser link. A request lasts ten minutes.
  • Interrupted connection: check the terminal’s connection message; a zero exit code alone does not establish success. If the terminal stopped after your approval, inspect API keys and revoke any new unused OpenCode key before retrying. A key may have been issued before OpenCode saved it.
  • Insufficient permissions: choose a workspace you own or administer and an active project.
  • Project policies: GLM cannot evaluate published project policies. Choose a project without applicable policies.
  • Model unavailable: connecting does not start or reserve a GPU. This self-hosted model must be running and ready; it does not automatically fall back to another provider. A successful connection confirms credentials, not current model availability.
  • Different model or endpoint: local OpenCode settings take precedence over the supplied defaults. Review user and project configuration before retrying.