OpenAI
Direct API key
Connection guide
Bring the model access you already use.
Limitcode supports direct APIs, account sign-in, existing CLI sessions, and local OpenAI-compatible runtimes. Each route has different billing, privacy, and account-risk boundaries.
API keyDirect provider billing OAuthAccount eligibility applies CLIReuse a local login LocalYour endpoint, your runtime
01 — Direct APIs
Use a provider-issued key.
Requests go from the plugin to the provider or gateway you select. Usage, rates, limits, and model availability remain with that service.
Anthropic
Direct API key
Google Gemini
Google AI API key
OpenRouter
Models enabled for your account
DeepSeek
Direct OpenAI-compatible API
Mistral AI
Direct OpenAI-compatible API
Other compatible APIs
Groq, xAI, Together, and custom gateways
02 — Account & OAuth
Sign in when a provider supports account access.
These integrations depend on provider-controlled accounts and service behavior. Availability, quotas, and compatibility can change independently of Limitcode.
Account
GitHub Copilot
Sign in with GitHub. Availability and model access depend on an eligible Copilot account or subscription.
Account
OpenAI Codex OAuth
Uses an OpenAI browser login and a local callback. Account eligibility, quotas, and endpoint behavior are controlled by OpenAI and may change.
Experimental · elevated risk
Google Antigravity OAuth **
Uses Google OAuth and Antigravity/Code Assist service behavior to access models available to the signed-in account.
03 — CLI sessions
Reuse an official local CLI login.
CLI bridges require the provider's command-line tool to be installed and authenticated before Limitcode starts the task.
Claude Code CLI
Uses an existing local `claude login` session.
Codex CLI
Uses an existing local `codex login` session.
CLI-backed providers may run their own internal agent loop and tools, outside some Limitcode permission controls.
04 — Local & custom
Point at your own runtime.
Local inference can remain on your machine when the endpoint and model are local. Tool calling depends on the endpoint and model implementation.
Ollama
Default local OpenAI-compatible endpoint
LM Studio
Local server and models managed by LM Studio
LiteLLM
Local or remote provider gateway
Custom endpoint
User-supplied OpenAI-compatible base URL
Before connecting
Know where the request goes.
Prompts and any file context or tool results included in a request are sent to the selected provider or endpoint. Credentials are stored in Sublime Text settings, not an operating-system keychain. Review the provider's terms before connecting a work or primary personal account.
Return to Limitcode Pro →