OpenRouter
Unified API key for 500+ models across Anthropic, OpenAI, Google, Meta, DeepSeek, and more.
Limitcode supports 40+ direct APIs, enterprise cloud gateways, account sign-in, existing CLI sessions, and local OpenAI-compatible runtimes. Each route has different billing, privacy, and account-risk boundaries.
Requests go directly from Sublime Text to the provider or gateway you select. Configure any provider via Ctrl+Alt+K or by adding its settings ID to api_keys in Limitcode.sublime-settings.
Unified API key for 500+ models across Anthropic, OpenAI, Google, Meta, DeepSeek, and more.
Direct API key for Claude Sonnet 5, Claude Opus 5.5, and Claude Fable 5.1.
Direct API key for GPT-6, GPT-6 Astra, GPT-6 Sol, and reasoning series.
Google AI Studio API key for Gemini 4 Argon and Gemini 3.7 Flash.
Direct API key (api.deepseek.com) for DeepSeek V4 and reasoning models.
Direct API key (api.x.ai/v1) for Grok 4.20 and coding models.
Direct API key (api.mistral.ai/v1) for Mistral Large, Codestral, and Devstral.
Direct API key (api.groq.com/openai/v1) for ultra-fast LPU inference.
Direct API key (api.cerebras.ai/v1) for high-speed wafer-scale inference.
Direct API key (api.together.xyz/v1) for open-weight coding and chat models.
Direct API key (api.deepinfra.com/v1/openai) for serverless open models.
Direct API key (api.moonshot.ai/v1) for Kimi K2.5 and long-context models.
DashScope API key for Qwen3 Coder and Qwen models.
Direct API key for Xiaomi MiMo reasoning and coding models.
Direct API key (integrate.api.nvidia.com/v1) for NVIDIA-hosted inference.
Direct API key (api.perplexity.ai) for Sonar online and reasoning models.
Direct API key (api.venice.ai/api/v1) for privacy-focused model inference.
Direct API key for Command R+ and enterprise Cohere models.
Curated coding gateways (opencode.ai/zen/v1 and opencode.ai/zen/go/v1).
AWS Bedrock Converse API for enterprise-hosted Claude, Llama, and Titan models.
Microsoft Azure Cognitive Services endpoint and key.
Enterprise Google Cloud Vertex endpoints for Gemini and Claude models.
Serverless edge inference via Cloudflare Workers AI.
Unified routing and caching via ai-gateway.vercel.sh/v1.
Observability and proxy gateway via oai.hconeai.com/v1.
Enterprise GitLab AI (gitlab.com/api/v4/ai) and SAP AI Core (api.ai.sap.com/v1) endpoints.
Any self-hosted vLLM, TGI, corporate proxy, or custom /v1/chat/completions URL.
These integrations depend on provider-controlled accounts and service behavior. Availability, quotas, and compatibility can change independently of Limitcode.
Sign in with GitHub via Limitcode: Login with GitHub Copilot (Ctrl+Alt+B). Availability and model access depend on an eligible Copilot subscription.
Sign in via Limitcode: Login with Codex (Ctrl+Alt+Z) using an OpenAI browser login and local callback. Account eligibility and quotas are controlled by OpenAI.
Sign in via Limitcode: Login with Google Antigravity (Ctrl+Alt+Shift+G) to access models available to the signed-in account.
CLI bridges require the provider's command-line tool to be installed and authenticated before Limitcode starts the task.
Reuses an existing local claude login session from your terminal (Ctrl+Alt+E).
Reuses an existing local codex login session from your terminal.
CLI-backed providers may run their own internal agent loop and tools, outside some Limitcode permission controls.
Local inference can remain on your machine when the endpoint and model are local. Tool calling depends on the endpoint and model implementation.
Default local OpenAI-compatible endpoint at http://localhost:11434/v1.
Local server and models managed by LM Studio at http://localhost:1234/v1.
Local or remote proxy gateway at http://localhost:4000/v1.
User-supplied OpenAI-compatible base URL in provider_base_urls.
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 →