Connect any LLM

Settings → Language model. Keys are encrypted on your machine.

ProviderBase URLExample model
openaihttps://api.openai.com/v1gpt-4.1-mini
anthropichttps://api.anthropic.com/v1claude-sonnet-5-5
geminihttps://generativelanguage.googleapis.com/v1beta/openaigemini-2.5-flash
groqhttps://api.groq.com/openai/v1llama-3.3-70b-versatile
openrouterhttps://openrouter.ai/api/v1openai/gpt-4.1-mini
deepseekhttps://api.deepseek.com/v1deepseek-chat
ollamahttp://localhost:11434/v1llama3.1
customyour URL–

Choose custom for any OpenAI-compatible endpoint, such as LM Studio, vLLM, Together, Mistral or Azure OpenAI. For a fully local setup, install Ollama and pick ollama.

Image model

The Media studio uses any OpenAI-compatible Images API, for example gpt-image-1 or dall-e-3. Set it in Settings → Language model → Image model.

From Claude or another agent

When an agent drives LinkedIn Agent over MCP, it can write the text itself with get_skill_prompt and save_draft. No model key is needed in that case.