Providers

Cloud providers using API keys#

Currently, the following cloud providers are supported:

For all the providers, an API key is needed. Note that this is charged separately from the subscription you might already have (e.g. Claude Pro). If that might be a problem, consider using either a subscription provider (see below) or using it externally via MCP.

Do note that most other LLM providers (e.g. OpenRouter, Groq, Mistral) can still be used in Trilium via the OpenAI-compatible custom endpoint (see below).

If you are using a proxy or gateway, you can also configure the base URL, otherwise the default will be used.

Subscription-based providers#

Trilium integrates multiple Subscription-based providers:

  • Claude Code by reusing your CLI.
  • GitHub Copilot by reusing your CLI's ACP.
  • Google Antigravity by downloading and setting up an ACP for Trilium.

Local/self-hosted providers#

Local or self-hosted providers are a free alternative which respects your privacy but requires specific hardware.

Trilium directly supports the following local providers:

  • Ollama
    • Generally Ollama runs in the background so it should be directly usable in Trilium as long as the models are downloaded (e.g. ollama pull llama3.2).
  • LM Studio
    • The OpenAI-compatible server is disabled by default in LM Studio installations. First download your desired models through the graphical interface, then go to Settings → Developer and toggle Developer mode. On the left there will be a new Developer tab, with a toggle to start it up.

Even for local providers that are not directly supported by Trilium, you can still use a custom endpoint (see below).

Custom endpoints#

If your desired hosted (e.g. OpenRouter, Groq, Mistral) or local LLM provider is not listed in Trilium, you can use the dedicated OpenAI-compatible provider from the Custom endpoint section.

This allows you to set the base URL to an OpenAI-compatible API, with an optional API key if required by the service.

Enter the base URL exactly as the service documents it, including its version path, such as https://api.groq.com/openai/v1 or https://open.bigmodel.cn/api/paas/v4. Only a bare host such as http://localhost:8080 is completed with /v1.

For custom endpoints, the pricing of the models is not known so the cost of a conversation will not be displayed; this is especially relevant for hosted providers.