<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:wght@400;500;600&family=Inter:wght@400;500;600;700&family=STIX+Two+Text:ital,wght@0,400;0,500;0,600;0,700;1,400&family=Material+Symbols+Outlined:wght,FILL@400,0..1&display=swap" />
General chat clients

AnythingLLM

Self-hosted RAG and chat workspace.

AnythingLLM treats FreeTheAi as a `Generic OpenAI` provider. Type the alias, set the context window, save.

Base URLhttps://api.freetheai.xyz/v1
Recommended modelsolm/kimi-k2.7-code
Chat completions Streaming Tool calling
Get a free keyOfficial docsGitHub repo
Step by step

Connect AnythingLLM to FreeTheAi.

3 steps
  1. 1

    Open LLM Preference

    Click `Settings` in the sidebar, then `LLM Preference`.

  2. 2

    Pick Generic OpenAI

    Set `LLM Provider` to `Generic OpenAI` and fill in the form.

    text
    Base URL: https://api.freetheai.xyz/v1
API Key: PASTE_YOUR_FREETHEAI_KEY
Chat Model Name: olm/kimi-k2.7-code
Token context window: 50000
  3. 3

    Save

    Hit save. AnythingLLM will use FreeTheAi for chat workspaces.

Recommended aliases

Models that pair well with AnythingLLM.

  • olm/kimi-k2.7-code
  • glm/glm-5.1
  • bbl/gpt-5.5-mini

See the full live catalog at /models. Aliases are stable; pricing on the free tier stays $0.

Heads up

Common gotchas.

  • AnythingLLM does not auto-fetch the catalog for Generic OpenAI - you have to type the alias and context window manually.
  • The Embedding Preference tab is separate. Leave it on a working embedding provider unless FreeTheAi exposes embeddings on your plan.
Where to next

Keep building.

All setup guidesQuickstartCross-compatibility docsModel catalogAsk in Discord