SillyTavern
Power-user roleplay frontend with deep prompt control.
SillyTavern uses its own Connection Profile system. Switch the API to Chat Completion with `Custom (OpenAI-compatible)` and SillyTavern will handle streaming and presets.
Connect SillyTavern to FreeTheAi.
- 1
Open the API panel
Click the plug icon in SillyTavern, the first icon in the right toolbar.
- 2
Pick the right API
Set `API` to `Chat Completion`. Set `Chat Completion Source` to `Custom (OpenAI-compatible)`.
- 3
Fill the endpoint and key
Use the FreeTheAi base URL and the key from /signup. SillyTavern auto-appends /chat/completions, so do not add it manually.
text Custom Endpoint (Base URL): https://api.freetheai.xyz/v1 Custom API Key: PASTE_YOUR_FREETHEAI_KEY - 4
Pick a model
Type or paste a FreeTheAi alias into `Enter a Model ID`. The dropdown will populate after the first connect.
text bbl/gpt-5.5-mini - 5
Save the profile
Save the Connection Profile so SillyTavern remembers FreeTheAi between sessions.
Models that pair well with SillyTavern.
bbl/gpt-5.5-miniglm/glm-5.1olm/kimi-k2.7-code
See the full live catalog at /models. Aliases are stable; pricing on the free tier stays $0.
Common gotchas.
- If a Test Message returns 404, append `/v1` to the endpoint. Never add `/chat/completions`.
- Use Strict Prompt Post-Processing for Claude-style models so SillyTavern alternates user and assistant correctly.
- FreeTheAi is rate-limited per minute. Lower SillyTavern's parallel generation if you see frequent 429s.