SillyTavern Free API Setup in 2026 (and the "Bad Request" Fix)
By Vibhek SoniUpdated 1 min read
This post is about the old free tier
FreeTheAI closed its free tier for most accounts on November 10, 2026, so parts of this post no longer apply. Paid models work the same way through the same API. Browse models
Quick answer
In SillyTavern open API Connections, choose Chat Completion with the Custom (OpenAI-compatible) source, enter https://api.freetheai.org/v1 as the endpoint, your FreeTheAI key, and a model like fta/zai/glm-5.3, then set Prompt Post-Processing to Semi-strict.
Key takeaways
- Use the base URL ending in /v1; SillyTavern adds /chat/completions itself.
- Semi-strict Prompt Post-Processing fixes most "Bad Request" errors.
- Save the setup as a Connection Profile to switch models in one click.
The settings
| Field | Value |
|---|---|
| API | Chat Completion |
| Chat Completion Source | Custom (OpenAI-compatible) |
| Custom Endpoint (Base URL) | https://api.freetheai.org/v1 |
| Custom API Key | Your full ftai_... key |
| Model ID | fta/zai/glm-5.3 |
| Prompt Post-Processing | Semi-strict (alternating roles) |
Step by step
- Click the plug icon in the top bar to open API Connections.
- Set API to Chat Completion and Chat Completion Source to Custom (OpenAI-compatible).
- Paste the base URL into Custom Endpoint. Do not add /chat/completions; SillyTavern does that.
- Paste your key into Custom API Key, type or pick a model ID, and press Connect.
- Set Prompt Post-Processing to Semi-strict.
- Do today's check-in and start chatting.
Fixing "API returned an error: Bad Request"
With Prompt Post-Processing set to None, SillyTavern can send a chat that has only the system prompt and the character's greeting, with no message from you. Some models refuse that and answer "Bad Request". Setting Prompt Post-Processing to Semi-strict makes sure every request carries a message from you, and the error goes away.
Other common problems
- No models appear after connecting: type the model ID by hand, and check that you did today's check-in.
- Replies cut off: raise Max Response Length in the sampler panel.
- Unauthorized: paste the full 53-character key; the short prefix in your key list does not work.
Frequently asked questions
What base URL does SillyTavern need?
https://api.freetheai.org/v1. SillyTavern appends /chat/completions itself.
How do I fix "Bad Request" in SillyTavern?
Set Prompt Post-Processing to Semi-strict in API Connections, then try again.
Which model should I use in SillyTavern?
fta/zai/glm-5.3 is the best default. See our comparison of the best free roleplay models for alternatives.
Was this post helpful?
About the author
Vibhek Soni founded FreeTheAI and builds and runs its API. He answers the support tickets these posts come from.
Published
Try the FreeTheAI API
Create an account, add funds, and make an API key. One key works with every model.
Create an account