Roleplay frontend · configuration guide + live pricing · sign up for trial credit
SillyTavern connects through Chat Completion → Custom (OpenAI-compatible); long-context models (Claude / Gemini families) work best for roleplay.
SillyTavern in one line: Chat Completion → Custom endpoint; long-context models fit roleplay. Recommended models and their market floor prices are in the table below; the full catalog is at https://321ai.cc/en/models/.
| Setting | Value | Notes |
|---|---|---|
API type | Chat Completion (not Text Completion) | plug icon at the top |
Chat Completion Source | Custom (OpenAI-compatible) | |
Custom Endpoint | https://321ai.cc/v1 | Base URL, include /v1 |
API Key | API key from the console | |
Model | enter the model name manually after connecting |
1. Top plug icon → API Connections → choose Chat Completion
2. Set Chat Completion Source to Custom (OpenAI-compatible), fill in the Custom Endpoint and API Key
3. Test the connection, then type the platform model name under Model
| What | Where | Notes |
|---|---|---|
| Live market floor pricing | https://321ai.cc/en/models/ | input per 1M tokens, per-supplier quotes on the marketplace |
Prices are the multi-supplier market floor and move in realtime; see all model prices →
Roleplay generally favors long-context models (Claude / Gemini families); go by each model's live price and upstream self-check records on the marketplace page.
Confirm the API type is Chat Completion rather than Text Completion, and that the endpoint includes /v1.