SillyTavern with Claude, GPT and Gemini

Connect in three fields

SillyTavern speaks the OpenAI Chat Completion format. Point its custom source at avots.

Setup

Chat Completion Source:     Custom (OpenAI-compatible)
Custom Endpoint (Base URL): https://api.avots.ai/openai/v1
Custom API Key:             av_mcp_YOUR_KEY
Model:                      anthropic/claude-sonnet-4.6

Keep /v1 on the URL but do not append /chat/completions, SillyTavern adds that itself. If the endpoint serves /v1/models the Model becomes a dropdown, otherwise type the id. If a status check fails wrongly, enable Bypass API status check.

Example request

curl https://api.avots.ai/openai/v1/chat/completions \
  -H "Authorization: Bearer av_mcp_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4.6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

The same key also unlocks MCP tools

Your av_mcp_ key is not only for chat. avots also runs as an MCP server, so SillyTavern can call avots creative tools, image, video, music, talking avatars, on the same key and the same balance.

MCP setup guide →

Models and prices

Set the model field to any id below, or a lazy name like claude / gpt / gemini that maps to a sensible default.

* Price in ⚡ per 1,000,000 tokens, input / output (1000⚡ ≈ $1). Free models need a positive balance. Full list via GET /openai/v1/models.

Questions

Other clients