AnythingLLM con Claude, GPT y Gemini

Connect in three fields

AnythingLLM tiene un proveedor Generic OpenAI para cualquier endpoint compatible con OpenAI. Apúntalo a avots.

Setup

LLM Provider:         Generic OpenAI
Base URL:             https://api.avots.ai/openai/v1
API Key:              av_mcp_YOUR_KEY
Chat Model Name:      anthropic/claude-sonnet-4.6
Token context window: 200000
Max Tokens:           4096

Generic OpenAI no tiene descubrimiento automático de modelos, escribe el Chat Model Name exacto a mano. Configura correctamente la Token context window y Max Tokens, los valores erróneos truncan en silencio o dan error. Esto configura solo el LLM de chat, los embeddings son un proveedor aparte.

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 AnythingLLM 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.

Preguntas

Otros clientes