Dashboard

AnythingLLM

Connect AnythingLLM to iCreat via OpenAI-compatible API

AnythingLLM is a local LLM stack with RAG support that can be self-hosted. Configure iCreat as a custom LLM provider through the OpenAI-compatible API.

Prerequisites

  • An iCreat API Key (replace <sk-your-token> below with your key)
  • AnythingLLM installed or deployed
  • Network access to https://api.icreat.ai

Setup

  1. Start AnythingLLM
  2. Go to Settings → LLM Configuration (or Preferences)
  3. Select Custom API or OpenAI-compatible
  4. Fill in the required fields:
Setting Value
Endpoint https://api.icreat.ai/v1/llm
API Key Your iCreat API Key (<sk-your-token>)
Model name gpt-5.6 (or your chosen model ID)
  1. Click Test connection to verify
  2. Click Save and restart AnythingLLM

Advanced configuration (config.json)

Advanced users can edit the AnythingLLM config file directly:

{
  "llm": {
    "provider": "openai-compatible",
    "endpoint": "https://api.icreat.ai/v1/llm",
    "model": "gpt-5.6",
    "apiKey": "<sk-your-token>",
    "temperature": 0.7,
    "maxTokens": 2048,
    "timeout": 30000
  }
}

Security

Do not commit config files containing real API Keys to Git. Use environment variables or a secrets manager in production.

Verify the connection

Send a test message in AnythingLLM. You should receive a response from your selected iCreat model within a few seconds. You can also confirm the call in Usage Logs on the iCreat console.

More resources