Custom Endpoints

Add custom AI providers like OpenRouter, Ollama, and Anthropic-compatible gateways to IntelliAsk using intelliask.yaml

IntelliAsk supports OpenAI API-compatible services as custom endpoints. It also supports Anthropic-compatible custom endpoints with provider: "anthropic". In the stack deployment you configure endpoints in config/intelliask.yaml and store API keys in config/.env (referenced with ${VAR_NAME} syntax).

Which File Does What?

Custom endpoint setup involves two configuration files:

  1. config/intelliask.yaml -- Defines your custom endpoints (name, API URL, models, display settings). It is already mounted into the IntelliAsk container by intelliask.compose.yml.
  2. config/.env -- Stores sensitive values like API keys (referenced from intelliask.yaml using ${VAR_NAME} syntax).

For a full overview of how configuration is organised, see Configuration & secrets.

Before You Start

This guide assumes you have a provisioned IntelliAsk stack running. If not, complete Installation first.

Step 1. Open the mounted config

The stack already mounts config/intelliask.yaml into the container, so there's nothing extra to wire up — just edit that file on the host.

Here is an example with OpenRouter, Ollama, and an Anthropic-compatible gateway:

version: 1.3.13
cache: true
endpoints:
  custom:
    - name: 'OpenRouter'
      apiKey: '${OPENROUTER_KEY}'
      baseURL: 'https://openrouter.ai/api/v1'
      models:
        default: ['meta-llama/llama-3-70b-instruct']
        fetch: true
      titleConvo: true
      titleModel: 'meta-llama/llama-3-70b-instruct'
      dropParams: ['stop']
      modelDisplayLabel: 'OpenRouter'
    - name: 'Ollama'
      apiKey: 'ollama'
      baseURL: 'http://host.docker.internal:11434/v1/'
      models:
        default: ['llama3:latest', 'command-r', 'mixtral', 'phi3']
        fetch: true
      titleConvo: true
      titleModel: 'current_model'
    - name: 'Claude-Compatible'
      provider: 'anthropic'
      apiKey: '${ANTHROPIC_API_KEY}'
      baseURL: 'https://api.anthropic.com'
      headers:
        anthropic-version: '2023-06-01'
      models:
        default: ['claude-sonnet-4-5']
        fetch: false
      titleConvo: true
      titleModel: 'claude-sonnet-4-5'

Browse all compatible providers in the AI Endpoints section. For the full field reference, see Custom Endpoint Object Structure.

Anthropic-Compatible Endpoints

Use provider: "anthropic" only for endpoints that speak the native Anthropic Messages API. For OpenAI-compatible gateways that merely expose Anthropic models, omit provider and use the regular OpenAI-compatible custom endpoint shape.

API Key Configuration

When configuring API keys in custom endpoints, you have three options:

  1. Environment variable (recommended): apiKey: "${OPENROUTER_KEY}" -- reads from .env
  2. User provided: apiKey: "user_provided" -- users enter their own key in the UI
  3. Direct value (not recommended): apiKey: "sk-your-actual-key" -- stored in plain text

Step 3. Set Environment Variables

Add the API keys referenced in your intelliask.yaml to config/.env:

OPENROUTER_KEY=your_openrouter_api_key

Each ${VARIABLE_NAME} in intelliask.yaml must have a matching entry in config/.env.

Step 4. Restart and Verify

After editing the config or .env, restart IntelliAsk for changes to take effect:

intelliask restart intelliask

Open IntelliAsk in your browser. Your custom endpoints should appear in the endpoint selector dropdown.

Not Seeing Your Endpoint?

Check the server logs for configuration errors:

intelliask logs intelliask

Common issues: YAML syntax errors or missing env vars. Validate your YAML with the YAML Validator.

OpenRouter Still Does Not Show Up

For OpenRouter specifically, verify the chain:

  1. config/.env has OPENROUTER_KEY=...
  2. intelliask.yaml has apiKey: "${OPENROUTER_KEY}" under the OpenRouter custom endpoint

Then restart with:

intelliask restart intelliask

If the endpoint appears but returns 402 Payment Required, the request reached OpenRouter successfully and the issue is usually account credits, billing, or model availability on OpenRouter.

Next Steps

AI Endpoints

Browse all compatible AI providers with example configurations

→

Configuration YAML Guide

Full setup guide and reference for the config file

→

Last updated on