Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/janhq/jan/llms.txt

Use this file to discover all available pages before exploring further.

Jan supports integrating with remote AI models from various providers, allowing you to use powerful cloud models through Jan’s interface while maintaining a unified experience with your local models.

​
Supported Providers

Jan integrates with the following remote model providers:

OpenAI

GPT-4o, o3, and other OpenAI models

Anthropic

Claude Opus, Sonnet, and Haiku models

Google

Gemini 1.5 and 2.0 series models

Groq

High-performance LLM inference

OpenRouter

Unified access to multiple providers

Others

Cohere, Mistral AI, HuggingFace, and more

​
General Setup Process

The setup process is similar across all providers:
1

Get Your API Key

Visit your chosen provider’s website and create an API key:
Ensure your API key has sufficient credits and access to the models you want to use.
2

Configure Jan

  1. Navigate to the Settings page in Jan
  2. Under Model Providers, select your provider
  3. Insert your API Key
  4. Click Save or Apply
3

Start Using Remote Models

  1. Open any existing chat or create a new one
  2. Select a remote model from the model selector
  3. Start chatting - Jan will route your requests to the remote provider

​
OpenAI Integration

Jan supports all OpenAI models, including GPT-4o, o3, and custom fine-tuned models.

​
Configuration Example

# Test your OpenAI integration
curl https://api.openai.com/v1/models \
  -H "Authorization: Bearer YOUR_OPENAI_API_KEY"

​
Available Models

Jan automatically includes popular OpenAI models. To use a specific model:
  • See the list of available models in OpenAI Platform
  • The model ID must match exactly (e.g., gpt-4o, gpt-4-turbo)

​
Anthropic Integration

Access Claude’s Opus, Sonnet, and Haiku models through Jan.

​
Available Models

  • Claude Opus 4: claude-opus-4@20250514
  • Claude Sonnet 4: claude-sonnet-4@20250514
  • Claude 3.5 Haiku: claude-3-5-haiku@20241022
See the complete list in Anthropic’s documentation.

​
Google (Gemini) Integration

Use Google’s Gemini models for multimodal AI capabilities.

​
Available Models

  • Gemini 1.5 Pro: gemini-1.5-pro
  • Gemini 2.0 Flash: gemini-2.0-flash-lite-preview
Check Google’s models page for the latest available models.

​
Groq Integration

Groq provides high-performance inference for open-source models.

​
Available Models

  • Llama 3.3 70B: llama-3.3-70b-versatile
  • Mixtral: Various Mixtral models
  • Llama 2: LLaMA 2 series models
See the full list in Groq’s documentation.

​
OpenRouter Integration

OpenRouter provides unified access to multiple AI model providers through a single API.

​
Why Use OpenRouter?

  • Access models from Anthropic, Google, Meta, and more with one API key
  • Competitive pricing across providers
  • Several free models available
  • Simplified billing and management

​
Model Format

OpenRouter uses the format: organization/model-name Examples:
  • Claude 4 Opus: anthropic/claude-opus-4
  • Google Gemini 2.5 Pro: google/gemini-2.5-pro-preview
  • DeepSeek R1: deepseek/deepseek-r1-0528
Browse all available models at OpenRouter’s Model Reference.

​
Adding Custom Models

If you want to use a specific remote model that isn’t listed in Jan:
1

Find the Model ID

Check your provider’s documentation for the exact model identifier
2

Add the Model

Follow the instructions in Jan’s Add Cloud Models guide
3

Configure Model Settings

Set the id property to match the provider’s model name exactly

​
Architecture Overview

Jan’s remote model integration is built on a clean architecture: 
// RemoteOAIEngine handles authentication and headers
abstract class RemoteOAIEngine extends OAIEngine {
  apiKey?: string
  
  override async headers(): Promise<HeadersInit> {
    return {
      ...(this.apiKey && {
        'Authorization': `Bearer ${this.apiKey}`,
        'api-key': `${this.apiKey}`,
      }),
    }
  }
}
This architecture ensures:
  • Consistent authentication across providers
  • Easy integration of new providers
  • Unified interface for local and remote models

​
Troubleshooting

​
API Key Issues

  • Verify your API key is correct and not expired
  • Check if you have billing set up on your provider account
  • Ensure you have access to the model you’re trying to use

​
Connection Problems

  • Check your internet connection
  • Verify the provider’s system status
  • Look for error messages in Jan’s logs

​
Model Unavailable

  • Confirm your API key has access to the model
  • Check if you’re using the correct model ID
  • Verify your account has the necessary permissions
  • Some models may have regional restrictions

​
Rate Limits

  • Most providers implement rate limits
  • Check your provider’s dashboard for current usage
  • Consider upgrading your plan for higher limits
Remote model requests consume API credits and require an internet connection. Be mindful of usage costs and privacy considerations when using cloud-based models.

​
Best Practices

  1. API Key Security
    • Never share your API keys
    • Store keys securely in Jan’s settings
    • Rotate keys periodically
  2. Cost Management
    • Monitor your usage through provider dashboards
    • Set up billing alerts
    • Use local models for development and testing
  3. Privacy Considerations
    • Be aware that remote models process data in the cloud
    • Use local models for sensitive information
    • Review each provider’s data retention policies
  4. Performance Optimization
    • Use streaming for better user experience
    • Select appropriate models for your use case
    • Consider latency when choosing providers

​
Need Help?

Join our Discord community for support and to connect with other Jan users working with remote models.

Build docs developers (and LLMs) love

Get started for freeTalk to us