LLM Providers

This application uses OpenRouter as the unified API gateway to access various Large Language Models from different providers. OpenRouter provides a single interface to access models from multiple LLM providers, simplifying integration and offering competitive pricing.

The application supports several models from different providers, each optimized for different use cases:

Google Models

Google provides the Gemini family of models through OpenRouter:

  • gemini-2.5-pro: High-quality Gemini model for complex reasoning and analysis; excellent for interpretation tasks. Zero data retention.

  • gemini-2.5-flash: Fast and efficient Gemini model; good balance of speed and quality for most tasks. Zero data retention.

Data Policy: Google Gemini models have a zero data retention policy - your data is not stored or used for training.

OpenAI Models

OpenAI provides the GPT family of models through OpenRouter:

  • gpt-5: Highest quality and most advanced model; best for complex interpretation and summarization, but more resource-intensive and slower than mini/nano.

  • gpt-5-mini: Optimized for speed and efficiency; suitable for most workflows with a balance of quality and cost.

  • gpt-5-nano: Fastest and lowest cost for simple extraction or tagging; not for detailed interpretations.

Data Policy: OpenAI stores data for 30 days for abuse detection purposes only. Your data is not used for training the models.

Mistral Models

Mistral AI provides the Mistral family of models through OpenRouter:

  • mistral-small-3.2: Efficient Mistral model for balanced performance; good for various text processing tasks. Zero data retention.

Data Policy: Mistral AI follows a zero data retention policy - your data is not stored or used for training.

Custom Model Configuration

For users who want to use their own models or custom endpoints, the application supports custom model configuration. You need to set the following environment variables:

  • LLM_CUSTOM_API_KEY: Your custom model API key (not required for local models)

  • LLM_CUSTOM_API_ENDPOINT: The API endpoint URL for your custom model (e.g. https://api.yourmodelprovider.com/v1/chat/completions)

  • LLM_CUSTOM_MODEL: The model name/identifier for your custom model (e.g. your-model-name)

We cannot guarantee compatibility for custom models, as they may have different API specifications.