llm-router

You can call multiple LLM models like Claude and Gemini using a single OpenAI-compatible API by using a unified API key. This gateway routes chat, vision, and comparison requests to 70+ models across diverse families through one consistent REST endpoint.

To compare outputs from different AI models, you can use the model comparison feature via CLI or Python client. By passing multiple model names and a message, the system queries each selected model and returns their responses together for direct evaluation.

Yes, you can analyze images with different vision models without separate integration code. The unified API provides a dedicated vision endpoint that accepts an image URL and prompt, allowing you to use models like GPT-4o through a consistent client interface.

The best way to manage API keys for routing requests across 70+ AI models is to use a single environment variable. By setting one key, you gain access to the unified gateway for chat, streaming, vision, and comparison tasks across all supported model families.

Yes, the unified LLM routing API supports streaming responses for chat endpoints. Alongside standard chat requests and vision analysis, the Python client and REST API provide streaming support to handle continuous data output efficiently.

To list all supported models available through the unified API gateway, you can execute a simple command via the CLI. Running the models command returns the complete roster of 70+ accessible AI models for chat, vision, and comparison tasks.