LLM Gateway

OpenPond LLM Gateway exposes hosted catalog models at /opchat/v1. Use a normal OpenAI-compatible client with an OpenPond API key and an explicit model ID.

Open LLM Gateway in Services. Use Overview for usage, Models for the callable catalog, and How to use for API setup. Personalized trained deployments belong to Serving.

Hosted models

Hosted catalog models are discovered at /opchat/v1/models and invoked through /opchat/v1/chat/completions. They use the opchat:model:read and opchat:chat:create scopes.

Choose an integration

• OpenAI-compatible API for endpoint and compatibility boundaries.
• JavaScript for a complete first request.
• Model catalog for current public IDs and rates.

Keep API keys on your server and make the first request with a small bounded prompt before moving production traffic.

How-tos

• Use the AI Gateway with the OpenAI JavaScript SDK.
• List models and make a first request.

Next: OpenAI-compatible API.