API
Cortecs offers a simple, OpenAI-compatible API for serverless inference across multiple providers. It supports two endpoints:
🔁 POST /v1/chat/completions
POST /v1/chat/completionsSubmit chat requests using any available model. Supports standard OpenAI parameters like messages, temperature, and max_tokens. Use preference to optimize for speed, cost, or balanced.
📦 GET /v1/models
GET /v1/modelsList all available models and their capabilities.
Last updated