Inference API

The OpenAI-compatible Inference API: chat completions, vision, images, video, embeddings, and reranking.

The Inference API runs models. It implements the OpenAI API surface, so existing OpenAI SDKs and tools work against it once you change the base URL.

• Base URL: https://inference.nebulablock.com/v1

• Authentication: Authorization: Bearer <your API key> — see Authentication

Note: These endpoints are also reachable at https://api.nebulablock.com/v1. Prefer the inference.nebulablock.com host.

Endpoints

Endpoint	What it does
GET /v1/models	List every model you can call
POST /v1/chat/completions	Chat and text generation
POST /v1/chat/completions (with image content)	Image understanding
POST /v1/images/generations	Image generation
POST /v1/videos/generations	Video generation (asynchronous)
POST /v1/embeddings	Text embeddings
POST /v1/rerank	Document reranking

Using an OpenAI SDK

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://inference.nebulablock.com/v1",
    api_key=os.environ["NEBULA_API_KEY"],
)

See also

• Serverless Inference

• Model Catalog

• Platform API