API Guide

Complete API reference for the Skytells platform — endpoints, authentication, versioning, and status.

Skytells API

The Skytells API gives you programmatic access to AI models, predictions, and services. Authenticate with a single API key, choose your endpoint, and start building.

API Endpoints

Two endpoints — Standard for general workloads and Edge for enterprise-grade, low-latency inference.

Versioning

The API is versioned via the URL path. Learn how versions work and how to stay up to date.

Authentication

All requests require an x-api-key header. Generate keys from your Dashboard and authenticate in seconds.

API Status

Monitor real-time availability and incidents for all Skytells services.

At a Glance

For a detailed comparison of Standard and Edge APIs (base URLs, audience, network, model support, latency), see API Endpoints.

Quick Start

Below, you can see a quick example of how to list available models using the Standard API.

curl https://api.skytells.ai/v1/models \
  -H "x-api-key: $SKYTELLS_API_KEY"

API Resources

Our APIs are organized into two main categories: Predictions and Inference.

Predictions API: Generate images, videos, audio, and other media with AI models.
Inference API: The gateway for LLMs, text, code, reasoning, and embeddings. Sub-APIs (Chat Completions, Responses, Embeddings) operate under it.
Inference API: The umbrella for LLM and text workloads — Chat Completions, Responses, and Embeddings operate under it.
Webhooks: Listen to API events and receive real-time webhook notifications on your server.