● Documentation · V1 · MAY 2026

Build with deeprelay.

OpenAI-compatible serverless inference (chat, embeddings, image and video) on deeprelay. A REST API and a CLI. These docs cover everything you can do as a developer on the platform.

Quick start →OpenAPI spec ↗Get an API key

§ 01 · Start here

JUMP IN

Run your first completion

From zero to a streaming chat completion in under five minutes.

Quick start →REFERENCE

Every /v1 endpoint

Schemas, examples in curl / Python / Node / Go, response envelopes.

Endpoint reference →ALL TOOLS

The developer hub

CLI and REST API in one page: one key, first call in minutes.

Explore the hub →

§ 02 · Contents

Getting started

02 chapters

00OverviewThe docs index: what lives here and where to start.
01Quick startGet an API key and make your first inference call in five minutes.

CLI

02 chapters

02The deeprelay CLIInstall deeprelay, authenticate, and run inference from your shell.
02.1deeprelayEvery deeprelay subcommand with flags, examples, and exit behavior, one page per command.

API

04 chapters

03ConventionsAuthentication, errors, pagination, idempotency, and rate limits.
04Endpoint referenceEvery /v1 endpoint with curl, Python, Node, and Go samples.
05Inference APIOpenAI-compatible chat, embeddings, image generation, and async video jobs.
06WebhooksLifecycle events, HMAC signatures, retry policy, verification.

SDKs

02 chapters

08Python SDKdeeprelay_sdk: typed Python client for inference, the subscription lifecycle, billing, usage, and webhooks.
09TypeScript SDK@deeprelay/sdk: the same surface for Node, CJS-primary with its own type declarations.

Guides

01 chapter

12Getting startedAccount, credit, and your first inference call in minutes.

Need a hand?

We respond fast. Email support@deeprelay.ai for anything: billing, integration help, weird edge cases.

Email support →