Overview

Unified API for AI inference on decentralized GPU infrastructure.

Open Beta — We're expanding our provider network and refining the platform. Expect new models and features regularly. Feedback welcome!

Relay provides standard REST endpoints for chat, images, speech, and video—abstracting away the complexity of GPU provisioning, load balancing, and blockchain settlement. Currently, all models are provided and maintained by the Relay team. Support for self-hosted models and provider onboarding is on the immediate roadmap.

How It Works

Relay organizes resources as mode.source.model:

mode       → routing/billing category (direct or opengpu)
source     → service type (ollama, vllm, audio, automatic1111, video)
model      → specific model (gpt-oss:120b, sesame/csm-1b, etc.)

Modes:

• direct — Low-latency (<1s), pay-per-request

• opengpu — Decentralized execution on the OpenGPU Network, a permissionless compute network with redundant computing for reliability and censorship resistance

Sources:

• ollama — Chat (Ollama-compatible)

• vllm — Chat (OpenAI-compatible)

• audio — Text-to-speech, Speech-to-text

• automatic1111 — Image generation

• video — Text-to-video generation

Quick Example

curl -X POST https://relay.opengpu.network/v2/ollama/api/chat \
  -H "X-API-Key: YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-oss:20b", "messages": [{"role": "user", "content": "Hello"}]}'

Endpoints

Source	Endpoint	Description
ollama	/v2/ollama/api/chat	Ollama-compatible chat
vllm	/v2/vllm/v1/chat/completions	OpenAI-compatible chat
audio	/v2/audio/tts/sesame	Text-to-speech
audio	/v2/audio/asr/whisper	Speech-to-text
automatic1111	/v2/automatic1111/sdapi/v1/txt2img	Image generation
video	/v2/video/generate	Text-to-video generation
video	/v2/video/edit	Image-to-video generation

Get Started

1. Quickstart - First request in 60 seconds

2. Authentication - API keys and tiers

3. Endpoints - Full documentation