Welcome | EmpirioLabs AI Docs

EmpirioLabs AI is a specialized AI inference and integration provider. We self-host open-source models on GPU infrastructure we manage, run optimized endpoints for proprietary models, help teams ship their own models to large audiences, and offer on-demand GPU Cloud instances and hosted AI agents. The catalog has 211+ text, image, video, audio, transcription, embedding, reranking, research, and 3D models, which you can call in the OpenAI, Anthropic, or Google Gemini request format.

What you can do with the platform

Access 211+ models

Models from Alibaba (Qwen), Amazon (Nova), ByteDance (Seed, Seedance, Seedream), DeepSeek, Google (Gemini, Gemma), Mistral, Xiaomi (MiMo), MiniMax, Perplexity, Stability AI, and more, including open-source models we host ourselves.

Use familiar SDKs

Send requests using the OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, or Google Gemini format with the SDK you already use.

Pay with prepaid credits

Top up your account from the Billing page and pay per-token, per-request, or per-unit depending on the model.

Track usage and cost

Every API call is logged with token counts, cost, and latency so you can monitor spend in real time.

Rent GPUs on demand

Deploy GPU Cloud instances and multi-node clusters with persistent storage, billed from the same credits.

Run hosted agents

Deploy private OpenClaw and Hermes agents that use EmpirioLabs models and talk to people on Telegram, Discord, Slack, and more.

Start here

Get an API key

Sign up at platform.empiriolabs.ai, add credits or choose a plan, and generate an API key from the dashboard. Keys use the sk-empiriolabs- prefix.

Make your first request

Follow the Getting Started guide to list available models and send a chat completion.

Browse the model catalog

Call GET /v1/models or visit the Models page to see pricing, regions, and supported parameters for every model.

Documentation map

Getting Started

Make your first API call in under a minute.

Authentication

Learn about API key format, bearer tokens, and error codes.

Models and Pricing

Browse model categories, pricing units, and API status values.

Compatibility

See how the OpenAI, Anthropic, and Gemini request formats map onto EmpirioLabs endpoints.

API Reference Overview

Tour the complete REST surface, from chat and media generation to search, batch, and jobs.

Support

Find the best path for onboarding, troubleshooting, and feedback.