Aplomb 1, our first model, is now available. Read the launch post
Browse our latest posts to learn more about us and what our platform has to offer.
API Access
HappyHorse 1.1 is one video model with three modes: text to video, image to video, and reference to video from up to 9 images, all with synchronized native audio. Here is how to call it on EmpirioLabs.
Animate any image into a short video with native audio using the Kling 3.0 Turbo API. OpenAI-compatible, pay-as-you-go per second, 720p or 1080p.
Kimi K2.7 Code Highspeed is the faster-serving tier of Moonshot AI's Kimi K2.7 Code: the same trillion-parameter agentic coding model, served on a lower-latency, higher-throughput path. Here is how to call it through the EmpirioLabs API, what it costs, and what to know before you build.
Call Z.ai's flagship GLM-5.2 through an OpenAI-compatible API: a 1M token context, adjustable reasoning effort, built-in web search, and usage-based per-token pricing.
Templates
Turn one portrait and a voice or singing clip into a talking video where the face lip-syncs to the audio, in a couple of minutes with the Lip Sync template.
Kimi K2.7 Code is Moonshot AI's trillion-parameter agentic coding model, released June 12, 2026. Here is how to call it through the EmpirioLabs API, what it costs, and what to know before you build.
First-person POV for any scene: dragon flights, rally drifts, spacewalks, shipwreck dives. Your own hands in frame and the immersive head-cam look, generated in one click with the POV template.
Wake up as a kid in December of 1999. First-person POV, your own hands in frame, era-accurate scenes from cereal mornings to the arcade. The Time Capsule template handles the look in one click.
Guides
Deploy any open model on a managed GPU and use it in any OpenAI-compatible app, from chat frontends like SillyTavern to coding assistants and the OpenAI SDKs.
Platform
Deploy a managed GPU in one click. Serve any open model behind an OpenAI-compatible endpoint, run a one-click template, or bring your own CUDA container, and pay per second.
Deploy a managed OpenClaw or Hermes agent that lives in your chat apps, runs code, generates media, browses the web, and connects your tools, using any EmpirioLabs model.
OpenClaw and Hermes are the two managed agent runtimes on EmpirioLabs. Here is what they share and how to pick the right one for your agent.
Showing 85–96 of 114 articles
Explore our models, or contact us about business inquiries, custom deployments, or anything else.
