GPU Cloud and Hosted Agents are now available. Explore GPU Cloud
Browse our latest posts to learn more about us and what our platform has to offer.
API Access
Call Qwen3.7 Flash, Alibaba's fast Qwen3.7 vision-language model with a 1M token context, switchable thinking, built-in tools, and text, image, and video input.
Fugu Ultra v1.1 is available on EmpirioLabs with distinct maximum reasoning, 1M context, image input, function calling, strict structured output, and web search.
Qwen Audio 3.0 TTS is available on EmpirioLabs as one model with a Plus and Flash tier, over 1,000 shared voices, 16 languages, and inline emotion tags.
Call Kimi K3, Moonshot AI's flagship reasoning model with a 1M token context, always-on thinking, native web search, and image and video input, through an OpenAI-compatible API on EmpirioLabs.
Seed 2.1 Turbo is ByteDance's next-generation coding and agent model on EmpirioLabs, with reasoning, function calling, structured output, and text, image, and video input across a 256K context.
Muse Spark 1.1 is Meta AI's frontier reasoning model with a 1M token context, image and video understanding, and built-in web search. Here is how to call it through one OpenAI-compatible API.
Seedream 5.0 Pro is available on EmpirioLabs for text-to-image generation, single-image edits, and multi-reference image fusion with 1K, 1.5K, and 2K output.
A practical guide to planning, editing, rendering, and auditing Compose jobs with /v1/videos/compose and /v1/account/usage.
Seedance 2.5 is expected soon. Here is what has been reported about 30-second clips, richer reference inputs, and planned EmpirioLabs support.
Seedance 2.0 Mini is the fastest, most affordable tier of Seedance 2.0 on EmpirioLabs: short cinematic clips with native audio at 480p and 720p, on one OpenAI-compatible API.
Seedance 2.0 Pro now renders native 4K (3840x2160) video with synchronized audio on the same OpenAI-compatible API. Pay-as-you-go per second.
Call Sakana AI's Fugu Ultra, a multi-agent conductor, through an OpenAI-compatible API: 1M context, image input, reasoning effort control, and built-in web search.
Showing 13–24 of 30 articles
Explore our models, or contact us about business inquiries, custom deployments, or anything else.
