Log inSign up
Image
user avatar
Runware
@runware
Run any AI model at the lowest cost. Pay less, build more. 🔗 discord.gg/ZwC6UmFQV3
runware.ai
Joined March 2024
385
Following
6,876
Followers
AffiliatesRepliesArticlesMedia
  • Pinned
    user avatar
    Runware
    @runware
    20h
    Today we're launching Sonic Inference Pods, our network of modular data centers built for AI inference. Each one delivers 1MW of compute from a 20-foot shipping container, deployed wherever there's power. Learn more: bit.ly/4hNdg9I
    Image
    00:00
  • user avatar
    Runware
    @runware
    15h
    Qwen-Image-3.0 is now on Runware 🎨 - Up to 4.5k tokens in → dense multi-panel layouts out, in one pass - Text stays legible down to 10px, LaTeX & formulas included - Near-photographic skin, pores & hair detail - Native support for 12 languages
    Image
    00:00
  • user avatar
    Runware
    @runware
    16h
    FLUX 3 Video is now on Runware on D0 🎬 Black Forest Labs (@bfl_ai) first video model - Text to video, image to video, keyframes - Strong physics, motion, and audio - Hyper-realistic, cinematic, animation, and motion design outputs - Up to 20 second clips at 1080p
    Image
    00:00
  • user avatar
    Runware
    @runware
    Jul 31
    DeepSeek V4 Flash 0731 is now on Runware on D0 🧠 - Intelligence Index 50, +10 over the last V4 Flash - runs long, multi-step agentic tasks start to finish - strong on coding, reasoning & tool use - 1M context, on the intelligence-vs-cost Pareto frontier
    Image
    00:00
  • user avatar
    Runware
    @runware
    Jul 31
    MiniMax H3 is now on Runware 🎬 - New open-weights flagship video model from MiniMax - Native synced audio, generated in the same pass as the video - Multi-reference conditioning keeps subjects and scene identity consistent across shots - Extend existing clips or audio segments
    Image
    00:00