Product Updates

Runware Serverless is now available
Update•Oct 2, 2026•10 min read

Runware Serverless: run your own AI from $0.63 per GPU-hour

Runware Serverless is live, with prices from $0.63 per GPU-hour. Run your own code, models and containers on Runware's GPU infrastructure, built on our own Sonic Pods, while we manage the platform.

Runware Zero Data Retention
Update•Sep 29, 2026•4 min read

Zero Data Retention on Runware, now available

Runware's Zero Data Retention (ZDR) lets enterprise teams run AI image, video, and language model requests without retaining prompts or generated outputs.

gpt-oss-safeguard-20b and Shieldstral 1.0 3B content moderation models on Runware
Update•Sep 29, 2026•3 min read

Content moderation for AI pipelines: gpt-oss-safeguard-20b and Shieldstral 1.0 3B

OpenAI's gpt-oss-safeguard-20b and Mistral AI's Shieldstral 1.0 3B are live on the Runware API: safety moderation for prompts, text, and generated images.

Introducing Style LoRA Training on Runware — train a custom style adapter on your own images
Update•Aug 3, 2026•14 min read

Introducing Style LoRA Training on Runware

In-house Style LoRA training is live on Runware. Train a small adapter on your own images for tighter brand and style consistency than reference images can give you, on FLUX.1 [dev], FLUX.2 [klein] 4B/9B, Qwen-Image, or Z-Image Base.

Runware MCP server and CLI: agents and terminal access to every model
Update•Jun 25, 2026•15 min read

Your stack, your choice: Runware via MCP, CLI, or Skills

Runware now offers an MCP server for AI agents, a CLI for the terminal, and Skills that package up Runware know-how for whichever one you're using. All three reach the same catalog across image, video, audio, 3D, and LLMs.

Building the revenue engine for Runware's next stage of growth
Update•Apr 24, 2026•10 min read

Building the revenue engine for Runware's next stage of growth

After taking Confluent's EMEA business from scale-up to IPO scale, Carlos joins Runware to do it again at 10x speed and volume. Here's what he's here to build next.

Runware usage dashboard showing request volume, spend, errors and performance metrics
Update•Apr 1, 2026•6 min read

Major web app overhaul: advanced usage reporting now live

We've rebuilt the Runware web app from the ground up, improving UI and UX across every dashboard. You can now also see requests, spend, errors, and performance data, along with searchable logs, all in a single reporting view.

A futuristic documentation interface with glowing schema trees and interconnected nodes
Update•Mar 26, 2026•8 min read

Introducing the new Runware documentation: Schema-driven and built for developers

We rebuilt our entire documentation from the ground up. Every model page is now generated directly from our API schemas, so the docs are always in sync with the API.

Neon-lit movie clapperboard with the word 'RUNWARE' in a futuristic server room
Update•Jul 3, 2025•6 min read

Lowest cost AI video generation now on Runware

Generate videos from text prompts or guide them with images at industry-leading prices. Easy integration through our unified API platform.

A cloaked figure made entirely of bending light and heat distortion, slightly warping the scene behind them like a heat haze, standing in a neon-lit room filled with mist
Update•May 23, 2025•7 min read

Introducing LayerDiffuse: Generate images with built-in transparency in one step

Generate images with built-in transparency directly from your prompts, eliminating the need for background removal in a single, efficient step.