The best image, video and audio models from Runway and other frontier labs. One API platform.
Trusted by
Deploy the best media models, generation workflows and real-time conversational agents through a single integration, with the visibility and controls to build at scale.
Models, Workflows, Recipes and Characters — all accessible through a single API.
Run the same prompt across models. Score by quality, speed and cost before committing to production.
Set a preference for cost, latency or quality. The platform routes every request to the best model automatically.
Full visibility into cost per model, per endpoint, per team. One invoice for everything.
The best video, image and audio models, from Runway and other labs, available the day they release.
We train frontier models and know how to get the most out of them. That expertise is built into the platform, so every call carries it.
Set your priority between cost, quality and latency, plus a cost ceiling per generation. The router picks the best model for every request, so you don't need to know every model's tradeoffs or keep up as new ones land.
More on model routing
Runway-built endpoints with our prompting and workflow expertise packaged in. One call returns a production-ready asset, without building or maintaining the workflow yourself.
Explore Recipes
The Runway Dev MCP connects your account to your coding agent, so it can build, debug and maintain the integration without leaving the editor.
Connect Dev MCP
Create your own pipelines combining multiple models, modalities and tasks. Trigger Workflows via custom endpoints.
Automate repetitive tasks at scale
Get dedicated support from Runway's Technical Artists for Workflow builds
Enterprise
Build expressive characters with custom voices, knowledge and tools — ready for live interaction directly from your product.
Give each team its own Runway Dev project, decide who can do what and see where every credit goes.
Give each team or product its own project, with its own API keys, credits, usage tier, members and billing.
Admin, Developer and Billing Admin roles decide who manages keys, billing and members.
See credits by model and by day in the dashboard or the usage API, and filter request logs by API key.
Set a maximum cost per generation in a Model Router, and it only picks models that fit.
import RunwayML from '@runwayml/sdk';
const client = new RunwayML();
const task = await client.textToVideo.create({
promptText: "A cinematic slow push-in across a sunlit kitchen as steam curls from a fresh cup of coffee, soft morning light, gentle natural motion.",
model: "gen4.5",
ratio: "1280:720",
duration: 5,
seed: 692126734
}).waitForTaskOutput();The enterprise-ready infrastructure layer for AI media.
Zero-data retention and enterprise-grade security standards as default.
99.9% Uptime
No training on your data
You own your outputs
Enterprise-level support
SOC 2 Type II
IP Indemnification
Content moderation