Sold by: Runway
Deployed on AWS
Runway Dev is an API platform for AI video, image, audio, and real-time avatar generation, with Runway's frontier models and the best from other labs.
SOC 2 Type II, IP indemnification, 99.9% uptime, audit logs, and spend controls. Trusted by Adobe, ElevenLabs, Shutterstock, and Figma Weave.
Overview
AI video, image, audio, and avatar generation in one API
Runway Dev is an API platform for generative media. One integration provides Runway's frontier models alongside models from other leading labs, with usage tracked in one place and billed through your AWS account. Adobe, ElevenLabs, Shutterstock, and Figma Weave build on Runway Dev.
Frontier AI models from Runway and other labs
Runway Dev provides Runway's own frontier models and a curated selection of third-party models through a single API and one set of credentials. New models are added as they ship, so adopting one is a parameter change rather than a new integration.
Automatic model selection with the Model Router
The Model Router selects a model for each request. It matches the request to the models that can handle the task, then optimizes across those for cost, quality, or latency. Routing only ever picks from the models you allow, and never exceeds the per-generation spend cap you set. Every routing decision can be read back and audited. Configure a router once and reference it by ID, then change the preference, the permitted models, or the spend cap at any time without changing your code.
Pre-built endpoints for ad creative, product video, and localization
Recipes are Runway-built endpoints that return a production-ready asset from a single API call. Each covers one professional use case, with model selection, prompting, and multi-step chaining already solved:
- Product ads
- Ad localization
- Product swaps
- Multi-shot video
- Marketing stock images
Custom multi-model pipelines
Workflows let you combine models, conditional logic, and transformations into a pipeline, then expose that pipeline as your own private API endpoint. Trigger it from your application, an internal tool, or an automated job.
Real-time interactive avatars
Characters are real-time interactive avatars with voice, tool calling, and a knowledge base, embedded directly in your product. Characters are available only on Runway Dev.
MCP server for coding agents
Runway Dev provides an MCP server so a coding agent can plan, configure, and debug the integration without leaving your editor. It works with Claude Code, Codex, and Cursor.
Cost controls and usage auditing
Runway Dev estimates the cost of a call before you make it and enforces spend limits per project and per call. Audit logs record usage by model, project, and API key, across every model provider on a single dashboard.
Security, compliance, and commercial use
Runway Dev is SOC 2 Type II certified and backed by a 99.9% uptime SLA. Generated output is covered by IP indemnification for commercial use. Runway manages vendor security across all model providers through security review, certification, and contractual data protection requirements, so your legal and security teams review one vendor rather than every model provider separately.
Getting started with the Runway Dev API
Subscribe through AWS Marketplace, then follow the Runway Dev developer documentation at https://docs.dev.runwayml.com/ to create an organization, generate an API key, and run your first generation.
Highlights
- Models: Runway Dev combines Runway's own frontier video, image, audio, and real-time character models with third-party models from other labs in a single API. Runway's models are not available through any other API, and new releases arrive on day zero.
- Tools: The Model Router selects a capable model for each request and optimizes for cost, quality, or latency within limits you set. Recipes return production-ready ad creative, product video, and localized assets from a single API call. Workflows expose custom multi-model pipelines as your own private endpoints.
- Security and commercial use: Runway Dev is enterprise-ready: SOC 2 Type II certified, with a 99.9% uptime SLA, IP indemnification for commercial use of generated output, audit logs, and spend controls per project and per call.
Details
Sold by
Categories
Delivery method
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/unit |
|---|---|---|
Credits | Credits are used to pay for the compute resources used by your models | $0.01 |
Dimensions summary
You pay with a single dimension: Credits. Credits cover the compute resources your generative models use, so billing follows actual usage rather than a fixed subscription. You buy credits and draw them down as you run video, image, or audio generation tasks through the API. Costs scale with how much you generate: heavier or longer generations consume more credits, lighter workloads consume fewer. There are no separate tiers or instance sizes to choose between. If you need usage beyond the self-serve level, you request higher limits directly from the vendor.
Top-of-mind questions for buyers
Credits pay for the compute resources a model uses to run a task. One credit maps to a slice of that compute, not to a fixed number of outputs. Longer or heavier generations consume more credits per task. Lighter tasks consume fewer credits. You draw credits down as tasks run.
Yes. Credits track the compute each task consumes, and different task types use different amounts of compute. Video generations, especially longer or higher-resolution ones, draw more credits than lighter image or audio tasks. Your bill reflects the actual compute each task runs, not a flat per-task rate.
You still pay in credits, but you request higher rate limits from the vendor. Submit an exception request on the usage page of your developer portal. Higher-usage customers also receive support through dedicated channels, earlier access to new features, and custom payment terms.
docs.dev.runwayml.com
Helpful?
Vendor refund policy
All sales are final. Fees are non-refundable.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Support
Vendor support
Enterprise support
Runway Dev enterprise customers receive support by email at enterprisesupport@runwayml.com and through a dedicated Slack channel, with a named account manager and access to Runway technical artists for help with output quality.
Documentation
Developer documentation, including integration guides, endpoint references, and quickstarts, is at
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Ultimate AI Media Generation Platform With 1000+ top-tier models, WaveSpeedAI is the most powerful platform for AI image and video generation - built to help you create faster and scale without limits.
Daily provides scalable video infrastructure & APIs to power incredible live video and audio experiences. Trusted by teams like Butter and Kumospace and backed by leading investors like YC, Tiger Global and Renegade Ventures.
By Z.ai
One-stop API access to Z.ai's full suite of GLM models, covering language, vision, image generation, and video capabilities. A single API key unlocks all AI capabilities for intelligent dialogue, content creation, visual understanding, and multimedia generation.
Create AI videos, images, audio, and visual effects with Kling AI creative tools.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.