canonical: https://jentic.com/apis/runwayml.com/runwayml

# Runway ML API

Runway ML generative AI API for video generation, image generation, audio, avatars, workflows, and more. Supports image-to-video, text-to-video, text-to-image, sound effects, speech synthesis, and real-time avatar sessions. The API exposes 37 endpoints secured with bearer authentication.

## For AI agents

Programmatically image to video, text to video. Covers 37 operations with bearer authentication.

## Scope

Does not handle payments, communications, or crm - use for media and content only.

## Capabilities

- Image to video
- Text to video
- Video to video
- Control a character
- Generate sound effects
- Speech to speech

## Use cases

### Media and Content Operations

Use the Runway ML API to perform media operations programmatically. The API provides 37 endpoints covering core functionality including image to video, text to video, video to video.

Example prompt: Call POST `/v1/image_to_video` to image to video

### Automated Avatars Management

Automate avatars operations by combining multiple Runway ML API endpoints. Agents can text to video and then video to video in a single workflow.

Example prompt: Call POST `/v1/text_to_video` to text to video, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Runway ML API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle bearer tokens manually.

Example prompt: Search Jentic for 'image to video', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/v1/image_to_video` | Image to video |
| POST | `/v1/text_to_video` | Text to video |
| POST | `/v1/video_to_video` | Video to video |
| POST | `/v1/text_to_image` | Text/Image to Image |
| POST | `/v1/character_performance` | Control a character |
| POST | `/v1/sound_effect` | Generate sound effects |
| POST | `/v1/speech_to_speech` | Speech to speech |
| POST | `/v1/text_to_speech` | Text to speech |

## Key resources

- **Avatars** — Operations related to Avatars
- **Knowledge** — Operations related to Knowledge
- **Organization** — Operations related to Organization
- **Realtime Sessions** — Operations related to Realtime Sessions
- **Start generating** — Operations related to Start generating

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 63 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 87 / 100
  - Developer Experience & Jentic Compatibility: 62 / 100
  - AI-Readiness & Agent Experience: 51 / 100
  - Agent Usability: 94 / 100
  - Security: 60 / 100
  - AI Discoverability: 43 / 100
- **View full report:** https://jentic.com/apis/runwayml.com/runwayml/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring the Runway ML API by hand means handling its bearer token, pointing at api.dev.runwayml.com, and managing your own retries for generation jobs. Through Jentic you install once, import the Runway ML API from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** The Runway ML API takes its inputs in the request body rather than the URL path, so scope the agent to the operations it needs, such as text to image or text to video, and leave out video to video or speech to speech unless the agent needs them.
- **Credential handling:** Your Runway ML API token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'generate a video from an image' or 'create speech from text', and Jentic returns the matching Runway ML API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Cloudinary** — Alternative media API
- **Mux** — Alternative media API

## FAQ

### What authentication does the Runway ML API use?

The Runway ML API uses a Bearer token in the Authorization header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I image to video with the Runway ML API?

Yes. Use the POST `/v1/image_to_video` endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Runway ML API?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I image to video through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'image to video'. Jentic returns the matching Runway ML API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Runway ML API have?

The Runway ML API exposes 37 endpoints covering avatars, knowledge, organization operations.

### Can I limit what my agent is allowed to do with the Runway ML API?

Yes. Because Jentic One is self-hosted, you set the rules that decide which Runway ML API operations and credentials your agent can use. You can scope the agent to only the endpoints it needs, such as POST `/v1/text_to_image` or POST `/v1/text_to_video`, and leave out others like POST `/v1/video_to_video` or POST `/v1/speech_to_speech.` The bearer token is stored once in your own instance and injected only for the operations you have allowed.