Runway API
The API makes generative AI models available, at the same credits prices listed here ($0.01 per credit):…
Fork copies the collection into your workspace, without the publisher's secrets, so you can add your own key and send requests. Star saves it to your starred APIs (Account › Marketplace) and helps others find it.
Overview
The API makes generative AI models available, at the same credits prices listed here ($0.01 per credit): https://help.runwayml.com/hc/en-us/articles/15124877443219-How-do-credits-work
Endpoints 68
Start generating
- POSTImage to vector
/v1/image_to_vectorConvert a source image into a scalable SVG. - POSTImage to video
/v1/image_to_videoThis endpoint will start a new task to generate a video from an image. - POSTText to video
/v1/text_to_videoThis endpoint will start a new task to generate a video from a text prompt. - POSTVideo to video
/v1/video_to_videoThis endpoint will start a new task to generate a video from a video. - POSTText/Image to Image
/v1/text_to_imageThis endpoint will start a new task to generate images from text and/or image(s) - POSTImage upscale
/v1/image_upscaleUpscale an image with Magnific precision upscaling. Each input dimension must be between 300px and 8000px. Output width and height are the input dimensions… - POSTVideo upscale
/v1/video_upscaleThis endpoint starts a task to upscale a video. Set model to choose the upscaler. - POSTVideo to HDR
/v1/video_to_hdrThis endpoint starts a task to upconvert an SDR video to true HDR with Ruby, Runway's HDR grading model. The output keeps the source's own pixels — luma and… - POSTControl a character
/v1/character_performanceThis endpoint will start a new task to control a character's facial expressions and body movements using a reference video. - POSTGenerate sound effects
/v1/sound_effectThis endpoint will start a new task to generate sound effects from a text description. - POSTGenerate audio from a video
/v1/video_to_audioGenerate synchronized sound effects for a video, optionally guided by a text description. Returns audio, not a video with a replacement soundtrack. - POSTSpeech to speech
/v1/speech_to_speechThis endpoint will start a new task to convert speech from one voice to another in audio or video. - POSTText to speech
/v1/text_to_speechThis endpoint will start a new task to generate speech from text. ElevenLabs models accept preset voices or custom voices created via the Voices API. Seed… - POSTGenerate music
/v1/text_to_musicThis endpoint will start a new task to generate a song or instrumental track from a text description. - POSTVoice dubbing
/v1/voice_dubbingThis endpoint will start a new task to dub audio content to a target language. - POSTVoice isolation
/v1/voice_isolationThis endpoint will start a new task to isolate the voice from the background audio. Audio duration must be greater than 4.6 seconds and less than 3600 seconds.
Task management
- GETGet task detail
/v1/tasks/:idReturn details about a task. Consumers of this API should not expect updates more frequent than once every five seconds for a given task. - DELETECancel or delete a task
/v1/tasks/:idTasks that are running, pending, or throttled can be canceled by invoking this method. Invoking this method for other tasks will delete them. Refund…
Uploads
- POSTUpload a file
/v1/uploadsUploads a temporary media file that can be referenced in API generation requests. The uploaded files will be automatically expired and deleted after a period…
Avatars
- GETList avatars
/v1/avatars?limit=50List avatars for the authenticated user with cursor-based pagination. - POSTCreate avatar
/v1/avatarsCreate a new avatar with a reference image and voice. - GETList conversations
/v1/avatar_conversations?limit=20List realtime avatar conversations for the authenticated user with cursor-based pagination. Each conversation corresponds to a realtime session, and the… - GETGet avatar usage
/v1/avatar_usage?startDate=2024-01-01T00:00:00Z&endDate=2024-01-01T00:00:00ZGet aggregate usage statistics for avatar conversations, including total duration, session counts, average duration, and a per-day breakdown. Per-day buckets… - GETGet conversation
/v1/avatar_conversations/:idGet detailed information about a specific conversation, including the transcript and recording download URL when available. The conversation ID is the same… - DELETEDelete conversation
/v1/avatar_conversations/:idPermanently delete a conversation, including its transcript and recording. - GETGet avatar
/v1/avatars/:idGet details of a specific avatar. - DELETEDelete avatar
/v1/avatars/:idDelete an avatar. - PATCHUpdate avatar
/v1/avatars/:idUpdate an existing avatar. At least one field must be provided.
Avatar Videos
- POSTGenerate avatar video from audio or text
/v1/avatar_videosStart an asynchronous task to generate a video of an avatar speaking. Provide speech with type: "audio" (audio file) or type: "text" (text script for TTS).…
Knowledge
- GETList documents
/v1/documents?limit=50&sort=createdAt&order=descList knowledge documents for the authenticated user with cursor-based pagination. - POSTCreate document
/v1/documentsCreate a new knowledge document. Documents can be attached to avatars to provide additional context during conversations. - GETGet document
/v1/documents/:idGet details of a specific knowledge document. - DELETEDelete document
/v1/documents/:idDelete a knowledge document. This also removes it from all avatars it was attached to. - PATCHUpdate document
/v1/documents/:idUpdate a knowledge document. At least one of name or content must be provided.
Realtime Sessions
- POSTCreate realtime session
/v1/realtime_sessionsCreate a new realtime session with the specified model configuration. The returned ID is also the conversation ID used later to fetch transcripts and… - GETGet realtime session
/v1/realtime_sessions/:idGet the status of a realtime session. This endpoint uses the same ID that the avatar conversation endpoints later expose as the conversation ID. - DELETECancel realtime session
/v1/realtime_sessions/:idCancel an active realtime session.
Model Router
- POSTRouted video generation
/v1/generate/videoStart a video generation task using a saved Model Router config instead of naming a model. - POSTRouted image generation
/v1/generate/imageStart an image generation task using a saved Model Router config instead of naming a model. - POSTRouted audio generation
/v1/generate/audioStart an audio generation task using a saved Model Router config instead of naming a model. Set input.type to speech to speak promptText verbatim, audio to… - GETList Model Routers
/v1/routers?limit=50List Model Router configurations for the authenticated organization with cursor-based pagination. - POSTCreate Model Router
/v1/routersCreate a Model Router configuration. - GETRetrieve Model Router
/v1/routers/:idRetrieve a Model Router configuration by ID. - DELETEDelete Model Router
/v1/routers/:idDelete a Model Router configuration. Deleted Model Routers cannot be used for generation. - PATCHUpdate Model Router
/v1/routers/:idUpdate a Model Router configuration. Settings changes append a new version; name and description updates do not. Settings are merged with the current snapshot… - GETList Model Router requests
/v1/routers/:id/requests?limit=50Paginated routing history for live Model Router requests (successful routes and failures). Playground dry runs are not recorded.
Organization
- GETList linked workspace usage
/v1/organization/webapp/usage?limit=50&from=2024-01-01T00:00:00Z&to=2024-01-01T00:00:00ZList per-generation credit-usage rows for the linked Runway workspaces you administer, newest first. Unlike /v1/organization/usage (this API project's own… - GETList linked workspace audit logs
/v1/organization/webapp/audit_logs?limit=50List audit log entries for the linked Runway workspaces you administer, newest first. Authorized via the account link between this API project and the… - GETGet a linked workspace audit log entry
/v1/organization/webapp/audit_logs/:eventIdGet a single audit log entry, including its metadata and forensic details, for a linked Runway workspace you administer. Authorized via the account link… - GETGet organization information
/v1/organizationGet usage tier and credit balance information about the organization associated with the API key used to make the request. - POSTQuery credit usage
/v1/organization/usageFetch credit usage data broken down by model and day for the organization associated with the API key used to make the request. Up to 90 days of data can be…
Recipes
- POSTLocalize an ad image
/v1/recipes/ad_localizationLocalize an existing ad image for a target language, preserving visual creative while adapting on-screen messaging. - POSTCreate a marketing stock image
/v1/recipes/marketing_stock_imageGenerate a polished marketing stock image from a text brief and optional brand logo image. - POSTCreate a product ad video
/v1/recipes/product_adGenerate a cinematic product ad from product images, optional style references, product info, and creative direction. - POSTCreate product campaign images
/v1/recipes/product_campaign_imageGenerate four fashion campaign images from a product image and style brief. - POSTSwap a product in a reference video
/v1/recipes/product_swapReplace the product in a reference video with a new product, preserving camera motion, lighting, and scene composition. - POSTCreate a multi-shot video
/v1/recipes/multi_shot_videoGenerate a multi-cut video from a story prompt (auto mode) or a custom shot list (custom mode). - POSTCreate a product UGC video
/v1/recipes/product_ugcGenerate a vertical user-generated content ad from a character image, product image, product details, and optional creative direction.
Voices
- GETList voices
/v1/voices?limit=50List custom voices for the authenticated organization with cursor-based pagination. - POSTCreate a voice
/v1/voicesCreate a custom voice from a text description, or clone a voice from an audio sample. - GETGet a voice
/v1/voices/:idGet details about a specific custom voice. - DELETEDelete a voice
/v1/voices/:idDelete a custom voice. - PATCHUpdate a voice
/v1/voices/:idUpdate the name and/or description of a custom voice. - POSTPreview a voice
/v1/voices/previewGenerate a short audio preview of a voice from a text description. Use this to audition a voice before creating it.
Workflows
- GETGet workflow details
/v1/workflows/:idReturns details about a specific published workflow, including its graph schema. - POSTRun a published workflow
/v1/workflows/:idStart a new task to execute a published workflow. You can optionally provide custom input values via nodeOutputs to override the defaults defined in the… - GETList published workflows
/v1/workflowsReturns a list of all published workflows for the authenticated user, grouped by source workflow with their published versions. - GETGet workflow invocation detail
/v1/workflow_invocations/:idReturn details about a workflow invocation. Consumers of this API should not expect updates more frequent than once every five seconds for a given workflow…
API details
- Base URL
https://api.dev.runwayml.com- Authentication
- A bearer token in the Authorization header
- Operations
- 68 operations on 52 pathsPOST 36GET 21DELETE 7PATCH 4
- Main resources
- Start generating 16Avatars 9Model Router 9Recipes 7Voices 6Knowledge 5Organization 5Workflows 4Realtime Sessions 3Task management 2
- Response formats
application/json- Description format
- OpenAPI 3.1.0, API version
2024-11-06 - Links
- OpenAPI document
- Listed from
- Runway's published OpenAPI description (runwayml/openapi) (Apache-2.0)
How to test the Runway API in Swastik Codes
- Open the APISelect “Fork & run in Swastik Codes” on this page. Sign in or create a free account if asked.
- Fork it into your workspaceChoose a workspace. You get your own copy of the Runway API collection, without the publisher's secrets.
- Add your credentialsThis API uses A bearer token in the Authorization header. Add yours in the collection's variables or an environment; the requests already reference it.
- Send a requestPick an endpoint, for example “Image to vector” (POST /v1/image_to_vector), and press Send. Check the response, add tests and run the whole collection with the runner.
Frequently asked questions
What is the Runway API?
The API makes generative AI models available, at the same credits prices listed here ($0.01 per credit):… It is listed under AI & machine learning and has 68 endpoints.
Who publishes the Runway API?
It is listed from Runway's public API description (an OpenAPI document), not published by Runway on Swastik Codes. Anyone who controls runwayml.com can claim the profile by adding a DNS TXT record.
What is the base URL of the Runway API?
Requests go to https://api.dev.runwayml.com. Endpoint paths are added to this base URL.
How do I authenticate with the Runway API?
With A bearer token in the Authorization header.
How many endpoints does the Runway API have?
68 operations on 52 paths (36 POST, 21 GET, 7 DELETE, 4 PATCH). The largest groups are Start generating, Avatars, Model Router, Recipes.
Is forking the Runway API free?
Yes. Forking copies the collection into your workspace for free. It has been starred 0 times and forked 0 times.