> ## Documentation Index > Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt > Use this file to discover all available pages before exploring further. # Create a Runway text-to-video task > Generate a video from a text prompt with Runway Gen-4.5 through CometAPI. Use `gen4.5` to generate a video from a text prompt. Send your CometAPI API key with Bearer authentication and a JSON request body. ## Prepare the request * Set `model` to `gen4.5`. * Describe the scene and motion in `promptText`, using 1 to 1,000 UTF-16 code units. * Set `ratio` to `1280:720` for landscape or `720:1280` for portrait. * Set `duration` to a whole number from `2` through `10` seconds. All four fields are required. To start from an image, use [Create a Runway image-to-video task](./runway-images-raw-video). Do not include `promptImage` or an `audio` toggle in this text-to-video request. ## Set optional controls For an explicit sampling seed, use `1` through `4294967295`. Omission or `0` selects a random seed. If you include `contentModeration`, set its `publicFigureThreshold` to `auto` or `low`; otherwise omit the object. Use `outputFormat` to select MP4, ProRes, PNG sequences, or one of the HDR formats listed in the request schema. Omit it for H.264 MP4. You can set `proresProfile` only when `outputFormat` is `prores` or `hdr_prores`. The HDR ProRes format accepts `422`, `422 HQ`, or `4444`. ## Retrieve the result Save the returned `id` and use [Get a Runway task](./runway-to-get-task-details). When `status` is `SUCCEEDED`, read the video URLs in `output`. ## OpenAPI ````yaml api/openapi/video/runway/official-format/post-generate-a-video-from-text.openapi.json POST /runwayml/v1/text_to_video openapi: 3.1.0 info: title: Create a Runway text-to-video task version: 1.0.0 description: Create a Runway text-to-video task through CometAPI. servers: - url: https://api.cometapi.com security: - bearerAuth: [] paths: /runwayml/v1/text_to_video: post: summary: Create a Runway text-to-video task description: >- Submit a JSON request and save the returned id. Use GET /runwayml/v1/tasks/{id} to retrieve the result. operationId: text_to_video requestBody: required: true content: application/json: schema: title: gen4.5 type: object properties: model: type: string description: Model ID for this request variant. const: gen4.5 enum: - gen4.5 promptText: description: >- Describe the requested scene or motion in 1 to 1,000 UTF-16 code units. type: string minLength: 1 maxLength: 1000 ratio: description: >- Requested output dimensions, expressed as width:height. Choose a value listed for this model and endpoint. type: string enum: - '1280:720' - '720:1280' duration: description: >- Requested video duration in whole seconds, from 2 through 10. type: integer minimum: 2 maximum: 10 seed: type: integer minimum: 0 maximum: 4294967295 description: >- Optional sampling seed. Use a positive integer for an explicit seed. Omission or 0 selects a random seed. contentModeration: type: object description: >- Optional content moderation settings. Omit the object to use standard moderation. properties: publicFigureThreshold: type: string description: >- Use auto for standard moderation or low for less restrictive public-figure filtering. enum: - auto - low required: - publicFigureThreshold additionalProperties: false outputFormat: description: >- Output encoding. Omit for mp4 (H.264). prores returns MOV; png_sequence returns a PNG ZIP; sdr_rec709_10bit returns 10-bit Rec.709 HEVC. hdr10 and hlg return 10-bit HDR MP4; hdr_pq_12bit_master returns 12-bit HEVC MOV; hdr_prores returns HDR ProRes MOV. The HDR PNG/EXR sequence formats return ZIP archives; the ACEScg variants target the named ACES version. type: string enum: - mp4 - prores - png_sequence - hdr10 - hlg - sdr_rec709_10bit - hdr_pq_12bit_master - hdr_prores - hdr_png_sequence - hdr_exr_sequence - hdr_exr_acescg_sequence_1_3 - hdr_exr_acescg_sequence_2_0 proresProfile: description: >- Profile for outputFormat prores or hdr_prores. Omit for 4444 with prores, or 422 HQ with hdr_prores. hdr_prores accepts only 422, 422 HQ, or 4444. Omit this field for other formats. type: string enum: - '422' - '4444' - 422 Proxy - 422 LT - 422 HQ - 4444 XQ required: - promptText - ratio - duration - model allOf: - if: required: - proresProfile then: required: - outputFormat properties: outputFormat: type: string description: Output format when proresProfile is supplied. enum: - prores - hdr_prores - if: required: - outputFormat properties: outputFormat: const: hdr_prores description: HDR ProRes output. then: properties: proresProfile: type: string description: Profile supported by HDR ProRes. enum: - '422' - 422 HQ - '4444' additionalProperties: false description: Request parameters for gen4.5. examples: Gen-4.5: summary: Gen-4.5 value: model: gen4.5 promptText: A paper boat drifts on calm water at sunrise. ratio: '1280:720' duration: 5 responses: '200': description: Task submitted. Save its id to retrieve task status. content: application/json: schema: type: object properties: id: type: string description: Task ID for GET /runwayml/v1/tasks/{id}. status: type: string description: Task state, when returned. createdAt: type: string description: Task submission timestamp, when returned. format: date-time output: type: array description: Result URLs, when returned. items: type: string format: uri failure: type: string description: Failure explanation, when returned. failureCode: type: string description: Machine-readable failure code, when returned. estimatedCost: type: object description: Task estimate metadata, when returned. properties: credits: type: integer description: Credit value reported with the task. required: - credits additionalProperties: false cost: type: object description: Task cost metadata, when returned. properties: credits: type: integer description: Credit value reported with the task. required: - credits additionalProperties: false required: - id additionalProperties: false example: id: 00000000-0000-4000-8000-000000000001 '400': description: Invalid request or unavailable task ID. content: application/json: schema: oneOf: - type: object description: Task request error. properties: code: type: - string - integer description: Machine-readable task error code. message: type: string description: Error explanation. data: description: Additional error details, when returned. required: - code - message additionalProperties: true - type: object description: Request authentication or validation error. properties: error: type: object description: Error details. properties: message: type: string description: Error explanation. type: type: string description: Error category. code: type: - string - integer - 'null' description: Error code, when returned. required: - message additionalProperties: true required: - error additionalProperties: true '401': description: Authentication failed. content: application/json: schema: type: object description: Request authentication or validation error. properties: error: type: object description: Error details. properties: message: type: string description: Error explanation. type: type: string description: Error category. code: type: - string - integer - 'null' description: Error code, when returned. required: - message additionalProperties: true required: - error additionalProperties: true x-codeSamples: - lang: Shell label: Gen-4.5 source: | curl "https://api.cometapi.com/runwayml/v1/text_to_video" \ --request POST \ --header "Authorization: Bearer $COMETAPI_KEY" \ --header "Content-Type: application/json" \ --data '{ "model": "gen4.5", "promptText": "A paper boat drifts on calm water at sunrise.", "ratio": "1280:720", "duration": 5 }' - lang: Python label: Gen-4.5 source: | import os import requests payload = {'model': 'gen4.5', 'promptText': 'A paper boat drifts on calm water at sunrise.', 'ratio': '1280:720', 'duration': 5} response = requests.post( "https://api.cometapi.com/runwayml/v1/text_to_video", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json=payload, timeout=60, ) response.raise_for_status() print(response.json()["id"]) - lang: JavaScript label: Gen-4.5 source: | const payload = { "model": "gen4.5", "promptText": "A paper boat drifts on calm water at sunrise.", "ratio": "1280:720", "duration": 5 }; const response = await fetch( "https://api.cometapi.com/runwayml/v1/text_to_video", { method: "POST", headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify(payload), }, ); if (!response.ok) throw new Error(await response.text()); console.log((await response.json()).id); components: securitySchemes: bearerAuth: type: http scheme: bearer description: Use your CometAPI API key. ````