Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
Aucune vidéo pour le moment. Envoyez le formulaire pour générer une vidéo.
Explorez différents cas d'utilisation et configurations de paramètres
Tarifs transparents sans frais cachés. Payez à l'utilisation.
| Règle & Modalité | Channel | Crédits | Prix (USD) | Prix officiel / référence | Économie quotidienne |
|---|---|---|---|---|---|
test videoRunway | Regular | 999per run | $4.541 | - | - |
Guide complet d'utilisation de runway-gen
Build cinematic AI video workflows with the Runway API on ApiPass. Use the unified runway/gen model to generate videos from text prompts or animate a single input image, with support for 5-second and 10-second durations, 720p and 1080p output, async task querying, and completion callbacks.
The Runway API gives developers access to advanced AI video generation through a clean task-based interface. On ApiPass, the public model runway/gen unifies text-to-video and image-to-video in one request format: provide a valid image_url to animate an image, or omit the image to generate directly from a text prompt. This makes it easy to integrate high-quality video creation into creative tools, marketing platforms, media pipelines, and automated content workflows.
Generate videos directly from natural language prompts. Describe the scene, subject, movement, camera direction, and style, then choose duration, quality, and aspect ratio for the final output.
Provide one HTTP(S) image URL and a motion prompt to transform a static image into dynamic footage. When an image is supplied, the task automatically runs in image-to-video mode and the image determines the aspect ratio.
Create a task with POST /api/v1/jobs/createTask, then query completion with GET /api/v1/jobs/recordInfo using the returned taskId. You can also provide callBackUrl to receive the final task result automatically.
Use runway/gen for both text-to-video and image-to-video. A valid image_url switches the request into image-to-video mode; otherwise, the same endpoint handles text-to-video generation.
Choose 5-second or 10-second videos, 720p or 1080p quality, and text-to-video aspect ratios including 16:9, 4:3, 1:1, 3:4, and 9:16. Note that 10-second generation cannot be combined with 1080p quality.
Runway generation is asynchronous. Query task states such as waiting, queuing, generating, success, and fail, or configure a callback URL so ApiPass posts the final result when generation completes.
Generate short product reveals, social ads, campaign teasers, and brand visuals from concise prompts. The Runway API is well suited for teams that need fast video variations at scale.
Turn portraits, product images, concept art, or storyboards into motion clips using image-to-video generation. Provide one source image and describe how the scene should move.
Integrate Runway generation into editors, design platforms, internal production tools, and automated publishing workflows with a simple async task API and callback support.
Use the ApiPass task workflow to submit generation jobs, monitor progress, and retrieve video URLs safely.
Send a POST request to /api/v1/jobs/createTask with model set to runway/gen and an input object containing prompt, duration, quality, and any optional image_url, aspect_ratio, or watermark values.
The create response returns data.taskId. Use that taskId with /api/v1/jobs/recordInfo to check states including waiting, queuing, generating, success, and fail. If callBackUrl is provided, ApiPass posts the final result to your endpoint.
Generated videos may be deleted after 14 days. Query completed tasks or process callbacks as soon as possible, then transfer the resultUrls video files to your own storage.
Runway generation uses credit-based pricing. On the regular route, 5 seconds at 720p costs 17 credits, 10 seconds at 720p costs 37 credits, and 5 seconds at 1080p costs 37 credits.
Pricing is the same for text-to-video and image-to-video. The billing rule is based on duration and quality rather than whether an input image is provided.
duration=10 with quality=1080p is not allowed. Use 10 seconds with 720p, or choose 5 seconds when generating at 1080p.
Start with a prompt, choose duration and quality, and optionally add a single image URL. Use text-to-video when image_url is empty, or image-to-video when a valid image URL is provided.
Send your request to POST /api/v1/jobs/createTask with model set to runway/gen. Include prompt, duration, quality, and aspect_ratio for text-to-video tasks without an image.
Use the returned taskId to query /api/v1/jobs/recordInfo, or provide callBackUrl to receive the final result automatically. Download generated videos from resultJson.resultUrls and save them to your own storage.
Toutes les API nécessitent une authentification via un token Bearer.
Authorization: Bearer
Submit a unified Runway runway/gen task for text-to-video or image-to-video generation.
The API accepts a JSON payload with the following structure:
1{
2 "model": "runway/gen",
3 "callBackUrl": "string (optional)",
4 "channel": "auto",
5 "input": {
6 "prompt": "string",
7 "image_url": "string (optional)",
8 "duration": 5,
9 "quality": "720p",
10 "aspect_ratio": "16:9",
11 "watermark": "string (optional)"
12 }
13}modelRequisstringThe ApiPass public model name. Use runway/gen for both text-to-video and image-to-video generation.
"runway/gen"
callBackUrlOptionnelstringCallback URL for task completion notifications. If omitted, no callback will be sent.
"https://your-domain.com/api/callback"
channelOptionnelstringYou may specify the corresponding provider within APIPASS via the channel parameter; these providers handle the actual image and video generation tasks. APIPASS currently offers three provider options:
The default value for the channel parameter is auto. When enabled, APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics to balance minimal cost and reliable performance. Retain the default auto value unless you have custom routing requirements.
Options disponibles :
auto
The input object contains the generation parameters. A valid image URL switches the task to image-to-video; without an image, the task is processed as text-to-video.
input.promptRequisstringPrompt describing the video to generate. This must be a non-empty string.
Maximum length: 1800 characters. Provide a clear action, scene, camera motion, subject, and style for best results.
"A cat walking through a sunlit garden"
input.image_urlOptionnelstringHTTP(S) image URL used for image-to-video generation. If omitted or empty, the task is treated as text-to-video.
Only one image is supported. Compatible aliases include imageUrl, image, input_image, inputImage, image_urls, imageUrls, and images. A URL string or a list containing exactly one image URL is accepted.
"https://example.com/cat.png"
input.durationRequisintegerVideo duration in seconds. Supported values are 5 and 10.
String values "5" and "10" are accepted for compatibility and are sent upstream as numbers. duration=10 cannot be used with quality=1080p.
Options disponibles :
5
input.qualityRequisstringOutput video quality. Supported values are 720p and 1080p.
The compatible field name resolution is also accepted. quality=1080p cannot be combined with duration=10.
Options disponibles :
"720p"
input.aspect_ratioOptionnelstringAspect ratio for text-to-video generation. Required when no image is provided; ignored when an image is provided.
Required for text-to-video tasks without an image. Ignored for image-to-video tasks because the input image determines the aspect ratio. Compatible aliases include aspectRatio, ratio, and size.
Options disponibles :
"16:9"
input.watermarkOptionnelstringOptional watermark text to apply to the generated video.
An empty string means no watermark. Compatible alias: waterMark.
""
1curl -X POST "https://api.apipass.dev/api/v1/jobs/createTask" \
2 -H "Content-Type: application/json" \
3 -H "Authorization: Bearer YOUR_API_KEY" \
4 -d '{
5 "model": "runway/gen",
6 "callBackUrl": "https://your-domain.com/api/callback",
7 "channel": "auto",
8 "input": {
9 "prompt": "A cat walking through a sunlit garden",
10 "duration": 5,
11 "quality": "720p",
12 "aspect_ratio": "16:9"
13 }
14 }'1{
2 "code": 200,
3 "message": "success",
4 "data": {
5 "taskId": "task_12345678"
6 }
7}codeStatus code. 200 indicates success; other values indicate failure.
messageResponse message. When the request fails, this contains the error description.
data.taskIdTask ID used to query the generation status and retrieve the result.
ByteDance
ByteDance
À partir de
0 crédits
ByteDance
ByteDance
À partir de
0 crédits
ByteDance
ByteDance
Turn text, images, video clips, and audio into cinematic, audio-synced videos with a single API call.
À partir de
0 crédits
MiniMax
MiniMax
À partir de
0 crédits
ByteDance
ByteDance
Generate cinematic 4K AI videos up to 30 seconds with Seedance 2.5's multimodal power.
À partir de
0 crédits
Google Veo 3.1 is the latest state-of-the-art generative video model designed to transform text and image prompts into high-fidelity cinematic visuals. Building upon its predecessors, Veo 3.1 features significant upgrades in prompt adherence, visual realism, and native audio generation, creating 8-second clips with synchronized sound effects and dialogue.
À partir de
0 crédits
wan
wan
À partir de
0 crédits
Kling
Kling
Transform text prompts and images into high-quality videos with advanced AI. Generate cinematic content with customizable duration, aspect ratio, and audio capabilities.
À partir de
0 crédits
MiniMax
MiniMax
Generate high-quality AI videos from text prompts or images with MiniMax's Hailuo 2.3 model. Support for both 6s and 10s durations, 768p and 1080p resolutions, with intelligent prompt optimization.
À partir de
0 crédits
grok
grok
Grok Imagine is xAI’s AI video generation model for creating high-quality videos with realistic motion, native audio, and synchronized speech. Grok Imagine 1.5 introduces faster generation speeds, improved motion physics, and stronger visual consistency for modern AI video applications.
À partir de
0 crédits
Luma
Luma
À partir de
0 crédits
Kling
Kling
Kling v3 video generation model, supports text-to-video and image-to-video, up to 15 seconds, 1080p pro mode
À partir de
0 crédits
wan
wan
Generate videos with cinematic consistency by reimagining existing footage through high-fidelity visual transformation and structural control.
À partir de
0 crédits
À partir de
0 crédits
grok
grok
À partir de
0 crédits
kling
kling
À partir de
0 crédits