Runway Gen-3 Video API

Quick start

Platform: Wizzx gateway; use Authorization: Bearer <your_api_key>.
Submit: POST https://api.wizzx.ai/api/v1/task/submit/runway-gen3, async task_id.
Poll: POST https://api.wizzx.ai/api/v1/task/status with task_id.
Modes: text-to-video (text prompt only), image-to-video (1 reference image).

Auth

Authorization: Bearer <your_api_key>

Submit job

Endpoint: POST https://api.wizzx.ai/api/v1/task/submit/runway-gen3, Content-Type: application/json

Field	Type	Required	Default	Description
`prompt`	string	Yes	-	Text prompt describing the video
`type`	string	Yes	-	`text-to-video` or `image-to-video`
`image_urls`	array	Conditional	-	Image URLs (required for `image-to-video`, max 1)
`duration`	int	No	5	Video duration: `5` or `10` seconds
`resolution`	string	No	`720p`	`720p` or `1080p` (10s does not support 1080p)
`fps`	int	No	24	Frame rate: `24`, `30`, or `60`
`aspect_ratio`	string	No	auto	`16:9`, `9:16`, or `1:1`

Constraint: 10-second videos cannot use 1080p resolution.

Example: Text-to-Video

curl -X POST https://api.wizzx.ai/api/v1/task/submit/runway-gen3 \
  -H "Authorization: Bearer <api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A cinematic drone flythrough of a neon city at night",
    "type": "text-to-video",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }'

Example: Image-to-Video

curl -X POST https://api.wizzx.ai/api/v1/task/submit/runway-gen3 \
  -H "Authorization: Bearer <api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Make the character walk forward gracefully",
    "type": "image-to-video",
    "image_urls": ["https://example.com/character.jpg"],
    "duration": 5,
    "resolution": "720p"
  }'

Success response:

{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "4bbbc9e0-8de8-4f35-a31e-8596c1a6d18a",
    "model_key": "runway-gen3",
    "credits_deducted": 5
  },
  "request_id": "d54c66a8-0f0f-439c-bd3a-36f3fd275881"
}

Query status

Endpoint: POST https://api.wizzx.ai/api/v1/task/status

{
  "task_id": "4bbbc9e0-8de8-4f35-a31e-8596c1a6d18a"
}

Response (succeeded):

{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "4bbbc9e0-8de8-4f35-a31e-8596c1a6d18a",
    "status": "SUCCEEDED",
    "result_urls": ["https://cdn.example.com/video.mp4"],
    "error": "",
    "credits_deducted": 5
  },
  "request_id": "499347b1-ff99-4ba2-a977-ad655431919d"
}

Client-visible states: PENDING, QUEUED, PROCESSING, REVIEW_REQUIRED, SUCCEEDED, and FAILED. See the task status API reference.

Pricing

Duration	Resolution	Credits
5s	720p	5
5s	1080p	10
10s	720p	5
10s	1080p	Not supported

Best practices

Duration & Resolution:
- For longer videos (10s), use 720p resolution
- 1080p is only available for 5-second videos
Mode Selection:
- Use text-to-video for pure text-driven generation
- Use image-to-video when you have a reference image for better consistency
Aspect Ratio:
- Use 16:9 for landscape videos
- Use 9:16 for portrait/vertical videos
- Use 1:1 for square videos
- Leave empty for auto-detection (recommended for image-to-video)
Frame Rate: Use 24 for a cinematic look, or 30/60 when smoother motion is more important.

Getting started

Agent integrations

Video Generation

Image Generation

Runway Gen-3 Video API

Quick start

Auth

Submit job

Example: Text-to-Video

Example: Image-to-Video

Query status

Pricing

Best practices

​Quick start

​Auth

​Submit job

​Example: Text-to-Video

​Example: Image-to-Video

​Query status

​Pricing

​Best practices

Quick start

Auth

Submit job

Example: Text-to-Video

Example: Image-to-Video

Query status

Pricing

Best practices