Runway Gen4 Image

Overview

Runway Gen4 Image generates still images from text prompts and optional reference images. Use it for higher-quality image generation when you need explicit aspect ratio, resolution, and seed controls.

Capability	Value
Model ID	`runway-gen4-image`
Modes	`text-to-image`, `image-to-image`
Prompt	Required non-empty string
Reference images	Required for `image-to-image`; optional for `text-to-image`; 1-3 public image URLs when provided
Aspect ratios	`1:1`, `16:9`, `9:16`, `4:3`, `3:4`
Resolution tiers	`720p`, `1080p`
Seed	Integer from `1` through `2147483647`

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
`POST`	`/generateTask/runway-gen4-image`	Submit an image generation task
`GET`	`/statusTask/runway-gen4-image?taskId={taskId}`	Poll task status and retrieve results

All requests require your APIXO API key:

Authorization: Bearer YOUR_API_KEY

Submit requests also require:

Content-Type: application/json

Copy-paste async quickstart

curl -X POST "https://api.apixo.ai/api/v1/generateTask/runway-gen4-image" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-image",
      "prompt": "A cinematic product photo of a silver running shoe on wet asphalt",
      "aspect_ratio": "4:3",
      "resolution": "1080p"
    }
  }'

Successful response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Save the taskId; you need it to poll for the final result.

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/runway-gen4-image?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Success response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://file.apixo.ai/runway-gen4-image.png\"]}",
    "createTime": 1782980000000,
    "completeTime": 1782980020000,
    "costTime": 20000
  }
}

Request body

Text-to-image

{
  "request_type": "async",
  "input": {
    "mode": "text-to-image",
    "prompt": "A fashion editorial portrait with dramatic side lighting",
    "aspect_ratio": "3:4",
    "resolution": "1080p",
    "seed": 123456
  }
}

Text-to-image with optional references

{
  "request_type": "async",
  "input": {
    "mode": "text-to-image",
    "prompt": "Use the reference composition but render it as a studio product photo",
    "image_urls": [
      "https://example.com/reference-1.png"
    ],
    "aspect_ratio": "4:3",
    "resolution": "1080p"
  }
}

Image-to-image

{
  "request_type": "async",
  "input": {
    "mode": "image-to-image",
    "prompt": "Keep the shoe silhouette but place it in a clean studio scene",
    "image_urls": [
      "https://example.com/reference-1.png"
    ],
    "aspect_ratio": "4:3",
    "resolution": "1080p"
  }
}

Parameters

request_type

string

default:"async"

Result delivery mode. Use async for polling with statusTask, or callback for webhook delivery.

callback_url

string

Required when request_type is callback. Must be a public HTTPS URL that can receive the final task payload. See Webhooks.

input

object

required

Runway Gen4 Image input parameters.

Show properties

mode

string

default:"text-to-image"

Generation mode. Supported values: text-to-image, image-to-image. If omitted, APIXO uses image-to-image when image_urls is non-empty; otherwise it uses text-to-image.

prompt

string

required

Text prompt describing the desired image. The prompt must be a non-empty string after trimming whitespace.

image_urls

string[]

Reference image URLs. Required for image-to-image. Optional for text-to-image. When provided in any mode, the array must contain 1 to 3 public, directly accessible image URLs.

aspect_ratio

string

default:"4:3"

Output aspect ratio. Supported values: 1:1, 16:9, 9:16, 4:3, 3:4.

resolution

string

default:"1080p"

Output resolution tier. Supported values: 720p, 1080p.

seed

integer

Optional seed. Must be a JSON integer from 1 through 2147483647; decimal values and quoted strings are not valid.

Response format

Submit task response

POST /generateTask/runway-gen4-image returns a task ID when the task is accepted:

code

integer

API status code. 200 means the task was accepted.

message

string

Human-readable status message.

data.taskId

string

Unique task identifier used with the status endpoint.

Status response fields

taskId

string

Unique task identifier.

state

string

Current task state: pending, processing, success, or failed.

resultJson

string

JSON string containing generated image URLs in resultUrls. Present when state is success.

failCode

string

Machine-readable failure code. Present when state is failed.

failMsg

string

Human-readable failure message. Present when state is failed.

createTime

integer

Task creation timestamp in Unix milliseconds.

completeTime

integer

Task completion timestamp in Unix milliseconds. Present after completion.

costTime

integer

Processing duration in milliseconds when available.

Webhook callback mode

Use callback mode when your backend should receive the final result automatically instead of polling.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/runway-gen4-image" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/webhooks/apixo",
    "input": {
      "mode": "image-to-image",
      "prompt": "Create a premium catalog image using this product reference",
      "image_urls": [
        "https://example.com/reference-1.png"
      ],
      "resolution": "1080p",
      "aspect_ratio": "4:3"
    }
  }'

See Webhooks for delivery requirements and retry behavior.

Billing

Runway Gen4 Image is billed per generated image. text-to-image and image-to-image use the same price for the same resolution.

Resolution	APIXO price
`720p`	`$0.05 / image`
`1080p`	`$0.08 / image`

Latency and polling

Actual latency may vary by prompt complexity, reference image accessibility, resolution, and current queue load.

Resolution	Typical generation time	Recommended first poll	Poll interval
`720p`	15s-30s	15s after task creation	3s-5s
`1080p`	20s-45s	20s after task creation	3s-5s

For production image workloads, use callback mode to avoid frequent polling while generation is still running.

Validation notes

Parameter	Backend behavior
`input.mode`	Optional. Supported values are `text-to-image` and `image-to-image`. If omitted, non-empty `image_urls` selects `image-to-image`; otherwise `text-to-image`.
`input.prompt`	Required string. Must not be empty after trimming whitespace.
`input.image_urls`	Required for `image-to-image`. Optional for `text-to-image`. When present, must be an array with 1-3 non-empty string URLs.
`input.aspect_ratio`	Optional. Defaults to `4:3`. Must be one of `1:1`, `16:9`, `9:16`, `4:3`, `3:4`.
`input.resolution`	Optional. Defaults to `1080p`. Must be `720p` or `1080p`.
`input.seed`	Optional JSON integer. Must be from `1` through `2147483647`.

Errors and troubleshooting

Code	Meaning	What to do
`400`	Invalid request body, mode, parameter value, or input image URL	Fix the request before retrying
`401`	Missing or invalid API key	Check the `Authorization` header
`402`	Insufficient balance or quota	Add balance or switch account/key
`403`	Key or route cannot access the model	Check permissions and route strategy
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server error or unknown generation failure	Retry with backoff
`502`	Generation service or network error	Retry with backoff
`504`	Generation timeout	Retry or use callback mode for long-running jobs

See Error Codes for the full error reference.

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Text-to-image

​Text-to-image with optional references

​Image-to-image

​Parameters

​Response format

​Submit task response

​Status response fields

​Webhook callback mode

​Billing

​Latency and polling

​Validation notes

​Errors and troubleshooting

​Related links

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Text-to-image

Text-to-image with optional references

Image-to-image

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Validation notes

Errors and troubleshooting

Related links