metadata: {"openclaw":{"requires":{"env":["CREAAAPIKEY"]},"primaryEnv":"CREAAAPIKEY"}}

Creaa AI - Image, Edit & Video Generation

Generate and edit AI images, and generate AI videos directly from your terminal using the Creaa API.

Get your API key at: https://creaa.ai/profile -> API Keys
Top up API credits at: https://creaa.ai/pricing

Available Models

Image Models

Model ID	Name	Credits/Image	Free Daily	Default Ratio	Max Ref Images	Capabilities
INLINECODE0	Seedream 5.0	4	10	1:1	4	texttoimage, imagetoimage
INLINECODE1

Nano Banana 2 | 10 | 5 | auto | 14 | texttoimage, imagetoimage, multiimageedit | | nano-banana-pro | Nano Banana Pro | 20 | 1 | auto | 10 | texttoimage, imagetoimage, multiimageedit | | gpt-image-1.5 | GPT Image 1.5 | 15 | 0 | 1:1 | 10 | texttoimage, imagetoimage, multiimageedit | | z-image-turbo | Z-Image Turbo | 1 | - | 1:1 | - | texttoimage |

Aspect ratio options per model:

• - seedream-5.0: auto, 1:1, 3:4, 4:3, 16:9, 9:16, 2:3, 3:2, 21:9
• INLINECODE6 / nano-banana-pro: auto, 1:1, 9:16, 16:9, 3:2, 2:3
• INLINECODE8: 1:1, 3:2, 2:3
• INLINECODE9: 1:1, 9:16, 16:9

Video Models

Model ID	Name	Credits/sec	Durations (sec)	Default Duration	Capabilities
INLINECODE10	Veo 3.1	22	8	8	texttovideo, imagetovideo
INLINECODE11

Seedance 2.0 | 25 | 5, 10, 15 | 5 | texttovideo, imagetovideo | | sora-2-pro | Sora 2 Pro | 12 | 4, 8, 12, 16, 20 | 12 | texttovideo, imagetovideo | | seedance-1.5-pro | Seedance 1.5 Pro | 12 | 5, 8, 12 | 5 | texttovideo, imagetovideo, firstlastframe | | kling-3.0 | Kling 3.0 | 25 | 5, 10, 15 | 5 | texttovideo, imagetovideo | | hailuo-2.3 | Hailuo 2.3 | 25 | 6, 10 | 6 | texttovideo, imagetovideo | | runway-gen-4.5 | Runway Gen-4.5 | 30 | 5, 10 | 5 | imagetovideo |

Aspect ratio options per model:

• - veo-3.1: 16:9, 9:16
• INLINECODE18: 9:16, 16:9, 1:1, 3:4, 4:3
• INLINECODE19: 9:16, 16:9
• INLINECODE20: 9:16, 16:9, 1:1, 3:4, 4:3
• INLINECODE21: 16:9, 9:16
• INLINECODE22: 9:16, 16:9
• INLINECODE23: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9

Available Commands

All generation and edit tasks are asynchronous: submit a task, get a task_id, then poll for results.

Generate Image

Step 1: Submit task
CODEBLOCK0

Parameters:

• - prompt (required): Image description
• INLINECODE26 (optional): Model ID from the image models table above. Default: INLINECODE27
• INLINECODE28 (optional): Aspect ratio like 1:1, 16:9, 9:16. Must match the model's supported ratios. Default varies by model.
• INLINECODE32 (optional): Number of images, 1-4. Default 1

Response:
CODEBLOCK1

Step 2: Poll status (wait 5-10 seconds between polls for images)
CODEBLOCK2

Status Response (completed):
CODEBLOCK3

Image generation typically takes 10-60 seconds. Poll every 5 seconds.

Edit Image

Use this endpoint for:

• - Single-image edit: image_url or image_data (base64)
• Multi-image reference edit / composition: image_urls or image_data_list (base64)

Step 1: Submit task (with URL)
CODEBLOCK4

Step 1: Submit task (with base64 image data)
CODEBLOCK5

Single-image edit parameters:

• - prompt (required): Edit instruction
• INLINECODE38 (option A): Public source image URL
• INLINECODE39 (option B): Base64-encoded image data. Supports data:image/png;base64,... prefix or raw base64 string. Max 20MB.
• INLINECODE41 (optional): Model ID from the image models table above. Default: INLINECODE42
• INLINECODE43 (optional): Must match the model's supported ratios
• INLINECODE44 (optional): Number of output images, 1-4. Default 1

Provide either image_url or image_data for single-image edit. If both are provided, image_url takes priority.

Multi-image edit / composition example:
CODEBLOCK6

You can also use image_data_list with base64 strings instead of image_urls.

Multi-image edit notes:

• - image_urls or image_data_list: 2-N images, where N depends on the model
• Max reference images by model:

- seedream-5.0: up to 4 input images
- nano-banana-2: up to 14 input images
- nano-banana-pro: up to 10 input images
- gpt-image-1.5: up to 10 input images

• - Only models with multi_image_edit capability support this mode
• URLs must be public http(s) URLs; base64 data is uploaded to storage automatically

Response:
CODEBLOCK7

Step 2: Poll status
CODEBLOCK8

Status Response (completed):
CODEBLOCK9

Image editing typically takes 10-90 seconds. Poll every 5 seconds.

Generate Video

Step 1: Submit task
CODEBLOCK10

Parameters:

• - prompt (required): Video description
• INLINECODE59 (optional): Model ID from the video models table above. Default: INLINECODE60
• INLINECODE61 (optional): text_to_video (default) or INLINECODE63
• INLINECODE64 (option A, required for imagetovideo): URL of the source image
• INLINECODE65 (option B, required for imagetovideo): Base64-encoded image data. Supports data:image/png;base64,... prefix or raw base64 string. Max 20MB.
• INLINECODE67 (optional): Duration in seconds, must match the model's supported durations. Default varies by model.
• INLINECODE68 (optional): e.g. 16:9, 9:16, 1:1. Must match the model's supported ratios.

For image_to_video mode, provide either image_url or image_data. If both are provided, image_url takes priority.

Response:
CODEBLOCK11

Step 2: Poll status (wait 15 seconds between polls for videos)
CODEBLOCK12

Status Response (completed):
CODEBLOCK13

Status values: pending -> processing -> completed or failed.
Video generation typically takes 60-300 seconds. Poll every 15 seconds.

Unified Task Status Endpoint

Image generation, image edit, and video tasks all use the same status endpoint: CODEBLOCK14

Keep polling until status is completed or failed.

• - For images: poll every 5 seconds
• For videos: poll every 15 seconds

List Available Models

CODEBLOCK15

Returns full model catalog with pricing, supported aspect ratios/durations, capabilities, and max_upload_images for image-edit models.

Check Usage

CODEBLOCK16

Usage is tracked against the API key's own credit pool (api_credits), not the website account balance.

Billing Notes

• - Open API requests charge the API key credit pool, not the user's main website balance.
• If task submission fails before the job is queued, credits are refunded immediately.
• If a queued task fails, credits are refunded automatically.
• For image generation and image editing, partial success is billed by successful outputs; unused credits are refunded automatically.
• For video generation, successful jobs keep the full charge; failed jobs are refunded in full.

Model Selection Tips

Image models:

• - seedream-5.0 - Best quality, great default choice (10 free daily)
• INLINECODE86 - Best default for multi-image editing / composition (5 free daily)
• INLINECODE87 - Higher quality image editing (1 free daily)
• INLINECODE88 - Strong image editing option via Replicate-backed path
• INLINECODE89 - Free, fastest generation

Video models:

• - veo-3.1 - Highest quality, 8s fixed duration (22 credits/sec)
• INLINECODE91 - Best value with long durations up to 20s (12 credits/sec)
• INLINECODE92 - Affordable with firstlastframe support (12 credits/sec)
• INLINECODE93 - High quality, flexible durations (25 credits/sec)
• INLINECODE94 - Image-to-video only, high quality

Error Handling

If any API call returns "success": false, display the error message to the user. Common errors:

• - invalid_api_key: The API key is missing or wrong. User should check their key at https://creaa.ai/profile
• INLINECODE97: Too many requests per minute. Wait and retry.
• INLINECODE98: Not enough credits. User should top up at https://creaa.ai/pricing
• INLINECODE99: The image URL points to localhost, private network, or a non-http(s) source.
• INLINECODE100: The requested model can edit a single image but cannot do multi-image composition.