Recraft Ai Recraft V4.1 Text To Image Utility
Playground
Try it on WavespeedAI!Recraft V4.1 Utility Text to Image is a fast, lightweight AI image generation model for high-volume creative workflows, ideation, A/B exploration, and content pipelines. Ready-to-use REST inference API for marketing visuals, product mockups, brand assets, social media content, creative design, rapid prototyping, and scalable text-to-image workflows with simple integration, no coldstarts, and affordable pricing.
Features
Recraft V4.1 Text-to-Image Utility
Recraft V4.1 Text-to-Image Utility is a faster, lighter variant of Recraft V4.1 built for high-volume raster image generation. It is well suited for quick ideation, A/B exploration, content pipelines, and general-purpose text-to-image workflows where speed and throughput matter.
Why Choose This?
-
Fast utility generation Generate raster images more quickly for iterative and high-volume workflows.
-
Great for ideation Useful for exploring visual directions, testing prompt variations, and building creative options at scale.
-
Simple prompt-based workflow Turn natural-language descriptions into finished images with minimal setup.
-
Preset image sizing Use
image_sizepresets for predictable output framing and composition. -
Production-friendly throughput A practical option for teams that need many images for experiments, pipelines, or content operations.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text prompt describing the image you want to generate. |
| image_size | No | Output image size preset. Default: square_hd. |
How to Use
- Write your prompt — describe the subject, style, composition, lighting, and mood you want.
- Choose image size (optional) — select the preset that best fits your intended layout.
- Submit — run the model and download the generated image.
Example Prompt
A clean modern product photo of wireless earbuds on a soft gradient background, studio lighting, subtle shadows, minimal premium commercial style
Pricing
Recraft official pricing for V4.1 Utility raster generation is a flat rate per image.
| Output | Cost |
|---|---|
| Per image | $0.04 |
Billing Rules
- Each generated image costs $0.04
- Pricing is fixed per image
image_sizedoes not affect pricing
Best Use Cases
- Quick ideation — Explore visual concepts rapidly from text prompts.
- A/B exploration — Generate many creative variants for comparison and testing.
- Content pipelines — Produce raster assets efficiently for ongoing workflows.
- Marketing visuals — Create banners, ad concepts, and branded images at scale.
- General text-to-image generation — Handle day-to-day creative image generation tasks with a faster runtime.
Pro Tips
- Keep prompts clear and specific for more controllable outputs.
- Use this utility variant when speed and iteration matter more than premium-tier rendering.
- Start with the default size preset unless you need a specific layout.
- Generate multiple prompt variations to compare different creative directions quickly.
Notes
promptis required.image_sizedefaults tosquare_hd.- The model returns a single raster image per request.
- Pricing is fixed at $0.04 per image.
Related Models
- Recraft V4.1 Text-to-Image — Standard raster image generation with the core V4.1 workflow.
- Recraft V4.1 Pro Text-to-Image — Premium raster generation for higher-end output quality.
- Recraft V4.1 Pro Text-to-Image Utility — Utility-oriented premium generation for higher-volume professional workflows.
- Recraft V4.1 Text-to-Vector — Generate editable SVG-style vector images from text prompts.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/recraft-ai/recraft-v4.1/text-to-image-utility" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"image_size": "1:1"
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Text prompt for the generated image. | |
| image_size | string | No | 1:1 | 1:1, 16:9, 9:16, 4:3, 3:4 | Output image size preset. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
| data.model | string | Model ID used for the prediction |
| data.outputs | string | Array of URLs to the generated content. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |