Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Recraft / Recraft V4.1

Recraft V4.1 Utility Pro Vector

Editable SVG image generation focused on flat lighting and predictable product compositions, with image-to-image transformation.

Image generation
availableClosed weightsImage generationImage editing
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
15 of 28 specification fields collected
Output formatsSVGSee specification notes below
Reference images1–10 style images; 64 MB combinedSee specification notes below
Input billingSee ratesRecraft
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)

Image references condition style; image-to-image editing is separately recorded and is not supported by every family.

Output modalities
ImageSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected

An MCP server can expose the image service to external agents; that is not native model function calling.

Structured output
Not collected

SVG images and JSON response envelopes do not establish schema-constrained text output.

Streaming
Not collected

Multipart image bytes remove a second download; that alone does not verify progressive generation streaming.

Batch processing
Not collected

Multiple images per generation request are documented; a separate Batch API is not verified.

Fine-tuning
Not collected

Custom reference styles do not require training; a model fine-tuning service has not been verified.

Knowledge cutoff
Not collected
Release date
May 2026Source for Release date (opens in a new tab)

The source specifies a month, not an exact release day.

Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected

Style reuse is documented, but inference caching and cache rates have not been verified.

Output formats
SVGSource for Output formats (opens in a new tab)
Maximum prompt characters
10,000 charactersSource for Maximum prompt characters (opens in a new tab)
Aspect ratios
View all 14 entries
  • 1:1
  • 2:1
  • 1:2
  • 3:2
  • 2:3
  • 4:3
  • 3:4
  • 5:4
  • 4:5
  • 6:10
  • 14:10
  • 10:14
  • 16:9
  • 9:16
Source for Aspect ratios (opens in a new tab)
Negative prompts
Not supportedSource for Negative prompts (opens in a new tab)
Position text in images
Not supportedSource for Position text in images (opens in a new tab)

Explicit positioning of text inside an image, not structured text generation.

Image-to-image editing
SupportedSource for Image-to-image editing (opens in a new tab)
Reference styles
SupportedSource for Reference styles (opens in a new tab)
Color palette control
SupportedSource for Color palette control (opens in a new tab)
Images per request
1–6 imagesSource for Images per request (opens in a new tab)

This is the synchronous n parameter, not evidence of an asynchronous Batch API.

Reference images
1–10 style images; 64 MB combinedSource for Reference images (opens in a new tab)

Optional style conditioning; a style must match the model it was created for.

Input image formats
PNG, JPG, WEBPSource for Input image formats (opens in a new tab)

Style-reference inputs. Image-to-image also accepts SVG on its own endpoint.

Style matching modes
flexible, preciseSource for Style matching modes (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Recraft

Provider source (opens in a new tab)
API model ID
recraftv4_1_utility_pro_vector
Access
Documented REST API. Account, bearer API token and a positive prepaid API-unit balance required; no paid generation was performed during review.
Regions
Not collected
API endpoint URL
POST https://external.api.recraft.ai/v1/images/generationsSource for API endpoint URL (opens in a new tab)
Output-specific API routes
/v1/images/generations/vectorSource for Output-specific API routes (opens in a new tab)

Output-type-enforcing route for the same model, not another checkpoint.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Image generationGeneration1$0.30image
Image style add-onStyle creation add-on2$0.005request

Rate conditions

  1. Direct Recraft API price per generated image. API units are $1 per 1,000 units; Studio subscription credits are separate.
  2. Additional charge per request that creates a style from attached references. Reusing an existing compatible style_id avoids creating another style. This is not a cache-token rate.
Pricing source (opens in a new tab)Pricing source (opens in a new tab)

Data & enterprise terms

The API policy states inputs and outputs are not used for training. Generated download URLs are retained for about 24 hours according to the API limits guide; the broader no-storage wording must not be interpreted as a verified zero-retention guarantee.

Read the service policy (opens in a new tab)

Recraft

Provider source (opens in a new tab)
API model ID
recraftv4_1_utility_pro_vector
Access
Documented REST API. Account, bearer API token and a positive prepaid API-unit balance required; no paid generation was performed during review.
Regions
Not collected
API endpoint URL
POST https://external.api.recraft.ai/v1/images/imageToImageSource for API endpoint URL (opens in a new tab)
Input image limits
Under 20 MB; at most 16 MP; each side 256–4096 pxSource for Input image limits (opens in a new tab)
Input image formats
PNG, JPG, WEBP, SVGSource for Input image formats (opens in a new tab)
Reference styles
Not supportedSource for Reference styles (opens in a new tab)

Style IDs on image-to-image apply to V3 only. V4/V4.1 style conditioning on text generation must not be inherited here.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Image generationImage to image1$0.30image

Rate conditions

  1. Direct Recraft per-image model rate; the image-to-image guide directs V4/V4.1 users to these model prices.
Pricing source (opens in a new tab)

Data & enterprise terms

The API policy states inputs and outputs are not used for training. Generated download URLs are retained for about 24 hours according to the API limits guide; the broader no-storage wording must not be interpreted as a verified zero-retention guarantee.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Recraft

recraftv4_1_utility_pro_vector
Not verified

Reusable styles and temporary output URLs do not establish inference-cache support.

How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Recraft

recraftv4_1_utility_pro_vector
Not verified

Reusable styles and temporary output URLs do not establish inference-cache support.

How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

The developer terms explicitly identify Recraft API models as proprietary, reserve underlying model rights and grant limited API access. The reviewed native model catalog ties this exact selector to that service.

Classification evidence (opens in a new tab)

Sources reviewed