Recraft: Recraft V4

Recraft V4 is a text-to-image model for photorealistic scenes and original illustrations. Its raster output is suitable for design exploration, editorial artwork, and visual concepts that emphasize composition and natural textures.

Compare models

recraft-v4

AvailableRecraftImageSync

Price: From $0.04
Modalities: Image

About Recraft V4

Recraft V4 is Recraft's design-focused text-to-image model, covering stylized illustration through photoreal scenes. Recraft describes it as opinionated: it favors balanced composition, cohesive color, and deliberate aesthetic choices over generic stock-photo output. The standard tier is the base raster model; Pro, Styles, and vector variants of V4 are listed as separate models.

Where it works well

Reads long, detailed creative direction and follows relationships such as reflections, materials, and how a subject sits against its background.
Renders legible text for infographics, menus, signage, and packaging mockups, according to Recraft.
Produces a deliberately art-directed look, from stylized illustration to photoreal, rather than flat stock imagery.
Balanced composition and controlled detail make first results usable as design starting points.

When to choose another model

This tier outputs at standard resolution; the Pro model is Recraft's choice for large print-ready work.
Its opinionated look is a poor match for plain, neutral product imagery, where the V4.1 Utility models fit better.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Text to imageTokenLab endpoint

POST/v1/images/generations

curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "n": 1,
  "operation": "text-to-image",
  "size": "1024x1024",
  "model": "recraft-v4",
  "prompt": "A minimalist product photo of matte black headphones on a soft blue background."
}'

Parameters

Text to image

Parameter	Values and limits	Default	Notes
`n`	1	`1`	Not provided
`operation`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`response_format`	url, b64_json	Not provided	Not provided
`size`	1024x1024	Not provided	Not provided

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Text to image

per image

Official price: $0.04
Verified price: —
Discount: —

	Official priceper image	Verified priceper image	Discount
Text to image	$0.04	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 15, 2026, 1:51 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Recraft V4 in Console with a prompt ready to edit or send.

Help me create an image with recraft-v4 using text-to-image at /v1/images/generations. Show the result, cost, and any limits I should know.

Use cases

Best for

Text to Image

Editorial artwork
Create a magazine-style illustration or a stylized photo shoot concept from a paragraph of art direction, then iterate on mood and palette.
Packaging and signage concepts
Mock up a menu board or product label with readable lettering to show a client before real artwork exists.
Infographic drafts
Generate a layout with headings and labelled sections as a visual draft that a designer then rebuilds in a layout tool.

Prompt examples

A magazine cover illustration of a lighthouse at dusk, muted teal and orange, bold title lettering reading NORTH COAST.

A chalkboard cafe menu with three drinks and their names clearly legible, warm lamp light.

Studio photoshoot of a silver chair on a red backdrop, reflections on a glossy floor, dramatic angle.

FAQ

What is Recraft V4 good at?

Design-led imagery. Recraft emphasizes balanced composition, cohesive color, controlled detail, and legible text in things like menus, signage, and packaging. It spans stylized illustration to photoreal, with a clear point of view instead of a neutral stock look.

How does Recraft V4 differ from V4 Pro?

V4 Pro is the same generation at higher resolution and finer detail; Recraft gives 2048 by 2048 pixels for the Pro model. Use the standard V4 to explore directions and Pro once you know which composition to finish.

Is Recraft V4 the same as Recraft V4.1?

No. V4.1 is the later release with quieter, more realistic photorealism and added Flash and Utility tiers. V4 is the earlier and more stylized, opinionated generation, so results differ for the same prompt.

Does this model produce SVG?

No, it returns raster images. Recraft offers V4 Vector and V4 Pro Vector for editable SVG, and a separate vectorize model converts an existing raster image.

How much does Recraft V4 cost?

On TokenLab, Recraft V4 costs $0.04 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Recraft V4 use?

Use https://api.tokenlab.sh/v1/images/generations for Recraft V4. The request example below shows the matching code shape.

Which operations does Recraft V4 support?

Recraft V4 supports Text to image. Select an operation above to see its endpoint and request example.