Recraft: Recraft V3
recraft-v3- Price
- From $0.04
- Modalities
- Image
About Recraft V3
Recraft V3 is the third-generation text-to-image model from Recraft, built for illustration, design, and brand-oriented pictures. Recraft credits it with a major step in photorealism and with being the first of its models to render mid-size text accurately. It stays the older, established look in the family, which suits applications that already tuned their prompts and style choices around it.
Where it works well
- Places text at a chosen location inside the image, which Recraft singles out as a capability unique to this generation.
- Recraft documents a curated style collection plus an unlimited AI-generated style library, so a look can be set by name rather than described in every prompt.
- An artistic-level setting shifts results from conventional compositions toward unusual angles and perspectives.
- Keeps one visual style consistent across several reference images without retraining.
When to choose another model
- It is a previous generation; V4 and V4.1 are Recraft's newer models and are the better start for new projects.
- It takes a text prompt only, so editing an existing picture needs a different model.
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 endpointPOST/v1/images/generationscurl -X POST "https://api.tokenlab.sh/v1/images/generations" \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ -d '{ "n": 1, "size": "1024x1024", "model": "recraft-v3", "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 |
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
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open Recraft V3 in Console with a prompt ready to edit or send.
Help me create an image with recraft-v3 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
Poster and social graphics
Generate a banner with a headline set at a specific spot, then re-run the prompt with another style to produce a matching set for a campaign.
Brand illustration sets
Pick a style once and produce a run of spot illustrations that share line weight and palette across a website or deck.
Stable legacy pipelines
Keep an application on V3 when its prompts and style settings were tuned for this model and output drift between generations would be costly.
Prompt examples
A flat illustration of a hot-air balloon over a patchwork valley, warm palette, the words SUMMER FAIR across the top in bold letters.
Product-style photo of a ceramic mug on a wooden desk, soft morning light, shallow depth of field.
A set of hand-drawn icons for a travel app: passport, suitcase, map pin, in one consistent line style.
FAQ
What is Recraft V3 used for?
Illustration, design assets, and brand-oriented images generated from text. Recraft highlights its photorealism and its ability to render mid-size text and place it at a precise spot in the image, so it fits posters, banners, and graphics that carry a headline.
Is Recraft V3 still worth using now that V4 exists?
For new work, test V4 or V4.1 first. V3 is the right choice when an existing application already depends on its look, because moving a tuned prompt set to a newer generation changes results and needs a fresh review.
Can Recraft V3 edit an existing image?
No. It generates a new raster image from a text prompt. For reference-driven work, use one of the Recraft V4 Styles models, or for turning a picture into SVG, the Recraft vectorize model.
Does Recraft V3 output vector files?
No. It returns raster images. Recraft sells a separate Recraft V3 Vector variant for SVG output, which is a different model. Choose Recraft V3 Vector or a V4 vector model when the deliverable must be SVG.
What does the artistic level setting do?
It controls how conventional the composition is. Recraft says lower values give familiar, portrait-like framing and higher values produce stranger perspectives and angles, so raise it when you want a less predictable picture.
How much does Recraft V3 cost?
On TokenLab, Recraft V3 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 V3 use?
Use https://api.tokenlab.sh/v1/images/generations for Recraft V3. The request example below shows the matching code shape.
Which operations does Recraft V3 support?
Recraft V3 supports Text to image. Select an operation above to see its endpoint and request example.
Compare Recraft V3
Guides that use Recraft V3
Sources
Reviewed Oct 2, 2026
More from Recraft