Recraft AI's text-to-vector model for generating production-ready SVG vector images with clean geometry, structured layers, and editable paths
Details
recraft-v4-svg
Starting from
Prices shown are in USD
See all providersProviders & Pricing (2)
Recraft V4 SVG is available from 2 providers, with per-image pricing starting at $0.08 through fal.ai.
fal/recraft-v4-svg
replicate/recraft-v4-svg
Recraft V4 SVG API OpenAI-compatible
Integrate Recraft V4 SVG via Lumenfall's OpenAI-compatible API to generate editable vector images and scalable graphics directly within your application workflow.
https://api.lumenfall.ai/openai/v1
recraft-v4-svg
Code Examples
Text to Image
/v1/images/generationscurl -X POST \ https://api.lumenfall.ai/openai/v1/images/generations \ -H "Authorization: Bearer $LUMENFALL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "recraft-v4-svg", "prompt": "", "size": "1024x1024" }'# Response:# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://api.lumenfall.ai/openai/v1'});const response = await client.images.generate({ model: 'recraft-v4-svg', prompt: '', size: '1024x1024'});// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }console.log(response.data[0].url);from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.lumenfall.ai/openai/v1")response = client.images.generate( model="recraft-v4-svg", prompt="", size="1024x1024")# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }print(response.data[0].url)Parameter Reference
Core Parameters
| Parameter | Type | Description | Modes |
|---|---|---|---|
prompt
|
string | Required. Text prompt for image generation |
T2I
|
Size & Layout
| Parameter | Type | Description | Modes |
|---|---|---|---|
size
|
string |
Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9")
WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.
|
T2I
|
aspect_ratio
|
string |
Aspect ratio of the output image (e.g. "16:9", "1:1")
Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.
|
T2I
|
resolution
|
string |
Output resolution tier (e.g. "1K", "4K")
1K
Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.
|
T2I
|
| Output |
size
|
aspect_ratio
+
resolution
|
|
|---|---|---|---|
| Flexible | |||
|
Custom
1–14142px per side
|
"WxH" |
— | Any pixel dimensions within model constraints |
1K 27 sizes
| Output |
size
|
aspect_ratio
+
resolution
|
|
|---|---|---|---|
| 768 × 1536 | "768x1536" |
or |
"1:2"
+
"1K"
|
| 1536 × 768 | "1536x768" |
or |
"2:1"
+
"1K"
|
| 896 × 1280 | "896x1280" |
or |
"10:14"
+
"1K"
|
| 1280 × 896 | "1280x896" |
or |
"14:10"
+
"1K"
|
| 832 × 1344 | "832x1344" |
or |
"6:10"
+
"1K"
|
| 896 × 1216 | "896x1216" |
or |
"3:4"
+
"1K"
|
| 1216 × 896 | "1216x896" |
or |
"4:3"
+
"1K"
|
| 832 × 1280 | "832x1280" |
or |
"2:3"
+
"1K"
|
| 1280 × 832 | "1280x832" |
or |
"3:2"
+
"1K"
|
| 866 × 1212 | "866x1212" |
or |
"10:14"
+
"1K"
|
| 1183 × 887 | "1183x887" |
or |
"4:3"
+
"1K"
|
| 916 × 1145 | "916x1145" |
or |
"4:5"
+
"1K"
|
| 1145 × 916 | "1145x916" |
or |
"5:4"
+
"1K"
|
| 1024 × 1024 | "1024x1024" |
or |
"1:1"
+
"1K"
|
| 887 × 1182 | "887x1182" |
or |
"3:4"
+
"1K"
|
| 724 × 1448 | "724x1448" |
or |
"1:2"
+
"1K"
|
| 1448 × 724 | "1448x724" |
or |
"2:1"
+
"1K"
|
| 793 × 1322 | "793x1322" |
or |
"6:10"
+
"1K"
|
| 836 × 1254 | "836x1254" |
or |
"2:3"
+
"1K"
|
| 1254 × 836 | "1254x836" |
or |
"3:2"
+
"1K"
|
| 768 × 1365 | "768x1365" |
or |
"9:16"
+
"1K"
|
| 1365 × 768 | "1365x768" |
or |
"16:9"
+
"1K"
|
| 1211 × 865 | "1211x865" |
or |
"14:10"
+
"1K"
|
| 768 × 1344 | "768x1344" |
or |
"9:16"
+
"1K"
|
| 896 × 1152 | "896x1152" |
or |
"4:5"
+
"1K"
|
| 1152 × 896 | "1152x896" |
or |
"5:4"
+
"1K"
|
| 1344 × 768 | "1344x768" |
or |
"16:9"
+
"1K"
|
How these parameters work
size
Exact pixel dimensions
"1920x1080"
aspect_ratio
Shape only, default scale
"16:9"
resolution
Scale tier, preserves shape
"1K"
Priority when combined
size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.
How matching works
7:1 on a model with
4:1 and 8:1,
you get 8:1.
0.5K 1K 2K 4K)
or megapixel tiers (0.25 1).
If the exact tier isn't available, you get the nearest one.
Output & Format
| Parameter | Type | Description | Modes |
|---|---|---|---|
response_format
|
string |
How to return the image
url
b64_json
Default:
"url" |
T2I
|
output_format
|
string |
Output image format
png
jpeg
gif
webp
avif
Gateway converts to requested format if provider doesn't support it natively.
|
T2I
|
output_compression
|
integer | Compression level for lossy formats (JPEG, WebP, AVIF) |
T2I
|
n
|
integer |
Number of images to generate
Default:
1Gateway generates multiple images in parallel even if provider only supports 1.
|
T2I
|
Additional Parameters
| Parameter | Type | Description | Modes |
|---|---|---|---|
background_color
fal
|
object | The preferable background color of the generated images. |
T2I
|
colors
fal
|
array | An array of preferable colors |
T2I
|
enable_safety_checker
fal
|
boolean | If set to true, the safety checker will be enabled. |
T2I
|
Parameter Normalization
How we handle parameters across different providers
Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:
| Behavior | What happens | Example |
|---|---|---|
passthrough |
Sent as-is to the provider | style, quality |
renamed |
Same value, mapped to the field name the provider expects | prompt |
converted |
Transformed to the provider's native format | size |
emulated |
Works even if the provider has no concept of it | n, response_format |
Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.
Gallery
View all 4 imagesRecraft V4 SVG FAQ
How much does Recraft V4 SVG cost?
Recraft V4 SVG starts at $0.08 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.
How do I use Recraft V4 SVG via API?
You can use Recraft V4 SVG through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "recraft-v4-svg". Code examples are available in Python, JavaScript, and cURL.
Which providers offer Recraft V4 SVG?
Recraft V4 SVG is available through fal.ai and Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.
Overview
Recraft V4 SVG is a specialized text-to-vector model developed by Recraft AI designed to generate production-ready vector graphics from natural language prompts. Unlike standard diffusion models that produce rasterized pixels (PNG/JPG), this model outputs natively scalable SVG files with defined geometric paths. Its distinguishing feature is the ability to generate clean, professional-grade vector code that maintains high visual fidelity across different zoom levels without pixelation.
Strengths
- Clean Geometry and Pathing: Produces simplified, logical vector paths that avoid the “jagged” or overly complex anchor points common in automated tracing tools.
- Structured Layering: Organizes drawing elements into distinct, logical groups within the SVG file, making the output easier to manage in professional design software like Adobe Illustrator or Figma.
- Anatomical Accuracy: High performance in maintaining the structural integrity of subjects, particularly in medical, technical, or iconographic styles.
- Variable Detail Control: Capable of generating a wide range of vector outputs, from minimalist flat icons and logos to highly detailed line art and complex vector illustrations.
Limitations
- Stylistic Constraints: While excellent for graphic design and illustration, the model is not intended for photorealistic imagery or complex textures that rely on gradients and raster-heavy effects.
- Prompt Sensitivity for Code Output: The “cleanliness” of the resulting SVG code can vary; highly complex prompts may result in more nested groups or redundant paths compared to simpler iconographic requests.
- Niche Utility: The model is highly optimized for vector output; users requiring standard raster images for web backgrounds or social media may find general-purpose diffusion models more flexible.
Technical Background
Recraft V4 SVG belongs to the Recraft V4 architecture family, specifically optimized for the unique constraints of vector mathematics rather than just pixel-based noise reduction. The training approach focuses on the relationship between descriptive text and the underlying syntax of SVG files, ensuring that the model understands not just visual aesthetics, but also the structural requirements of scalable graphics. This architectural focus allows the model to bypass the “tracing” step typically required to turn AI-generated images into vectors.
Best For
Recraft V4 SVG is ideal for UI/UX designers creating custom icon sets, brand identity developers generating logos, and technical illustrators requiring scalable diagrams. It is particularly useful for workflows where the output must be edited in vector-based software following generation. You can experiment with and integrate Recraft V4 SVG into your applications through Lumenfall’s unified API and playground.
Try Recraft V4 SVG in Playground
Generate images with custom prompts — no API key needed.