> ## Documentation Index
> Fetch the complete documentation index at: https://www.recraft.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Recraft API
> Generate and edit raster and vector images with Recraft models over one REST API. Get a token, send a prompt, get an image.
**Building with an AI agent?** Give Claude, Cursor, or ChatGPT this one link. It has every model, parameter, and a working request:
```text theme={null}
https://www.recraft.ai/docs/api-reference/agents.md
```
Using Claude Code? Install the [Recraft skill](/docs/api-reference/ai-tools#claude-code-skill) once and ask for what you need.
## Your first image
Get a token on your [profile page](https://app.recraft.ai/profile/api) and set it once per terminal session:
```bash theme={null}
export RECRAFT_API_TOKEN=your_token
```
Then send a prompt:
```bash cURL theme={null}
curl https://external.api.recraft.ai/v1/images/generations \
-H "Authorization: Bearer $RECRAFT_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"prompt": "a red fox in a snowy forest, flat vector", "model": "recraftv4_1_vector"}'
```
```python Python theme={null}
import os
import requests
response = requests.post(
'https://external.api.recraft.ai/v1/images/generations',
headers={'Authorization': f"Bearer {os.environ['RECRAFT_API_TOKEN']}"},
json={'prompt': 'a red fox in a snowy forest, flat vector', 'model': 'recraftv4_1_vector'},
)
if not response.ok:
raise SystemExit(f'{response.status_code}: {response.text}')
print(response.json()['data'][0]['url'])
```
```python Python (OpenAI SDK) theme={null}
# pip install openai
import os
from openai import OpenAI
client = OpenAI(
base_url='https://external.api.recraft.ai/v1',
api_key=os.environ['RECRAFT_API_TOKEN'],
)
response = client.images.generate(
prompt='a red fox in a snowy forest, flat vector',
model='recraftv4_1_vector',
)
print(response.data[0].url)
```
```javascript JavaScript theme={null}
const response = await fetch('https://external.api.recraft.ai/v1/images/generations', {
method: 'POST',
headers: {
Authorization: `Bearer ${process.env.RECRAFT_API_TOKEN}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({ prompt: 'a red fox in a snowy forest, flat vector', model: 'recraftv4_1_vector' }),
});
if (!response.ok) throw new Error(await response.text());
console.log((await response.json()).data[0].url);
```
You get a link to an SVG file, valid for about 24 hours:
```json theme={null}
{
"created": 1759140000,
"credits": 80,
"data": [{ "image_id": "0e6a1b8c-5b1f-4a8e-9f3a-2c7d4e8b9a10", "url": "https://..." }]
}
```
New to the API? The [Quickstart](/docs/api-reference/getting-started) walks through each step.
## Models
About 1.3 s and \$0.007 per image, quality close to V4.1.
Raster Fastest
The default. Photorealism, illustration, and strong short prompts. From \$0.035.
Raster Vector Styles
Match any style from 1 to 10 reference images. From \$0.035.
Raster Vector Style match
Design taste and production-grade vectors. From \$0.04.
Raster Vector Styles
Curated styles, exact text placement, and all editing operations. From \$0.04.
Inpaint Outpaint Text layout
The cheapest vector option, for icons and simple illustration. From \$0.022.
Raster Vector Icons
Not sure which to pick? Compare them in [All models](/docs/api-reference/models/overview).
## What else you can do
Image to image, inpaint, outpaint, and erase region.
Remove, replace, or generate a background.
Turn a PNG or JPG into SVG for \$0.01.
Crisp or creative upscale, and refine details.
Save your brand look once, reuse it in every request.
Expand a short prompt into a detailed one.
## Reference
* [Endpoints](/docs/api-reference/endpoints): every operation with its parameters.
* [Pricing](/docs/api-reference/pricing) and [Limits and sizes](/docs/api-reference/appendix): prices, sizes, prompt limits, and rate limits.
* [Clients and SDKs](/docs/api-reference/clients): plain HTTP or the OpenAI Python library.
* [Use with AI tools](/docs/api-reference/ai-tools): `llms.txt`, Markdown pages, and the Claude Code skill.
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.