# Recraft v4.1 | Text to Vector

Generate fully editable SVG vectors from a simple text prompt with Recraft V4.1, purpose-built for logos, typography, icons, lettering, and flat illustrations on each::labs.

## API Information

- **Model Slug:** recraft-v4-1-text-to-vector
- **Branded URL:** https://www.eachlabs.ai/recraft/recraft-v4-1/recraft-v4-1-text-to-vector
- **Provider:** Recraft
- **Category:** Text to Image
- **Output Type:** image
- **Status:** active
- **Base Cost:** $0.08 per execution
- **Estimated Processing Time:** 13 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/recraft-v4-1-text-to-vector

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.08 per execution
- **Pricing Details:** default: $0.08

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text description of the desired vector image. |
| image_size | string | No | square_hd | square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9 | Aspect ratio / size preset for the generated vector image. |
| colors | array | No | - | - | Preferred color palette. Each entry is an RGB triple (0-255). |
| background_color | object | No | - | - | Preferred background color (RGB 0-255). |
| enable_safety_checker | boolean | No | true | - | Run safety checker on output. Default: true. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "recraft-v4-1-text-to-vector",
  "input": {
    "prompt": "A modern retail price tag design, clean white background, bold teal and purple geometric shapes as decorative elements, royal blue elegant border frame, golden yellow accent stripe at the top, minimalist typography layout with price area and barcode section at the bottom, flat vector style, professional retail branding, ultra clean graphic design"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated image)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**Recraft v4.1 | Text to Vector Overview**

Recraft v4.1 | Text to Vector is a text-to-image model from Recraft AI that generates clean, scalable vector artwork directly from natural language prompts. Instead of producing pixel-based raster images, it focuses on crisp SVG-style graphics suitable for logos, UI elements, icons, and flat illustrations. This vector-first capability is the primary differentiator of Recraft v4.1 | Text to Vector compared with most recraft text-to-image models that output bitmaps. Designers and developers can quickly move from concept to production-ready assets without manual vector tracing. Integrated through the Recraft v4.1 | Text to Vector API on each::labs, the model streamlines brand-safe, resolution-independent visuals for web, product, and marketing workflows.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.