# Recraft V4.1

> Generate a polished, high-resolution raster image from a text prompt — Recraft's newest V4.1 model, producing imagery up to 2048×2048 with professional composition, lighting, and materials at an economical per-image price.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/recraft/v4.1/text-to-image`
- **Model ID**: `recraft/v4.1/text-to-image`
- **Category**: text-to-image
- **Kind**: inference
- **Tags**: recraft, recraft-v4.1, text-to-image, image, design, photorealistic, illustration

## Pricing

- **Price**: $0.035 per output

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/recraft/v4.1/text-to-image` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/recraft/v4.1/text-to-image/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/recraft/v4.1/text-to-image/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/recraft/v4.1/text-to-image/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`prompt`** (`string`, _required_):
  The text description of the image to generate (subject, scene, lighting, mood). Output is a polished, high-resolution raster image.

- **`image_size`** (`ImageSize | ImageSizeEnum`, _optional_):
  The size/aspect of the generated image. Pick a preset or supply an explicit width/height (up to 2048x2048 or an ultra-wide crop).
  - Default: `"square_hd"`
  - Options: `"square_hd"`, `"square"`, `"portrait_4_3"`, `"portrait_16_9"`, `"landscape_4_3"`, `"landscape_16_9"`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "a hand-thrown ceramic teapot glazed in deep celadon green, resting on a rough linen cloth beside dried lavender sprigs, soft studio window light, minimalist product photography",
  "image_size": "square_hd"
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/kygJjHnbh4HAg5IXnOnOR.webp"
]
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/recraft/v4.1/text-to-image \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "a hand-thrown ceramic teapot glazed in deep celadon green, resting on a rough linen cloth beside dried lavender sprigs, soft studio window light, minimalist product photography",
  "image_size": "square_hd"
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("recraft/v4.1/text-to-image", {
  input: {
  "prompt": "a hand-thrown ceramic teapot glazed in deep celadon green, resting on a rough linen cloth beside dried lavender sprigs, soft studio window light, minimalist product photography",
  "image_size": "square_hd"
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "recraft/v4.1/text-to-image",
        arguments={
  "prompt": "a hand-thrown ceramic teapot glazed in deep celadon green, resting on a rough linen cloth beside dried lavender sprigs, soft studio window light, minimalist product photography",
  "image_size": "square_hd"
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/recraft/v4.1/text-to-image)
- [OpenAPI Schema](https://modelrunner.ai/models/recraft/v4.1/text-to-image/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/recraft/v4.1/text-to-image/llms.txt)