Name: FireRed-Image-Edit 1.1 API: Instruction Image Editing
Brand: magicapi
SKU: api-magicapi-general-purpose-image-editing-api-prunaai-firered-image-edit-1-1
Availability: InStock
Author: API Market

Shashank Agarwal

# 🖌️ Instruction-Based Image Editing API (FireRedTeam FireRed-Image-Edit 1.1)

## Overview
FireRed-Image-Edit 1.1 is a general-purpose image editing model from FireRedTeam, served here in a speed-optimized build by Pruna AI. Its developer describes it as delivering high-fidelity and consistent editing across a wide range of scenarios.

Send one or more images in `image` and a text instruction in `prompt`, such as "change the raincoat color to red". Each request returns the URL of one edited image.

## Features
- **Edit by instruction**: describe the change in plain language in `prompt`.
- **Several input images**: `image` is a list, so you can pass the image to edit plus reference images (jpeg, png, gif or webp).
- **Aspect ratio**: keep the source dimensions with `match_input_image` (default) or choose `1:1`, `16:9`, `9:16`, `4:3` or `3:4`.
- **Guidance and steps**: `true_cfg_scale` (0 to 20, default 4) and `num_inference_steps` (1 to 100, default 40).
- **Fast mode**: `go_fast` (default `true`) uses optimized cache scheduling for faster generation.
- **Output formats**: `webp` (default), `jpg` or `png`, with `output_quality` from 0 to 100 (default 95).
- **Seed**: set `seed` to reproduce a result.

## Use Cases
1. **Product photo variations**: change the color or material of a product without a new shoot.
2. **Photo retouching**: add, remove or replace objects with a short instruction.
3. **Style changes**: restyle a photo while keeping its composition.
4. **Reference-guided edits**: pass a second image so the edit can use it as a reference.

## Visual Examples
### Example Input
![Input photo of a person in a raincoat](https://blog.api.market/wp-content/uploads/2026/10/firered-image-edit-1-1-input-api-market.webp)

Prompt: "change the raincoat color to red"

Settings: `aspect_ratio` `match_input_image`, `go_fast` `true`, `true_cfg_scale` 4, `num_inference_steps` 40, `output_format` `webp`, `output_quality` 95.

### Example Output
![FireRed-Image-Edit 1.1 output: the same photo with the raincoat changed to red](https://blog.api.market/wp-content/uploads/2026/10/firered-image-edit-1-1-output-q90nwc4s-api-market.webp)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | Text instruction describing the requested image edit |
| `image` | array of strings (URLs) | Yes |  |  | Input images to edit or use as references. Must be jpeg, png, gif or webp. |
| `aspect_ratio` | string | No | `match_input_image` | `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `match_input_image` | Aspect ratio override. Use `match_input_image` to preserve the source dimensions. |
| `seed` | integer | No | none |  | Random seed. Leave blank for a random seed. |
| `true_cfg_scale` | number | No | `4` | 0 to 20 | True CFG guidance scale |
| `num_inference_steps` | integer | No | `40` | 1 to 100 | Number of denoising steps |
| `go_fast` | boolean | No | `true` |  | Use optimized cache scheduling for faster generation |
| `output_format` | string | No | `webp` | `webp`, `jpg`, `png` | Format of the saved output image |
| `output_quality` | integer | No | `95` | 0 to 100 | Quality for jpg and webp outputs |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.024 per API unit.
- **1 API unit = one request with up to 14 seconds of processing.** A request that takes longer is billed one more unit for every started 14-second block (for example, 14 to 28 seconds is 2 units, $0.048).
- More `num_inference_steps`, more input images or `go_fast` set to `false` can take longer and use more units.
- **Example cost**: the example request took 13.1 seconds of processing, so it used 1 unit ($0.024).
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/general-purpose-image-editing-api-prunaai-firered-image-edit-1-1`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/general-purpose-image-editing-api-prunaai-firered-image-edit-1-1/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "2275e825ae9ed8a17168e0ea82ae6722fe60ca25652bb9e61b98887eb0ad5bcc",
    "input": {
      "image": [
        "https://blog.api.market/wp-content/uploads/2026/10/firered-image-edit-1-1-input-api-market.webp"
      ],
      "prompt": "change the raincoat color to red",
      "go_fast": true,
      "aspect_ratio": "match_input_image",
      "output_format": "webp",
      "output_quality": 95,
      "true_cfg_scale": 4,
      "num_inference_steps": 40
    }
  }'
```

Response (201 Created):
```json
{
  "id": "q90nwc4s09rp40d1d8mte8a4yr",
  "version": "2275e825ae9ed8a17168e0ea82ae6722fe60ca25652bb9e61b98887eb0ad5bcc",
  "status": "starting",
  "created_at": "2026-10-23T19:07:53.728Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/general-purpose-image-editing-api-prunaai-firered-image-edit-1-1/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "q90nwc4s09rp40d1d8mte8a4yr",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/firered-image-edit-1-1-output-q90nwc4s-api-market.webp",
  "error": null,
  "created_at": "2026-10-23T19:07:53.728Z",
  "started_at": "2026-10-23T19:07:54.728Z",
  "completed_at": "2026-10-23T19:08:07.728Z"
}
```

`output` is a single URL string pointing to the edited image.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `prompt`, an empty `image` list or an `aspect_ratio` that is not in the list.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/general-purpose-image-editing-api-prunaai-firered-image-edit-1-1";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "2275e825ae9ed8a17168e0ea82ae6722fe60ca25652bb9e61b98887eb0ad5bcc", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  image: ["https://blog.api.market/wp-content/uploads/2026/10/firered-image-edit-1-1-input-api-market.webp"],
  prompt: "change the raincoat color to red",
  go_fast: true,
  aspect_ratio: "match_input_image",
  output_format: "webp",
  output_quality: 95,
  true_cfg_scale: 4,
  num_inference_steps: 40
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/general-purpose-image-editing-api-prunaai-firered-image-edit-1-1"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "2275e825ae9ed8a17168e0ea82ae6722fe60ca25652bb9e61b98887eb0ad5bcc", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


print(create_and_wait_for_prediction({
    "image": ["https://blog.api.market/wp-content/uploads/2026/10/firered-image-edit-1-1-input-api-market.webp"],
    "prompt": "change the raincoat color to red",
    "go_fast": True,
    "aspect_ratio": "match_input_image",
    "output_format": "webp",
    "output_quality": 95,
    "true_cfg_scale": 4,
    "num_inference_steps": 40
}))
```

## FAQ
- **Why is `image` a list?**
  - The field accepts several images: the image to edit plus optional reference images. Send a list even for a single image, as in the example.
- **Will the output keep my image's size?**
  - With `aspect_ratio` at its default `match_input_image`, the source dimensions are preserved. Pick another ratio to change the shape.
- **How many images does one request return?**
  - One. `output` is a single image URL.
- **What does `go_fast` change?**
  - It is on by default and uses optimized cache scheduling for faster generation. Set it to `false` to turn it off.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page. You can also email our support team at hello@magicapi.com.


Edit images from a text instruction with FireRed-Image-Edit 1.1: change colors, objects and styles, with optional reference images.