# GPT-1 | Image Generation

OpenAI Image Generation creates images from text descriptions using AI. Just type what you want to see, and it generates a matching picture.

## API Information

- **Model Slug:** openai-image-generation
- **Branded URL:** https://www.eachlabs.ai/openai/gpt-image/openai-image-generation
- **Provider:** OpenAI
- **Category:** Text to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Input at $10 per 1M tokens, output at $40 per 1M tokens
- **Estimated Processing Time:** 40 seconds
- **Last Updated:** 2026-04-09
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/openai-image-generation

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Input at $10 per 1M tokens, output at $40 per 1M tokens

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Input at $10 per 1M tokens, output at $40 per 1M tokens |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| output_format | string | No | jpeg | png,jpeg,webp | - |
| output_compression | integer | No | - | 0–100 | - |
| prompt | string | Yes | - | - | - |
| number_of_images | integer | No | 1 | 1–10 | - |
| quality | string | No | auto | auto,high,medium,low | - |
| background | string | No | auto | auto,transparent,opaque | - |
| image_size | string | No | auto | auto,1024x1024,1536x1024,1024x1536 | - |

## 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": "openai-image-generation",
  "input": {
    "prompt": "A vibrant and surreal flower with glowing petals in a dreamy color palette, featuring intricate details and ethereal lighting, surrounded by floating orbs of light in a misty forest at twilight, with soft rays of light piercing through the fog and illuminating the petals."
  }
}'
```

## 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

OpenAI Image Generation is a state-of-the-art AI model developed by OpenAI for creating images from natural language text descriptions. The model is designed to interpret detailed prompts and generate high-quality, contextually relevant images that match the user's intent. It is the latest in a series of image generation models from OpenAI, building on the capabilities of earlier systems like DALL-E and DALL-E 3.

Key features include advanced prompt understanding, support for parameterized editing (such as masking and inpainting), and multiple output quality and resolution options. The model is notable for its ability to produce images that closely align with user instructions, offering fine-grained control over image attributes and regions. Its underlying technology leverages large-scale diffusion or transformer-based architectures trained on extensive datasets, enabling both creative and precise image synthesis.

What sets OpenAI Image Generation apart is its explicit support for region-specific edits, reproducible API workflows, and robust policy enforcement for ethical image creation. The model is widely used in both creative and professional settings, with documented strengths in compositional accuracy and parameterized editing 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.