# GPT Image 1 Mini - Core.Today AI API

> Cheaper, faster tier of OpenAI's GPT Image 1, served through the LLM gateway via the OpenAI Images API. Same token-billed generation flow at a fraction of the cost - ideal for drafts and high-volume image generation.

- **Provider**: OpenAI
- **Model ID**: gpt-image-1-mini
- **Category**: Image Generation
- **Credits**: 8 per image (approx, 1024×1024)
- **Speed**: Fast
- **Quality**: High

## Features
- Cheaper, faster image generation tier of GPT Image 1
- Token-based billing: text input tokens (3,716 credits/1M) and image output tokens (14,864 credits/1M) are billed separately
- Natively multimodal generation flow (text and image inputs, image outputs)
- Served through the LLM gateway via the OpenAI Images API

## Use Cases
- Low-cost draft iteration before a final GPT Image 1 render
- High-volume image generation pipelines
- Thumbnails and placeholder art
- Rapid prompt experimentation

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **model**: string - Model identifier
- **prompt**: string - A text description of the desired image

### Optional
- **size**: string (default: auto) - Output image size
  Options: 1024x1024, 1536x1024, 1024x1536, auto
- **quality**: string (default: auto) - Rendering quality. Higher quality produces more image output tokens and therefore costs more
  Options: low, medium, high, auto
- **background**: string (default: auto) - Set whether the background is transparent, opaque, or chosen automatically
  Options: auto, transparent, opaque
- **output_format**: string (default: png) - Output image format
  Options: png, jpeg, webp
- **n**: integer (default: 1) - Number of images to generate. Each image bills its own output tokens

## Examples

### Draft Iteration
Cheap, fast image draft via the OpenAI Images API
```json
{
  "model": "gpt-image-1-mini",
  "input": {
    "model": "gpt-image-1-mini",
    "prompt": "A minimalist flat-design logo concept for a coffee brand, warm palette",
    "size": "1024x1024"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Works with the OpenAI SDK - set base_url to https://ai.api.core.today/llm/openai/v1 and use client.images.generate()
- Billing is token-based: text input tokens at 3,716 credits/1M plus image output tokens at 14,864 credits/1M - larger sizes and higher quality produce more output tokens
- The ~8 credits per image figure assumes a 1024×1024 output; treat it as an estimate, not a flat rate
- Roughly 5x cheaper than GPT Image 1 - iterate here, then switch models for the final render

## Documentation
https://platform.openai.com/docs/models/gpt-image-1-mini