# GPT Image 2 HD on TokPort

> A GPT Image 2 variant that renders up to 2048 × 2048, for text-to-image and reference-image edits.

- Model id: gpt-image-2-hd
- Modality: image
- Price: $0.035 per image
- Base URL: https://api.tokport.io
- Auth: Authorization: Bearer <api key> (create one at https://tokport.io/dashboard/keys)
- OpenAPI: https://tokport.io/api/openapi?model=gpt-image-2-hd
- Human docs: https://tokport.io/models/gpt-image-2-hd/api

## Text to image — POST /v1/images/generations

Parameters:
- model (string, required): "gpt-image-2-hd"
- prompt (text, required): What to generate. Be concrete about subject, style, lighting and composition.
- size (enum): Output size as "WIDTHxHEIGHT" pixels. [one of 1024x1024 | 2048x2048; default 1024x1024]
- n (integer): Number of images to generate in one request. Each image is billed. [default 1; range 1-4]
- response_format (enum): Return hosted URLs (expire after a while) or inline base64 PNG data. [one of url | b64_json; default url]

Example:
```bash
curl https://api.tokport.io/v1/images/generations \
  -H "Authorization: Bearer $TOKPORT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-image-2-hd","prompt":"a neon koi swimming through clouds, cinematic lighting","size":"1024x1024","n":1}'
```

Response: Synchronous. `data[]` holds one entry per generated image with `url` (or `b64_json` when requested). The `X-Oneapi-Request-Id` response header identifies the request in your usage log.
```json
{
  "created": 1726400000,
  "data": [
    {
      "url": "https://cdn.example.com/generated/abc.png",
      "revised_prompt": "a neon koi swimming through clouds, cinematic lighting"
    }
  ]
}
```

## Image to image — POST /v1/images/edits

Parameters:
- model (string, required): "gpt-image-2-hd"
- image (image, required): Reference image as a public URL or a data: URL (PNG, JPEG or WebP, up to 8 MB).
- prompt (text, required): How the reference image should change. The model keeps what you do not mention.
- size (enum): Output size as "WIDTHxHEIGHT" pixels. [one of 1024x1024 | 2048x2048; default 1024x1024]
- n (integer): Number of images to generate in one request. Each image is billed. [default 1; range 1-4]
- response_format (enum): Return hosted URLs (expire after a while) or inline base64 PNG data. [one of url | b64_json; default url]

Example:
```bash
curl https://api.tokport.io/v1/images/edits \
  -H "Authorization: Bearer $TOKPORT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-image-2-hd","image":"https://example.com/reference.png","prompt":"put the product on a marble pedestal with soft studio lighting","size":"1024x1024","n":1}'
```

Response: Synchronous. `data[]` holds one entry per generated image with `url` (or `b64_json` when requested). The `X-Oneapi-Request-Id` response header identifies the request in your usage log.
```json
{
  "created": 1726400000,
  "data": [
    {
      "url": "https://cdn.example.com/generated/abc.png",
      "revised_prompt": "a neon koi swimming through clouds, cinematic lighting"
    }
  ]
}
```