gpt-image-2.6-sunburst

GPT Image 2.6 Sunburst API — price per token

GPT Image 2.6 Sunburst generates static images from text and edits reference images through the Images API. Use the same API key and prepaid balance as your other GPT and Gemini models.

Pricing per 1M tokens

RateOfficial OpenAIHere (−50%)
Text input$5$2.5
Cached text input$1.25$0.625
Image input$8$4
Cached image input$2$1
Image output$30$15

Text input

Official OpenAI
$5
Here (−50%)
$2.5

Cached text input

Official OpenAI
$1.25
Here (−50%)
$0.625

Image input

Official OpenAI
$8
Here (−50%)
$4

Cached image input

Official OpenAI
$2
Here (−50%)
$1

Image output

Official OpenAI
$30
Here (−50%)
$15

Every request is metered at the official rate first, then the flat 50% B2C discount is subtracted before it touches your prepaid balance. Context window: per request. Max output: 1–10 images (n).

Best for

  • Creating static images from a text prompt.
  • Editing up to sixteen reference images in one request.
  • Returning PNG, JPEG or WebP from one Images API integration.

Good to know

  • Use gpt-image-2.6-sunburst with POST /v1/images/generations for new images or POST /v1/images/edits for reference edits. Edits accept 1–16 PNG, JPEG or WebP references as multipart image/image[] files or as a JSON images array of image_url values (HTTPS URL or base64 data URL). Hosted Responses image tools are not available for this model here.
  • Supported outputs are static PNG, JPEG and WebP. GIF, SVG, complexity, markup, animation controls and streaming return 400 documented_limitation on this endpoint.
  • size steers proportions; it does not guarantee exact pixels or 4K. Read the actual dimensions from response.size. Verified examples include 1254×1254 square, 1024×1536 portrait and 1672×941 wide images.
  • Higher requested quality values do not guarantee a higher rendered tier. In the verified neutral-prompt tests, low, medium, high, xhigh, max and auto all returned low. Transparent backgrounds can use a different tier; inspect the returned metadata and alpha channel.
  • Image output is charged by actual image-output tokens, not a fixed price per picture. The existing account discount applies to the official token rates; no separate image subscription is needed.

How to use GPT Image 2.6 Sunburst

Use gpt-image-2.6-sunburst with POST /v1/images/generations for new images or POST /v1/images/edits for reference edits at https://router.apitoken.sale/v1. Authenticate with Authorization: Bearer using the same key and prepaid balance. The default response contains PNG data in data[].b64_json. Top up your balance before sending API requests.

Frequently asked questions

What is the API model ID for GPT Image 2.6 Sunburst?

Use gpt-image-2.6-sunburst in POST /v1/images/generations. No dated alias is required.

Can I generate animated GIFs here?

No. OpenAI documents GIF and SVG output for its Image API, but this product endpoint currently supports static PNG, JPEG and WebP only. Unsupported formats return an explicit error.

Does requesting max quality or 4K guarantee that output?

No. The current channel normalizes quality and pixel requests. size controls proportion hints, and the response reports the actual quality and dimensions.

Can I edit a reference image with this model?

Yes. Send 1–16 reference images to POST /v1/images/edits with model gpt-image-2.6-sunburst, as multipart image files or as JSON images[].image_url (HTTPS URL or base64 data URL). Image input is charged at the official $8 per 1M image-input tokens before your account discount.

Run GPT Image 2.6 Sunburst on the OpenAI-compatible API at a flat 50% off — instant key, prepaid balance, card or crypto.