GPT Image 2.5 Sunburst vs Flare: Cost per Image and Which to Choose

By Joe @ SimpleMetrics
Published 10 September, 2026
Updated 28 September, 2026

Start with Flare for everyday image generation. Consider Sunburst when precise editing is your priority. That is OpenAI's positioning, not the result of our own head-to-head test. If GPT Image 2 already works for you, test your usual prompts before switching.

Conceptual cover showing a product image and a precise image-editing selection
Conceptual cover, not a comparison of model outputs.

What is different about Sunburst and Flare?

ModelOpenAI's positioningWhat to check on your own work
GPT Image 2.5 FlareFast, high-quality everyday generationDoes it produce a usable image faster?
GPT Image 2.5 SunburstCapable generation and precise editingDoes it make the requested change while preserving the rest?
GPT Image 2Earlier generation model; our existing comparison is separateIs the improvement worth changing your workflow?

The exact 2.5 model IDs are gpt-image-2.5-flare and gpt-image-2.5-sunburst. Both accept text and image inputs. Both support low, medium, high, xhigh, max, and auto quality settings.

A model described as more capable is not automatically the best choice for every image. A quick product draft and a careful edit to an approved design are different jobs.

How much does GPT Image 2.5 cost per image?

From about $0.006 at low to $0.211 at max for a 1024x1024 image. These are image output costs from the calculator in OpenAI's image generation guide, which uses the same estimate for Sunburst and Flare. They exclude prompt text, reference images and streamed partial images.

Quality1024x10241024x1536 or 1536x1024Same output tokens as GPT Image 2
low$0.006$0.005low
medium$0.013$0.010None (fewer tokens)
high$0.053$0.041medium
xhigh$0.094$0.074None
max$0.211$0.165high
Estimated image output cost per image, checked against OpenAI's calculator on September 28, 2026.

The same quality name does not mean the same cost. GPT Image 2.5 medium uses about a quarter of the output tokens of GPT Image 2 medium, and 2.5 high costs what 2 medium did. So compare images, not setting names, before deciding which setting replaces your old one. Your actual bill is the token usage returned by the API.

Both 2.5 models list these standard API token rates in US dollars, the same as GPT Image 2:

Billed itemPrice per million tokens
Text input$5
Image input$8
Image output$30

Cached input has separate discounted rates. Do not carry over the old GPT Image 2 "$0.053 per medium image" figure to 2.5 medium; the guide's calculator now has a separate GPT Image 2.5 option. These API charges are also different from ChatGPT subscription allowances.

What can a generated product image look like?

Generated AURORA sparkling water can with readable label text, lemon slices and droplets on wet black stone
Illustrative example generated September 10 using our image tool configured for GPT Image 2.5 Flare. Automatic size and quality; the tool revised the submitted prompt. This is not a controlled comparison, and no per-image API cost or speed measurement is claimed.

Submitted prompt: Create a studio-quality product photo of a premium sparkling water can called "AURORA" on a wet black stone surface with lemon slices and soft rim lighting. The can label should clearly read "AURORA", "Sparkling Water", and "Lemon". Photorealistic, commercial ad style, high detail.

The requested label text is readable in this example. One successful image does not establish how consistently the model follows prompts or how it compares with Sunburst or Image 2.

How can you compare it with GPT Image 2?

Use the same prompt, output size and requested quality for each model. Our existing GPT Image 2 comparison includes three prompts you can reuse:

  1. A sparkling-water product photo with readable label text.
  2. A Kyoto travel advertisement with a headline, price and booking text.
  3. A water-cycle infographic with four labels and arrows.

Check the finished images, time each request, and use returned token usage to calculate the cost. We have not run this matched three-model benchmark; the older Image 2 images are not Image 2.5 results.

Should you switch now?

For now, use the official positioning as a shortlist, not a guarantee. Try Flare for a generation-heavy workflow and evaluate Sunburst separately for editing. Keep GPT Image 2 if it already meets your needs until a matched test shows a useful improvement.

For an upgrade decision, ask three simple questions: Is the result usable? How long did it take? What did that usable result cost, including retries?

Sources

Found this useful? Share it!

If this helped you, I'd appreciate you sharing it with colleagues.

Was this page helpful?

Your feedback helps improve this content.

Related Posts