Skip to main content
GPT Image 2.5 Flare and Sunburst are available in LaoZhang API official-forward groups, using the existing GPT Image 2 official-forward integration and the same token rates. Default continues to use gpt-image-2-web, which now runs the latest GPT web version, 2.5. Two VIP per-call models are also available: gpt-image-2.5-flare-vip and gpt-image-2.5-sunburst-vip, each at $0.03/call, using the same integration as gpt-image-2-vip.
  • Published: September 9, 2026
  • Last checked: September 9, 2026
  • Status: Active; available

​
Choose a model and route

Both Flare and Sunburst can generate and edit images. Choose Flare for speed, Sunburst for edit precision, or offer both in your app. For production calls that prioritize stability, choose the enterprise official-forward group (called image2Enterprise in the launch notice; the public catalog key is GPT_Image_2_Enterprise, displayed as GPTImage2 Sora2 Enterprise). The regular official-forward group is Sora2Official, with catalog key sora_official.

​
What users should do

  • Existing GPT Image 2 official-forward integrations: confirm that your token permits the target model, keep the Images API endpoint and authentication, and change model to begin testing. Use POST /v1/images/generations for generation and POST /v1/images/edits for editing.
  • Existing VIP integrations: keep the per-call token, endpoint, and request structure used for gpt-image-2-vip, then change model to gpt-image-2.5-flare-vip or gpt-image-2.5-sunburst-vip.
  • Default web-route integrations: keep model="gpt-image-2-web"; switching to Flare / Sunburst is unnecessary for this web update.
  • Other existing routes: this notice does not require a universal migration. To adopt 2.5 official forwarding, verify the model, group, and usage-based billing settings.
Copy generation, editing, and image-saving examples from the GPT Image 2.5 integration guide. Launch notices and model listings cannot replace real-request acceptance. Before increasing traffic, open the returned image and check usage and charges in call logs. Representative generation parameters for both VIP models were tested on September 9, 2026. See the integration guide for verified sizes; these tests do not validate editing or official-forward parameters.

​
Frequently asked questions

​
Do matching GPT Image 2 rates mean the same cost per image?

No. The official-forward token rates match, but models, quality, dimensions, and reference images can change consumption and the total price. See the billing guidance and current console pricing; contact support for enterprise quotes.

​
Can Default directly call Flare or Sunburst?

Unsuffixed Flare / Sunburst require a usage-billed token in an official-forward group. Default can use gpt-image-2.5-flare-vip and gpt-image-2.5-sunburst-vip at $0.03/call each. Its web entry remains gpt-image-2-web.

​
Which size and quality values should VIP requests use?

For VIP generation, use low, medium, or high; xhigh / max are currently unsupported. Both models were verified with size="2048x2048" and quality="medium", making this a shared starter request. Omit a field when you do not need to specify it. See the VIP generation parameters for verified sizes and examples.

​
Can I pin a model version?

For official forwarding, set model to a full dated snapshot ID from the table. The notice does not map gpt-image-2-web to an official-forward snapshot, so do not assume it is identical to Flare or Sunburst.