← Back to Payloads
AI News2026-09-08

OpenAI Shipped GPT Image 2.5 Sunburst and Flare. Six Quality Settings, Inpainting, and a Real Responses API Tool Path for Image Agents.

OpenAI published GPT Image 2.5 Sunburst and Flare on the Sep 8 changelog with snapshot 2026-09-08, xhigh and max quality tiers, inpainting as a first-class feature, and a real Responses API tool path for multi-turn image editing. The integration is the story — the model names are the wrapper. Pricing published on the model pages but not yet in the public pricing table; the GPT Image 2 calculator does not estimate 2.5 consumption.
Quick Access
Install command
$ mrt install openai
Browse related skills

OpenAI Shipped GPT Image 2.5 Sunburst and Flare. Six Quality Settings, Inpainting, and a Real Responses API Tool Path for Image Agents.

Hey guys, Mr. Technology here.

The OpenAI changelog dated September 8, 2026 published two new image generation models, GPT Image 2.5 Sunburst (gpt-image-2.5-sunburst) and GPT Image 2.5 Flare (gpt-image-2.5-flare), with the snapshot dated 2026-09-08. Both are available through the Image API and as the model field of the Responses API image generation tool. Both add xhigh and max to the quality-setting list, support inpainting as a first-class feature, and ship with a new image-token pricing surface that did not exist before today. This is a documentation comparison — I read the changelog, both model pages, the image generation guide, and the pricing page. I have not run the models.

If you build image agents on the Responses API, this changes your routing math. If you build coding agents, you can skip the article.

What Shipped

From the OpenAI changelog, dated September 8, 2026 (verified verbatim 2026-09-08 20:08 UTC):

"Released GPT Image 2.5 Sunburst and GPT Image 2.5 Flare for image generation and editing through the Image API and the Responses API image generation tool. Use Sunburst for workflows where editing precision matters most, or Flare for fast, high-quality everyday image generation. Both models support the new xhigh and max quality settings and use GPT Image 2 token rates."

Two distinct model roles, one shared API surface.

  • Sunburst — "Our most capable model for image generation and editing" (per the model page). Use it when editing precision is the primary requirement.
  • Flare — "Fast, high-quality everyday image generation" (per the model page). Use it when throughput matters and the task is routine.

Both models accept text and image inputs, output image, and use the same snapshot date 2026-09-08. The supported endpoints are listed as v1/images/generations and v1/images/edits only. Chat Completions, Responses, Realtime, Batch, Fine-tuning, and Embeddings are explicitly "Not supported" for both models. The v1/images/* routes are the only callable paths.

This is a hard boundary. If your existing agent stack calls image generation through Responses or Chat Completions, you do not call either model directly — you select a supported mainline model at the top level and pass gpt-image-2.5-sunburst or gpt-image-2.5-flare inside the image generation tool's model field. The guide states this explicitly: "With the Responses API, select a supported mainline model at the top level and specify gpt-image-2.5-sunburst or gpt-image-2.5-flare in the image generation tool's model field."

What Actually Changed For Builders

Three concrete changes:

1. The quality-setting ladder widened. The supported quality enum on both models is low, medium, high, xhigh, max, auto. The two new top-of-ladder values are xhigh and max. They replace whatever the previous tier ceiling was — both model pages state the same six-value list, with auto as the default behavior. The OpenAI changelog phrasing is "new xhigh and max quality settings," which is the cleanest statement of capability delta.

2. Inpainting is now a first-class supported feature. Both model pages list inpainting under "Supported features." Inpainting lets you edit a specific region of an input image while preserving the rest. The v1/images/edits endpoint is the route. Previously, inpainting-style workflows required prompt-only edits through the legacy edits endpoint; the model pages now advertise it as supported.

3. The Responses API tool got a real multi-turn editing path. The image generation guide says the Responses API "supports image generation as a built-in tool, and accepts image inputs and outputs within context." Compared to the Image API, it adds two things: multi-turn editing ("Iteratively make high fidelity edits to images with prompting") and flexible inputs ("Accept image File IDs as input images, not just bytes"). For an agent that needs to show a generated image, accept user edits as text, and continue editing across turns, the Responses API tool path is the only documented mechanism that holds the image across turns without re-uploading bytes.

Why Developers And Founders Should Care

The Responses API integration is the part that matters for agent builders, not the new model names. An agent that wants to produce marketing visuals, product mockups, presentation assets, or design iterations can now:

1. Call the Responses API image generation tool with gpt-image-2.5-flare for a first pass (cheap, fast); 2. Receive the generated image as a File ID in the conversation; 3. Have the model iterate ("make the background dark blue, keep the foreground subject") with the File ID as input; 4. Switch to gpt-image-2.5-sunburst for the final pass at xhigh or max quality.

This is the agent-native image workflow. The guide calls out the two-API split explicitly: "If you only need to generate or edit a single image from one prompt, the Image API is your best choice. If you want to build conversational, editable image experiences with GPT Image, go with the Responses API."

The pricing also matters for routing math. Both models share an identical pricing surface:

MetricPriceUnit
Text input$51M tokens
Cached text input$1.251M tokens
Image input$81M tokens
Cached image input$21M tokens
Image output$301M tokens

Both model pages state: "Image output costs $30 per million tokens. Text output is not billed because this model outputs images, not text. Token rates match GPT Image 2. The GPT Image 2 calculator does not estimate GPT Image 2.5 token consumption." The last sentence is the practical caveat — there is no working calculator for these models today. Treat token cost estimates as approximate until OpenAI ships a 2.5-specific calculator or a third-party tool catches up.

Evidence And Test Results

Primary sources verified at 2026-09-08 20:08 UTC:

  • OpenAI changelog Sep 8, 2026 entry: <https://developers.openai.com/api/docs/changelog>
  • GPT Image 2.5 Sunburst model page (snapshot gpt-image-2.5-sunburst-2026-09-08, supported features include inpainting): <https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst>
  • GPT Image 2.5 Flare model page (snapshot gpt-image-2.5-flare-2026-09-08, supported features include inpainting): <https://developers.openai.com/api/docs/models/gpt-image-2.5-flare>
  • Image generation guide (Image API vs Responses API split, File ID inputs, multi-turn editing): <https://developers.openai.com/api/docs/guides/image-generation>
  • OpenAI pricing page: <https://developers.openai.com/api/docs/pricing>

No first-hand test was run. The article is a documentation comparison, not a benchmark or field report.

Cost, Risk, And Limitations

Cost. The pricing page does not yet list gpt-image-2.5-sunburst or gpt-image-2.5-flare in the Standard / Batch / Flex / Fast tables at the time of fetch (2026-09-08 20:08 UTC). The model pages publish a token rate, but the public pricing page only references "GPT Image 2 token rates" without surfacing the 2.5 models in the visible table. If your billing automation keys off the pricing table rows, the new models may not appear until a subsequent page update. Plan for an offline token-rate estimate using the model-page numbers until the pricing page catches up.

Risk. The image generation guide adds a guardrail: "To ensure these models are used responsibly, you may need to complete the API Organization Verification from your developer console before using GPT Image models." Unverified orgs may be blocked or rate-limited at request time. Verify before you ship to production.

Limitations.

  • No batch tier, fast tier, or flex tier rows for the 2.5 models visible in the public pricing table at the time of writing. Cost figures above are the model-page token rates, not the live tiered pricing.
  • Both model pages list only v1/images/generations and v1/images/edits as supported endpoints. There is no v1/responses direct call path; the Responses API integration is tool-mediated.
  • The "GPT Image 2 calculator" does not estimate GPT Image 2.5 token consumption per the model pages. Existing cost calculators will under- or over-estimate.
  • Inpainting is supported but no documented resolution ceiling or region-size limit was visible on either model page at fetch time. Treat any region-size claims as untested.

Mr. Technology Verdict

OpenAI shipped two new flagship image generation models with a real Responses API tool integration. The integration is the story — the model names are the wrapper. For builders running image agents on the Responses API, Sunburst and Flare replace whatever image model you were using before today with a wider quality ladder (xhigh, max), explicit inpainting support, and a documented multi-turn editing path. For builders running coding agents, this is a no-op.

The pricing surface is real but immature — token rates exist on the model pages, the public pricing table does not yet surface the 2.5 models in tier rows, and the legacy GPT Image 2 calculator does not estimate 2.5 consumption. Plan for a brief cost-estimation gap.

Recommended Action

Today

  • If you build image-generation agents on the Responses API: pull both model pages (/api/docs/models/gpt-image-2.5-sunburst, /api/docs/models/gpt-image-2.5-flare) into your model registry and add the new quality enum values (xhigh, max) to any quality-selection UI.
  • If your org is not yet API-Organization-Verified, complete verification before routing production traffic. The guide makes this a precondition for GPT Image models.

This week

  • A/B test Sunburst vs your previous editing model on a representative editing task — measure both quality (subjective) and per-image token cost against the model-page rates.
  • A/B test Flare on high-volume, low-risk image generation traffic — measure latency and per-image token cost against the model-page rates.
  • Track the OpenAI pricing page for the day gpt-image-2.5-sunburst and gpt-image-2.5-flare rows appear in Standard / Batch / Fast tier tables. Until then, use the model-page token rates and label your cost estimates as approximate.

Skip if not in scope

  • Coding agents, text-only agents, and embedding/RAG agents — this release does not affect you.
  • Anyone waiting on a working 2.5 cost calculator. The published guidance is "the GPT Image 2 calculator does not estimate GPT Image 2.5 token consumption." Use the model-page rates directly.

Sources

Related Dispatches