Playbooks · Coding
GPT-Image-2.6: Flare or Sunburst?
Written November 10, 2026
OpenAI's Images 2.6 ships two API models at the same token rates: Flare for speed, Sunburst for detail. Pick by the job, not by the name.
The problem
A builder calling the image API now has two model names where there was one choice to make, and the names do not say which job each one fits. Flare is the fast one, Sunburst is the careful one, and the price per token is the same for both — so the choice is about time against detail, not about cost per token.
What OpenAI says each one is for
OpenAI's November 4 announcement puts it plainly: Flare generates images in as little as six seconds when quality is set to low, and also improves layout quality for posters, product imagery, and other professional visuals. Sunburst brings higher-quality generation and greater consistency across edits when quality is set to medium or high. Images 2.6 as a whole generates images 50% faster than before, by OpenAI's own measure. Both variants are available in the API, alongside GIF creation, SVG export, image markup, and a new complexity parameter that controls how much planning the model does before it renders.
The rule that follows from that is simple. Use Flare when you will throw half the outputs away: drafts, social graphics, poster concepts, product variations, quick edit rounds. Use Sunburst when the output has to hold up on close inspection or stay consistent across a series of edits: brand assets, product shots that must match across a campaign, character sheets, scenes with many constraints.
What independent tests measured
Artificial Analysis ran both variants through its blind text-to-image and editing leaderboards, and the two models took the top two positions on both. Sunburst ranked first in seven of the ten text-to-image use cases tracked, and Flare ranked first in the consumer and marketing categories. The speed gap in those tests is large: Flare's median text-to-image latency was about 30 seconds, with edits at about 32 seconds, against Sunburst at about 135 seconds per image and about 120 seconds per edit.
| Variant | Text-to-image latency | Edit latency | Best for |
|---|---|---|---|
| Flare | About 30 seconds | About 32 seconds | Drafts, iteration, batch generation |
| Sunburst | About 135 seconds | About 120 seconds | Detail, typography, identity-preserving edits |
Both variants share one token rate card: $5 per million text input tokens, $8 per million image input tokens, and $30 per million image output tokens. At maximum quality, Artificial Analysis calculates about $0.21 for a 1024 by 1024 image, or about $211 per thousand images. The per-image cost is the same for both variants at the same settings; Sunburst costs more in wall-clock time, not in tokens.
How to call them
Set the model explicitly in the API call: gpt-image-2.6-flare or gpt-image-2.6-sunburst. There is no variant selector in ChatGPT itself, so an API call that names neither gets whatever the default is, not the variant you meant. Both variants take the same parameters, including the complexity setting: low complexity for quick edits, medium or high for scenes with many elements or constraints. Both default to high complexity, which is easy to miss and adds latency to a call that did not need it.
Limits
- No image was generated for this page, and neither variant was run here. The comparison rests on OpenAI's stated trade-offs and on Artificial Analysis' independent measurements, not on a run of ours.
- OpenAI's 50% faster claim is the vendor's own figure, measured against its previous generation, with no published baseline, workload, or method.
- The latency figures are Artificial Analysis medians from its leaderboard tests, not a promise for any single prompt: a crowded scene at high quality will take longer than a simple one at low quality.
- The token rates above are as listed on the models' pages and reported by independent checks; OpenAI's announcement links to pricing without printing the numbers.
Related playbooks
- GPT Image 2 shuts down Feb 10, 2027
- GPT-5 snapshots and o3 shut down Dec 11
- GPT-5.5-Cyber preview ends February 1, 2027
- GPT-6 Cyber: OpenAI's restricted security model
Sources
- Introducing Images 2.6 — OpenAI
- AA-Image-T2I v2.1 Leaderboard — Artificial Analysis
- GPT Image 2.6: GIFs, Flare vs Sunburst, API Changes — aireiter
Back to: Coding playbooks hub · Also: Hermes Agent 0.23.0: paid MCP spend limits