OpenAI · image model

GPT-Image-2.6 Flare

GPT-Image-2.6 Flare is OpenAI's latest image-generation model in our dataset, released Nov 4, 2026. Proprietary, API access only. GPT-Image-2.6 Flare costs $30 per 1M image-output tokens, $8 per 1M image-input tokens and $5 per 1M text-input tokens (OpenAI, read Nov 5, 2026). OpenAI positions it for fast iteration, so it suits quick drafts and many variations. Limits: image generations and image edits endpoints only; Batch and the Responses API are not supported. Verified against vendor sources on Nov 5, 2026.

Reported Last verified Nov 5, 2026 · All models · JSON · Markdown

Primary source: https://developers.openai.com/api/docs/changelog. We are the fast, independent index; the vendor’s own page is the source of record for these model facts.

GPT-Image-2.6 Flare at a glance: API id gpt-image-2.6-flare; takes text, image in; returns image; listed price $5 in / $30 out per 1M tokens.

ReleasedNov 4, 2026
LicenceProprietaryProprietary (API)

InTextImageOutImage

Key facts

Vendor-reported facts are read from the linked vendor page on the date shown above; we did not run the model. Independently tested means we ran it; no fact on this page is. Editorial is our own classification, not a vendor claim. Where a linked page does not itself state a value, the row says so. How to read provenance.

GPT-Image-2.6 Flare: key facts with sources
Fact	Value	Label	Source
Vendor	OpenAI	Editorial	n/a
Released	Nov 4, 2026	Vendor-reported	source
Status	generally available	Editorial	n/a
API id	gpt-image-2.6-flare	Vendor-reported	source
Input	text, image	Vendor-reported	source
Output	image	Vendor-reported	source
Licence	Proprietary (API)	Vendor-reported	source
Pricing	$5 in / $30 out per 1M tokens Prices: developers.openai.com/api/docs/models/gpt-image-2.6-flare · Checked Nov 5, 2026	Vendor-reported	source

Where GPT-Image-2.6 Flare sits in our data

Released Nov 4, 2026 (week 45 of 2026), in November 2026. Other models in our data released that month: Gemini Omni 1.2 Flash, GPT-6 Cyber, Hy4, Ripple-65B Preview.
The previous OpenAI model we track is GPT-Rosalind-6 (Oct 30, 2026), 5 days earlier.
OpenAI tools we cover: Codex CLI, ChatGPT, OpenAI Agents SDK.
All releases by date: AI model releases by month · new AI models this week.

Alternatives to GPT-Image-2.6 Flare

Image models from other vendors that share at least one of our groups with GPT-Image-2.6 Flare. Comparable on paper, from each model’s sourced facts; we have not run them.

Nano Banana 2.1Google · Both in: Image, Small and fast · 1K image $0.0336; 2K image $0.0504; 4K image $0.113 (per image) · released Oct 6, 2026
MAI-Image-2.7Microsoft · Both in: Image · released Oct 27, 2026

How GPT-Image-2.6 Flare differs from GPT-Image-2.6 Sunburst

Read from the recorded facts of the two models, not from a head-to-head test. We have not run either.

Listed price is the same as GPT-Image-2.6 Sunburst: $5 in and $30 out (per 1M tokens).
Both accept text, image as input.
Both were released on Nov 4, 2026.
Facts for the other model: GPT-Image-2.6 Sunburst.

What the sources say

These are claims from the linked pages, not our measurements.

OpenAI's model page describes it as: "Image generation and editing for fast iteration." Supported endpoints: image generations and image edits; Batch and the Responses API are listed as not supported.
Supports the new `complexity` setting (low, medium, high; high by default), markup-guided edits, SVG output and animated GIF output through the Image API, per OpenAI's image generation guide.

Notes

How it differs from GPT-Image-2.6 Sunburst: the per-token price is the same; OpenAI's model pages describe GPT-Image-2.6 Flare as "Image generation and editing for fast iteration" and Sunburst as built for detailed visual work. Launch details for both are in the Images 2.6 news brief (/news/openai-introducing-images-2-6).

What we tested

Nothing yet. We have not run GPT-Image-2.6 Flare ourselves, so every fact on this page is Reported from the sources below. When we do test it, the scope will be stated here and in our test logs. See methodology.

Not verified, left out

We could not confirm these on a vendor page, so we do not state them.

Context window and output-token limits: not stated on the model page.
Speed and quality figures are OpenAI's launch-post claims (50% faster overall; Flare as little as six seconds at low quality); we have not measured them.