GPT Image 2.6 Flare

Not yet independently verified. Not yet independently verified. Release date, prices and capabilities rest on OpenAI's own changelog and model page; we found no dated independent report or test yet. We will update this when it can be confirmed, and remove this note.

GPT Image 2.6 Flare is the faster of the two image models OpenAI released on 4 November 2026. OpenAI describes it as the model for interactive generation and editing, where a person tries a prompt, looks, and tries again, while its sibling GPT Image 2.6 Sunburst is meant for detailed compositions.

Same features, a different balance

Flare carries the same 2.6 additions as Sunburst: an adjustable complexity setting, markup-guided edits on a marked region of an image, SVG vector output and animated GIF output. OpenAI does not publish latency figures for either model, so the difference between them is stated only as purpose, not as measured speed.

Prices are identical to Sunburst

The model page lists the same per-token prices as Sunburst: text input at $5 per million tokens ($1.25 cached), image input at $8 per million ($2 cached) and image output at $30 per million. Because the price is per token rather than per image, the cost of a picture depends on its size and the complexity setting, so the price table alone does not say which of the two is cheaper for a given job. Both run only on the Images API generation and edit endpoints.

Key facts

Developer: OpenAI Released: 4 November 2026 Model ID: gpt-image-2.6-flare Input: text, image Output: image (including SVG and animated GIF) Endpoints: images/generations, images/edits Price: $5 per million text input tokens, $8 per million image input tokens, $30 per million image output tokens