GPT-Image-2.6 Flare
OpenAI's GPT Image 2.6 model for fast visual iteration, with adjustable complexity, markup-guided edits, editable SVG graphics and animated GIFs.
OpenAI's GPT Image 2.6 model for fast visual iteration, with adjustable complexity, markup-guided edits, editable SVG graphics and animated GIFs.
Plain-English overview
Flare is the GPT Image 2.6 option for interactive generation and editing. OpenAI positions it for fast iteration; compare it with Sunburst when visual detail matters more than response time.
Choose low, medium or high complexity independently of rendering quality. High is the default; lower settings can suit focused edits, while higher settings can help dense text and complex layouts.
Guide edits with a separate transparent annotation image. Generate editable SVG graphics or animated GIFs through the generation endpoint; these formats are not supported by the edit endpoint.
Category comparison
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
Pricing & comparisons
Set your usage. Your estimate updates as you type.
Example output: square 1,024 × 1,024 images. Prices depend on supported resolution and quality; edits and retries can cost extra.
GPT-Image-2.6 Flare
OpenAI
Pricing & comparisons
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Availability
Available through OpenAI's image generation and image editing endpoints.
Direct API access follows OpenAI's current supported-country and account availability rules.
Check live availabilityData and training
OpenAI says direct API inputs and outputs are not used for model training by default. Standard abuse-monitoring retention and organization-specific data controls still apply.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
OpenAI's GPT Image 2.6 model for fast visual iteration, with adjustable complexity, markup-guided edits, editable SVG graphics and animated GIFs. Flare is the GPT Image 2.6 option for interactive generation and editing. OpenAI positions it for fast iteration; compare it with Sunburst when visual detail matters more than response time.
The provider does not publish a clear release date for GPT-Image-2.6 Flare in the source material reviewed by Cody.
Available through OpenAI's image generation and image editing endpoints. The access routes listed in this guide are OpenAI.
$5 text input · $8 image input · $30 image output / 1M tokens. Rates are per million tokens. SVG adds authoring-model charges; image cost varies with token use, quality and dimensions.
Available through OpenAI's image generation and image editing endpoints. Direct API access follows OpenAI's current supported-country and account availability rules.
OpenAI says direct API inputs and outputs are not used for model training by default. Standard abuse-monitoring retention and organization-specific data controls still apply. The policy belongs to the provider route and account terms, so verify it again before production use.
Related comparisons
OpenAI's GPT Image 2.6 model for detailed compositions and edits, with adjustable complexity, markup guidance, editable SVG graphics and animated GIFs.
Open full comparisonOpenAI's speed-first GPT Image 2.5 model for everyday generation and editing, positioned at GPT Image 2-level image quality with lower latency.
Open full comparisonGoogle's versatile image workhorse for fast generation, conversational edits, multiple references, grounded imagery, and outputs up to 4K.
Open full comparisonBlack Forest Labs' production-focused image model for scalable generation and editing, precise composition, and multi-reference creative workflows.
Open full comparison