GPT Image 2.6 Flare

Model id gpt-image-2.6-flare · OpenAI · image · 2 modes: text-to-image, image-to-image.

This page reflects the current catalog. Inputs, allowed values, limits and prices can change as the model evolves; the field names and their meaning do not. For the exact schema at any time, your agent calls get_model with the mode.

Text To Image

Mode text-to-image. Text to image.

Input

Field	Type	Required	Allowed	Default	Description
`prompt`	string	Yes	up to 32,000 characters		What the image should show, or, when editing, the changes to make to the reference images.
`aspect_ratio`	string		`1:1`, `4:3`, `3:4`, `16:9`, `9:16`		Width-to-height ratio of the generated images.
`resolution`	string		`minimum`, `1K`, `2K`, `4K`		Output resolution tier. Minimum keeps the ratio at the smallest size. Defaults to 1K.
`quality`	string		`low`, `medium`, `high`	`high`	Output quality. Higher costs more per image.
`complexity`	string		`low`, `medium`, `high`	`high`	How much the model plans before rendering. Higher helps dense layouts; it does not change the price. Defaults to high.
`num_images`	integer		1 to 4		How many images to generate in one call.
`output_format`	string		`jpeg`, `png`, `webp`		File format of the generated images.

Pricing

fal’s token bill per image, by size × quality. High: 1K 2.55 (1:1) / 1.75 (4:3) / 1.25 (16:9), minimum 1.37–2.23, 2K 2.05–5.18, 4K 4.84–8.61 credits; low ≈ 0.11× and medium ≈ 0.25× of high. Default (high, no size) 1.75. Each reference image adds 0.41; prompt text adds $5/M tokens. Fixed price: charged as estimated. For the exact price of a request, use estimate_generation.

Example

The arguments of generate_media:

{
  "model": "gpt-image-2.6-flare",
  "mode": "text-to-image",
  "input": {
    "prompt": "Studio photo of a ceramic mug with steam, soft morning light",
    "aspect_ratio": "1:1",
    "resolution": "minimum"
  }
}

Image To Image

Mode image-to-image. Edit or restyle 1 to 16 images.

Input

Field	Type	Required	Allowed	Default	Description
`prompt`	string	Yes	up to 32,000 characters		What the image should show, or, when editing, the changes to make to the reference images.
`aspect_ratio`	string		`1:1`, `4:3`, `3:4`, `16:9`, `9:16`		Width-to-height ratio of the generated images.
`resolution`	string		`minimum`, `1K`, `2K`, `4K`		Output resolution tier. Minimum keeps the ratio at the smallest size. Defaults to 1K.
`quality`	string		`low`, `medium`, `high`	`high`	Output quality. Higher costs more per image.
`complexity`	string		`low`, `medium`, `high`	`high`	How much the model plans before rendering. Higher helps dense layouts; it does not change the price. Defaults to high.
`num_images`	integer		1 to 4		How many images to generate in one call.
`output_format`	string		`jpeg`, `png`, `webp`		File format of the generated images.
`references`	File list	Yes	1 to 16 items		References the output must follow. The kind of each one (image, video, audio) is read from the file; per-kind limits are in the mode’s `capabilities.references`.

References: up to 16: 16 images. Assets, URLs and elements are accepted.

Pricing

fal’s token bill per image, by size × quality. High: 1K 2.55 (1:1) / 1.75 (4:3) / 1.25 (16:9), minimum 1.37–2.23, 2K 2.05–5.18, 4K 4.84–8.61 credits; low ≈ 0.11× and medium ≈ 0.25× of high. Default (high, no size) 2.55. Each reference image adds 0.41; prompt text adds $5/M tokens. Fixed price: charged as estimated. For the exact price of a request, use estimate_generation.

Example

The arguments of generate_media:

{
  "model": "gpt-image-2.6-flare",
  "mode": "image-to-image",
  "input": {
    "prompt": "Studio photo of a ceramic mug with steam, soft morning light, keeping the look of the reference",
    "aspect_ratio": "1:1",
    "resolution": "minimum",
    "references": [
      "asset_91a3c7e5b2d84f6a8e0c1b9d7f3a5e24"
    ]
  }
}

Models

Video

Image

Audio

GPT Image 2.6 Flare

Text To Image

Input

Pricing

Example

Image To Image

Input

Pricing

Example

​Text To Image

​Input

​Pricing

​Example

​Image To Image

​Input

​Pricing

​Example

Text To Image

Input

Pricing

Example

Image To Image

Input

Pricing

Example