promptstringrequired
The text prompt to generate an image from.
Default: "Generate an image of gray tabby cat hugging an otter with an orange scarf"
openai/gpt-image-2.5-flareGPT Image 2.5 Flare is optimized for fast, high-quality image generation for everyday creative workflows.
Try the model
Customize your input with more control.
Select an example to load its inputs and result into the playground.
{
"aspect_ratio": "16:9",
"prompt": "Create a photorealistic candid photograph of an elderly sailor standing on a small fishing boat.\nHe has weathered skin with visible wrinkles, pores, and sun texture, and a few faded traditional sailor tattoos on his arms.\nHe is calmly adjusting a net while his dog sits nearby on the deck. Shot like a 35mm film photograph, medium close-up at eye level, using a 50mm lens.\nSoft coastal daylight, shallow depth of field, subtle film grain, natural color balance.\nThe image should feel honest and unposed, with real skin texture, worn materials, and everyday detail. No glamorization, no heavy retouching."
}{
"aspect_ratio": "16:9",
"prompt": "Create a detailed Infographic of the functioning and flow of an automatic coffee machine like a Jura.\nFrom bean basket, to grinding, to scale, water tank, boiler, etc.\nI'd like to understand technically and visually the flow."
}{
"aspect_ratio": "16:9",
"prompt": "Give me a cool in culture ad / fashion shot for a brand called Thread.\nIt's a hip young street brand. The ad shows a group of friends hanging out together with the tagline \"Yours to Create.\"\nMake it feel like a polished campaign image for a youth streetwear audience: stylish, contemporary, energetic, and tasteful.\nUse clean composition, strong color direction, natural poses, and premium fashion photography cues.\nRender the tagline exactly once, clearly and legibly, integrated into the ad layout.\nNo extra text, no watermarks, no unrelated logos."
}{
"aspect_ratio": "4:3",
"output_format": "webp",
"prompt": "Original editorial pixel illustration with sculptural depth. Finished opaque rectangular 4:3 landscape model cover: paint the entire background, with no transparency, cutout mask, or chroma-key fringes. Bold, carefully composed silhouettes; stepped pixel edges; broad planes of flat color; selective ordered dithering in shadows and tonal transitions. A contemporary art print drawn on a visible, consistent pixel grid, with dimensional form but no photographic surfaces. One clear visual idea, a single prominent main subject, and enough breathing room to read its silhouette. Keep the important action within the central 70 percent so crops remain legible. No text, letters, numbers, logos, watermark, UI, border, photorealism, glossy 3D, blur, or glow.\n\nSubject: one large tortoise in high three-quarter view, head lifted, one front foot planted forward, filling roughly 60 percent of the frame and reading instantly at thumbnail size. Every scute of its high domed carapace is a separate, differently patterned stepped plate drawn at one identical plate size, one identical cream rim highlight and one identical stepped pixel edge: cobalt blue with pale-blue speckle, solid coral red, coral red with cream barring, cream with fine ink ticks, and pale blue with mustard flecks — about ten in all — seated flush together into one continuous unbroken dome. The marginal scutes run around the shell rim at the same pitch, and the plastron edge below them stays plain ink-navy. Head, neck, legs and tail are plain ink-navy with crisp cream rim light, so each patterned plate reads as one supplied reference seated into the single shell.\n\nVisible action: one clean stepped rectangle of a new, wider, shallower proportion is marked in deep ink on the ground beneath the tortoise, and the whole silhouette has just re-seated flush inside that newly chosen frame — the four feet planted exactly along its inner edge, the shell dome just clearing its top edge — so the animal is unmistakably the same creature placed onto a new canvas rather than a copy of its old one.\n\nComposition: single compact focal grouping, the tortoise centred and slightly low in the frame, the ink rectangle directly beneath it and no wider than the middle two-thirds of the picture, generous flat ochre space above and to the sides.\n\nPalette roles: flat warm ochre-mustard (about #d9a430) as the single background field; ink-navy (about #131022) for all line work, shadow cores and the unpatterned body; cobalt blue (about #2c58d8) as the largest subject hue across several scutes and the head shadow; coral red (about #e2543a) as the second strong subject hue on the remaining scutes and the foot highlights; cream (about #f2ecdc) for every rim highlight, plate outline and fine speckle. Distinct dark and light values throughout, saturated and harmonious. No purple, plum or violet anywhere, including the ground; no greyed or muddy mixes; no dim lighting.\n\nTexture treatment: irregular dithering across the background field, especially where it is otherwise clean — uneven clusters of pixel stipple, broken halftone patches and occasional tiny displaced fragments, denser near the ink rectangle marking and in the tortoise's cast shadow, quieter in the open spaces, built mostly from nearby ochre, terracotta and cream tones with a few cobalt or coral accent pixels. Let some stipple touch the shell's shadow side and the carapace edges without breaking the silhouette or the plate pattern. Keep it a surface treatment only: no uniform full-frame noise, no large glitch bands, no obligatory neon color splitting, no zooming out, no shrunk subject, no added scenery and no second focal point.\n\nExclude: tools, machines, workshop scenes, human body parts, and snakes, serpents, eels, worms, caterpillars, centipedes, millipedes, leeches or slugs anywhere in the image.",
"quality": "high"
}Human preference
Elo ratings from blind side-by-side votes, compared with other image and video models.
Rankings sourced from Artificial Analysis Arena
Text-to-image arena: people pick the better of two images generated from the same prompt, without seeing the model names.
GPT Image 2.5 Flare is the fast GPT Image 2.5 tier for everyday creative work, with the same quality levels and 1K to 4K output as Sunburst.
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 50,000 characters. |
quality | low / medium / high / xhigh / max | high | Higher quality costs more; high is the default. |
resolution | 1k / 2k / 4k | — | Output size tier; omit for 1K. |
aspect_ratio | 1:1 / 1:2 / 2:1 / 1:3 / 3:1 / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 9:21 / 21:9 | 1:1 | Output frame shape. |
output_format | jpeg / png / webp | png | Output file format. |
Price depends on quality and resolution, per image:
| Quality | 1k | 2k | 4k |
|---|---|---|---|
| low | $0.01 | $0.02 | $0.03 |
| medium | $0.024 | $0.04 | $0.07 |
| high (default) | $0.09 | $0.15 | $0.27 |
| xhigh | $0.16 | $0.27 | $0.48 |
| max | $0.36 | $0.60 | $1.00 |
Failed runs are not charged.
low or medium, then rerun at high.Other GPT Image endpoints: openai/gpt-image-2.5-sunburst, openai/gpt-image-2.5-sunburst/edit, openai/gpt-image-2.5-flare/edit, openai/gpt-image-2, openai/gpt-image-2/edit.
Start building
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "openai/gpt-image-2.5-flare",
"prompt": "Generate an image of gray tabby cat hugging an otter with an orange scarf",
"quality": "high",
"aspect_ratio": "1:1",
"output_format": "png"
}
SANDBASE_JSON
)
printf '%s\n' "$result"Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
promptstringrequiredThe text prompt to generate an image from.
Default: "Generate an image of gray tabby cat hugging an otter with an orange scarf"
qualitystringRendering quality. `xhigh` and `max` add detail at higher latency and cost.
Default: "high"
Possible values: "low", "medium", "high", "xhigh", "max"
resolutionstringThe resolution of the generated image. Leave unset to preserve the provider's standard dimensions.
Possible values: "1k", "2k", "4k"
aspect_ratiostringThe aspect ratio of the generated image.
Default: "1:1"
Possible values: "1:1", "1:2", "2:1", "1:3", "3:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "9:21", "21:9"
output_formatstringThe format of the generated image.
Default: "png"
Possible values: "jpeg", "png", "webp"
{
"model": "openai/gpt-image-2.5-flare",
"prompt": "Generate an image of gray tabby cat hugging an otter with an orange scarf",
"quality": "high",
"aspect_ratio": "1:1",
"output_format": "png"
}A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"source": "OpenAI Cookbook prompt (MIT)",
"source_url": "https://developers.openai.com/cookbook/examples/multimodal/image-gen-models-prompting-guide",
"url": "https://static.sandbase.ai/examples/2f24d1cd-084b-4de4-a62d-48feec7bc289/output/6eaea130-4f71-47ae-8631-d74772f2b750.png"
}
]