GPT Image 2.5 FlareAI image generator
The quicker GPT Image 2.5: quality up to max, 4K, and up to 8 references. On Leap, it sits beside 172 other models in one studio.
- Text to image
- Image edit
- 8 aspect ratios
- No subscription
- Every top model, one account
- Pay per run, priced before it starts
First $5 top-up, no card fee.

AI image generator
GPT Image 2.5 Flare at a glance
GPT Image 2.5 Flare is an image model from OpenAI. It makes images from words or up to 8 photos, at up to 4K.
- Made by
- OpenAI
- Makes
- Images
- Starts from
- Words or up to 8 photos
- Resolution
- 1K, 2K or 4K
- Shapes
- 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9
- Per run
- Up to 4 images
- Prompt
- Up to 32,000 characters
- Price per run
- $0.087 to $0.65
- On Leap since
- October 4, 2026
- Updated
- October 6, 2026
- 01Describe it, or start from a photo
- 02See the exact price, then press go
- 03Keep it in your library, or take it further
Made on Leap
More from GPT Image 2.5 Flare

A hand-painted shop sign that reads OPEN LATE above a tiny ramen bar on a rainy night, warm light spilling onto wet cobblestones, cinematic 35mm photo
Pick the right one
GPT Image 2.5 Flare and its siblings
| Model | Best for | Resolution | Price per run |
|---|---|---|---|
| GPT Image 2.5 Flare (this page) | The quicker GPT Image 2.5: quality up to max, 4K, and up to 8 references. | Up to 4K | $0.087 to $0.65 |
| GPT Image 2 | OpenAI's image model: precise prompt following and text, at medium quality. | – | $0.07 to $0.085 |
| GPT Image 1.5 | The GPT Image before 2: strong at text and layout, at medium quality. | – | $0.079 to $0.105 |
| GPT Image 2.5 Sunburst | OpenAI's newest image model, built for precise edits: quality up to max, 4K, and up to 8 references. | Up to 4K | $0.087 to $0.65 |
Side by side
More image models on Leap
No prompt needed
Or start from a recipe
Recipes write the prompt for you: add a photo, pick a look, and get a finished result.
Questions
GPT Image 2.5 Flare, answered
- What is GPT Image 2.5 Flare?
- GPT Image 2.5 Flare is an image model from OpenAI. The quicker GPT Image 2.5: quality up to max, 4K, and up to 8 references. On Leap it runs in one studio beside every other top model, with one account.
- Can GPT Image 2.5 Flare start from a photo?
- Yes. GPT Image 2.5 Flare starts from words or up to 8 photos.
- What resolution and sizes does it make?
- Up to 4K, in 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16 or 21:9.
- How is it different from GPT Image 2, GPT Image 1.5 and GPT Image 2.5 Sunburst?
- GPT Image 2.5 Flare: The quicker GPT Image 2.5: quality up to max, 4K, and up to 8 references. GPT Image 2: OpenAI's image model: precise prompt following and text, at medium quality. GPT Image 1.5: The GPT Image before 2: strong at text and layout, at medium quality. GPT Image 2.5 Sunburst: OpenAI's newest image model, built for precise edits: quality up to max, 4K, and up to 8 references. They all run in the same studio, so you can try one prompt on each.
- How much does a run cost?
- An image costs $0.11 at the default settings. By quality, a run costs $0.087 to $0.65. You see the exact price before you press go, and a run that fails costs nothing.
- Is GPT Image 2.5 Flare free to try?
- No. There is no free credit: you add credit from $5, and your first top-up has no card fee. The cheapest run is $0.087 (an image), so $5 covers 57 of those. You pay per run, in dollars, with no subscription.
- Can I use what I make commercially?
- Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
- Is there an API?
- Yes. Leap's REST API runs it as openai/gpt-image-2.5-flare, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
- Do I need an OpenAI account?
- No. Leap sends your request to OpenAI's model and gives you what it makes. One Leap account runs GPT Image 2.5 Flare and every other model, in the studio, through the API and from your agents.
Your idea, GPT Image 2.5 Flare.
Every run shows its price before it starts, and one that fails costs nothing.
Make it with GPT Image 2.5 FlareFor developers
Run GPT Image 2.5 Flare from code
- Model ID
- openai/gpt-image-2.5-flare
- Makes
- Image
- Pricing
- Per run, quoted first: POST /v1/quotes
Inputs
What the model takes. Leave out anything with a default.
The request
The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.
curl https://api.tryleap.ai/v1/generations \ -H "x-api-key: $LEAP_API_KEY" \ -H "content-type: application/json" \ -H "prefer: wait=60" \ -d '{ "model": "openai/gpt-image-2.5-flare", "input": { "prompt": "A paper boat drifting down a rainy street at dusk" } }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"






