New
GPT Image 2.5 FlareAI image generator
OpenAI's newest image model, the fast variant: sharp text and layouts from a prompt. On Leap, it sits beside 169 other models in one studio.
- Text to image
- 3 aspect ratios
- Start free, no card
- Every top model, one account
- Pay per run, priced before it starts
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.
- Made by
- OpenAI
- Makes
- Images
- Starts from
- Words
- Shapes
- 1:1, 3:2, 2:3
- Per run
- Up to 4 images
- Prompt
- Up to 2,000 characters
- Price per run
- $0.056276 to $0.068948
- On Leap since
- October 4, 2026
- Updated
- October 4, 2026
- 01Describe what you want to see
- 02See the exact price, then press go
- 03Keep it in your library, or take it further
Pick the right one
GPT Image 2.5 Flare and its siblings
| Model | Best for | Price per run |
|---|---|---|
| GPT Image 2.5 Flare (this page) | OpenAI's newest image model, the fast variant: sharp text and layouts from a prompt. | $0.056276 to $0.068948 |
| GPT Image 2 | OpenAI's image model: precise prompt following and text, at medium quality. | $0.056276 to $0.068948 |
| GPT Image 2.5 Sunburst | OpenAI's newest image model, the precise editor: restages your product or photo and keeps its label and text. | $0.112596 to $0.125268 |
| GPT Image 1.5 | The GPT Image before 2: strong at text and layout, at medium quality. | $0.064152 to $0.081752 |
Start with an idea
Three ways to try GPT Image 2.5 Flare
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. OpenAI's newest image model, the fast variant: sharp text and layouts from a prompt. It is new on Leap and in preview: it works, and it may still change. On Leap it runs in one studio beside every other top model, with one account.
- What resolution and sizes does it make?
- 1:1, 3:2 or 2:3.
- How is it different from GPT Image 2, GPT Image 2.5 Sunburst and GPT Image 1.5?
- GPT Image 2.5 Flare: OpenAI's newest image model, the fast variant: sharp text and layouts from a prompt. GPT Image 2: OpenAI's image model: precise prompt following and text, at medium quality. GPT Image 2.5 Sunburst: OpenAI's newest image model, the precise editor: restages your product or photo and keeps its label and text. GPT Image 1.5: The GPT Image before 2: strong at text and layout, at medium quality. They all run in the same studio, so you can try one prompt on each.
- How much does a run cost?
- A 1:1 image costs $0.068948 at the default settings. By shape, a run costs $0.056276 to $0.068948. 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?
- Yes. Sign up with a Gmail, Outlook or work address and you start with $2 of free credit, no card needed. The cheapest run is $0.056276 (a 3:2 image), so the credit covers 35 of those. After that 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.
Start free, no card. Every run shows its price before it starts.
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.
Promptprompt
Text, up to 2,000 characters, required
Aspect ratioaspect_ratio
1:1, 3:2, 2:3. Default: 1:1
Imagesn
1 to 4. Default: 1
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"