Start free

Leap API

GPT Image 2.5 APIOpenAI's model, through Leap

OpenAI's newest image model, built for precise edits: quality up to max, 4K, and up to 8 references. One Leap key and one balance run it and every other model, priced per call in dollars.

Get an API keyRead the quickstart
  • One key for every model
  • Every call quoted first
  • A failed call costs nothing
curl https://api.tryleap.ai/v1/generations \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: application/json" \  -H "prefer: wait=60" \  -d '{    "model": "openai/gpt-image-2.5-sunburst",    "input": {      "prompt": "A silk scarf in the wind on a ferry deck",      "aspect_ratio": "1:1",      "settings": {        "quality": "medium"      }    }  }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"

Set LEAP_API_KEY and send it. With prefer: wait=60 the answer holds the result when the call finishes within a minute; a longer one is read again by its ID.

Model ID
openai/gpt-image-2.5-sunburst
Price per call
$0.0704 to $0.5269
This call
An image costs $0.0858.
Free to start
The $2 welcome credit covers 23 calls like it.

What it makes

Made with GPT Image 2.5 Sunburst

Real GPT Image 2.5 Sunburst runs on Leap. Each one passed Leap's media quality check before it was shown.

More on the GPT Image 2.5 Sunburst page
  • Marcus, sky pirate captain, a real run on Leap

    Marcus, sky pirate captain

  • A ride along the coast, anime film, a real run on Leap

    A ride along the coast, anime film

  • A snake through a skull, with peonies, a real run on Leap

    A snake through a skull, with peonies

  • Tomas, a swordsman under the cherry tree, a real run on Leap

    Tomas, a swordsman under the cherry tree

  • A mechanic and her giant robot, a real run on Leap

    A mechanic and her giant robot

  • A tiger in bamboo and clouds, Japanese back piece, a real run on Leap

    A tiger in bamboo and clouds, Japanese back piece

The answer

What comes back

A generation. Check status first: succeeded has the file in output, a signed link that works for 24 hours, so download what you keep. failed has error and failure_cause, and costs nothing. usage.cost_usd is what the call was charged.

200 OK, trimmed
{  "id": "gen_...",  "object": "generation",  "model": "openai/gpt-image-2.5-sunburst",  "status": "succeeded",  "output": [    {      "type": "image",      "url": "https://api.tryleap.ai/files/..."    }  ],  "error": null,  "usage": {    "cost_usd": "0.0858"  }}

Your own photo

Start from an image

Upload the image to POST /v1/files and pass the ID it returns in images. Inputs take file IDs, not URLs. Files and uploads covers video and sound.

curl, with jq
# Upload the photo (PNG, JPEG or WebP, up to 4 MB) and keep its ID.FILE_ID=$(curl -s "https://api.tryleap.ai/v1/files?filename=photo.jpg" \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: image/jpeg" \  --data-binary @photo.jpg | jq -r .id) # Then run the model with it.jq -n --arg file "$FILE_ID" '{  "model": "openai/gpt-image-2.5-sunburst",  "input": {    "prompt": "A silk scarf in the wind on a ferry deck",    "aspect_ratio": "1:1",    "settings": {      "quality": "medium"    },    "images": [      $file    ]  }}' \  | curl https://api.tryleap.ai/v1/generations \    -H "x-api-key: $LEAP_API_KEY" \    -H "content-type: application/json" \    -H "prefer: wait=60" \    -d @- # Still "queued" or "running" after the wait? Read it again by its "id".

Inputs

What GPT Image 2.5 Sunburst takes

Only prompt is needed; everything else has a default. The same schema is public, with no key, at api.tryleap.ai/v1/public/models/openai/gpt-image-2.5-sunburst.

Promptprompt
Text, up to 2,000 characters, required
Reference imagesimages
Up to 8 imagesUploaded files to edit or combine, by ID.
Aspect ratioaspect_ratio
1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9. Default: 1:1
Imagesn
1 to 4. Default: 1
Qualitysettings.quality
Low, Medium, High, Extra high, Max. Default: MediumHigher quality takes longer and costs more.
Resolutionsettings.resolution
1K, 2K, 4K. Default: 1K

Pricing

Price per call

An image costs $0.0858. The $2 welcome credit covers 23 default calls. Prices are the provider's list price plus 10%, read from the catalog, and a quote gives the exact price of any input for free.

GPT Image 2.5 Sunburst and its family

A free quote
curl https://api.tryleap.ai/v1/quotes \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: application/json" \  -d '{    "model": "openai/gpt-image-2.5-sunburst",    "input": {      "prompt": "A silk scarf in the wind on a ferry deck",      "aspect_ratio": "1:1",      "settings": {        "quality": "medium"      }    }  }'

How it works

How the GPT Image 2.5 API works

Every model takes the same request, a model ID and its input, and results, prices, failures and limits work the same way for all of them.

  • Wait for it, or hear when it ends

    prefer: wait=60 holds the request until the result is ready, for up to a minute. A longer run is read again by its ID, or a signed webhook tells your server when it ends.

    prefer: wait=60 / "webhook": "https://..."

    In the docs

  • Failed calls cost nothing

    The price is held when a call starts and charged only if it succeeds. A failed or refused call comes back with its failure_cause, and the hold is released.

    "status": "failed" / "failure_cause": "provider_refused"

    In the docs

  • The price before the call

    POST /v1/quotes takes the same body as a generation and returns its exact price, with the input checked, for free. Every result carries what it was charged.

    POST https://api.tryleap.ai/v1/quotes / "cost_usd"

    In the docs

  • Rate limits

    600 requests a minute per API key and 300 per IP address. A 429 carries Retry-After with the seconds to wait.

    RateLimit-Remaining / Retry-After

    In the docs

  • Safe retries

    Send an idempotency key and a retry after a dropped connection returns the same generation instead of starting a second one.

    idempotency-key: <uuid>

    In the docs

  • Batches

    POST /v1/batches starts up to 50 calls in one request, priced and held together, so either all start or none do.

    POST https://api.tryleap.ai/v1/batches

    In the docs

MCP

Or let your agent call it.

Leap's MCP server lets Claude Code, Claude, VS Code and other MCP clients run GPT Image 2.5 Sunburst, read its inputs and fetch the result, on your balance. Signing in happens in the browser, so there is no key to paste.

Connect an agentThe agent guide
Add Leap to Claude Code
claude mcp add --transport http leap https://app.tryleap.ai/api/mcp

Claude Code signs you in through the browser the first time it calls Leap.

Teach your coding agent the Leap API
curl -fsSL https://www.tryleap.ai/install.sh | sh

Installs the Leap skill for every coding agent it finds: which endpoint to call, how to read a model's inputs, when to wait and when to poll.

Questions

GPT Image 2.5 API questions

How much does the GPT Image 2.5 API cost?
An image costs $0.0858. By quality, a call costs $0.0704 to $0.5269. That is the provider's list price plus 10%, the same as in the studio. POST /v1/quotes prices any input for free before you run it.
Can I try the GPT Image 2.5 API for free?
Yes. Sign up with a Gmail, Outlook or work address and your workspace starts with $2 of credit, no card needed. An image costs $0.0858. The $2 welcome credit covers 23 default calls.
Do I pay for calls that fail?
No. The price is held when a call starts and charged only if it succeeds. A call that fails, or that the model's safety filter refuses, comes back with status "failed" and a failure_cause, and the hold is released.
Is this OpenAI's own API?
No. Leap is a separate service: it sends your call to OpenAI's model and gives you what it makes, so you need no OpenAI account. One Leap key runs GPT Image 2.5 Sunburst and every other model in the catalog, from one balance.
What are the rate limits?
600 requests a minute per API key and 300 a minute per IP address. A batch starts up to 50 calls in one request. A 429 says how long to wait in its Retry-After header.
Can an AI agent call it?
Yes. Leap's MCP server lets Claude Code, Claude, VS Code and other MCP clients find GPT Image 2.5 Sunburst, read its inputs, run it and fetch the result on your balance. The client signs you in through the browser, so there is no key to paste.

Build with GPT Image 2.5 Sunburst.

Start with $2 of credit, no card. The same key runs every model on Leap.

Get an API key