API ManyNew models: Qwen 3.8 Max, Claude Haiku 5.5, Claude Opus 5.5, Claude Sonnet 5.5

GPT Image 1 API

Input / 1M tokens$4.40$5.00
Output / 1M tokens$35.20$40.00
ImageOpenAI12% below officialText & image to image
Loading playground…

About GPT Image 1

GPT Image 1 by OpenAI is available on API Many from $4.40 per million input tokens and $35.20 per million output tokens, and you call it with the same API key you use for every other model.

Send a prompt — and reference images when the model supports them — to /v1/images/generations. The job runs asynchronously and the finished images stay downloadable for 30 days.

You pay only for successful results: failed or rejected requests are refunded automatically, and every call is recorded in your console with its exact cost.

Related models

−95%
GPT Image 2gpt-image-2
ImageOpenAIText & image to imageUp to 4K
from $0.011/ imageTry it
New−12%
GPT Image 2.5 Sunburstgpt-image-2.5-sunburst
ImageOpenAIText & image to image
$4.40 in · $26.40 outTry it
DALL·E 3dall-e-3
ImageOpenAIText to image
from $0.04/ imageTry it
GPT Image 1 (Official)gpt-image-1-official
ImageOpenAIText & image to image
from $0.0088/ imageTry it
GPT Image 1.5 (Official)gpt-image-1.5-official
ImageOpenAIText & image to image
from $0.0072/ imageTry it
GPT Image 2 (Official)gpt-image-2-official
ImageOpenAIText & image to imageUp to 4K
from $0.0018/ imageTry it
GPT Image 2.5 Extgpt-image-2.5-ext
ImageOpenAIText & image to image
from $0.011/ imageTry it
New−12%
GPT Image 2.5 Flaregpt-image-2.5-flare
ImageOpenAIText & image to image
$4.40 in · $26.40 outTry it

Frequently asked questions

How much does the GPT Image 1 API cost?

GPT Image 1 starts at $4.40 per million input tokens and $35.20 per million output tokens on API Many. The price table on this page lists every tier; you are charged only for successful requests.

How do I call GPT Image 1?

Create an API key in the console, then send a request to /v1/images/generations with "model": "gpt-image-1". The API tab has copy-ready examples in cURL, Python and Node.js.

Is this the official GPT Image 1 model?

Yes. Requests are forwarded to the model maker or an authorized channel with the same parameters, so the output matches the official API.

What happens if a request fails?

Failed, rejected or timed-out requests are not charged. Reserved balance is released automatically and the reason is shown in the call record.