OpenAI

GPT Image 2

GPT Image 2 is OpenAI's image generation model. It reads images.

Vision input

Output price

$24.90

USD / 1M tokens

17% below list price

Add $5, get $5 more on your first top-up.

Same GPT Image 2. 17% less.

Price
USD / 1M tokens, next to OpenAI's list price.
TokensList pricePromptsForLess
Input$5.00$4.15
Output$30$24.90
Your monthly bill
Enter your monthly usage to see the difference.
At list price$110
With PromptsForLess$91.30

That's $18.70 saved every month.

USD, before tax and prompt caching.

Specs.

Model ID
gpt-image-2
Made by
OpenAI
Context window
Varies
Max output
Varies
Endpoint
/v1/images/generations
Billing
Per token, from one balance
Built for
  • Creative generation. Generate images from text prompts through the same API key and balance as your text models.

Edge gateways

Requests enter at the gateway nearest your app and go straight to the model, so routing adds very little to each call.

One key, every model

Switch models by changing a string. One prepaid balance covers all of them, billed per token.

Nothing stored

We keep token counts for billing, never your prompts or responses.

Call GPT Image 2 in a minute.

Use the model ID gpt-image-2 with the same API key and balance as your text models.

Read the quickstart

More from OpenAI.

Questions.

How much does GPT Image 2 cost?

$24.90 / 1M tokens output and $4.15 / 1M tokens input, 17% below OpenAI's list price. You pay per token from a prepaid balance, with no subscription or minimum. We match your first $5 top-up, so you start with $10 of credit.

Is it the real GPT Image 2?

Yes. Your requests run on OpenAI's GPT Image 2, not a distilled copy or a substitute. The discount comes from how we buy capacity, not from changing the model.

Which tools can use GPT Image 2?

Call GPT Image 2 through the PromptsForLess API with the model ID gpt-image-2, using the same key and balance as your text models.

How fast is it?

Requests go through our edge gateways, so the network hop adds very little on top of GPT Image 2's own generation time. Responses stream back token by token.