GPT Image 1.5 API — pricing & specs

GPT Image 1.5 is an OpenAI model that generates images from text prompts. On KeepRouter, GPT Image 1.5 costs $8.00 per 1M input tokens and $32.00 per 1M output tokens, billed pay-as-you-go with no monthly fee. Call it through a compatible KeepRouter endpoint supported by its active route, with the model id gpt-image-1.5.

MakerOpenAI
ModalityText-to-image
Input price$8.00 per 1M tokens
Output price$32.00 per 1M tokens
CapabilitiesImage generation (text-to-image)
EndpointPOST /v1/images/generations
Model idgpt-image-1.5

How pricing works for GPT Image 1.5

GPT Image 1.5 is billed per token — $8.00 per 1M input tokens and $32.00 per 1M output tokens. The published price is pay-as-you-go, with no monthly fee; actual request cost depends on measured token usage.

Calling GPT Image 1.5 on KeepRouter

Point a compatible client at the supported KeepRouter endpoint and set the model to gpt-image-1.5. KeepRouter preserves the client-facing request shape while handling upstream routing or translation. Send image-generation requests to POST /v1/images/generations.

cURL

curl https://keeprouter.com/v1/images/generations \
  -H "Authorization: Bearer $KEEPROUTER_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gpt-image-1.5","prompt":"a red bicycle on a beach"}'

Python

import os
from openai import OpenAI
client = OpenAI(base_url="https://keeprouter.com/v1", api_key=os.environ["KEEPROUTER_KEY"])
img = client.images.generate(model="gpt-image-1.5", prompt="a red bicycle on a beach")

JavaScript

const res = await fetch("https://keeprouter.com/v1/images/generations", {
  method: "POST",
  headers: { Authorization: "Bearer " + process.env.KEEPROUTER_KEY, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "gpt-image-1.5", prompt: "a red bicycle on a beach" }),
});

Estimate API costs

At the current KeepRouter customer price, an example workload of 1,000 total input tokens, no cached input, and 500 output tokens per request costs approximately $0.0240 per request. At 100 requests per day, that is $72.00 over 30 days. This is a usage estimate, excluding processing fees, taxes, retries and application infrastructure. Actual usage, cache hits and supported generation durations need their own checks.

Adjust quantities in the API cost calculator.

How to evaluate GPT Image 1.5

GPT Image 1.5 is listed on KeepRouter as text-to-image under the exact id gpt-image-1.5. Use /v1/images/generations for the listed route; a maker's upstream features do not automatically apply to this gateway endpoint. No context limit is asserted here because the exact upstream limit has not been verified for this catalog entry.

First workload: Generate a small batch from your real prompt and asset dimensions; review text rendering, composition, retry rate and cost per accepted image.

Before production: This is an image-generation route. Do not send it to chat completions or assume another router's image parameters are interchangeable.

Public model usage evidence

No public, exact-variant usage figure has been verified for this KeepRouter model id. Missing data is not zero usage; family-level or maker-wide traffic is not presented as this model's traffic.

Published examples and cases

No exact-model customer case has been verified for this entry. The workload above is an evaluation recipe, not a claim of a public deployment.

Source and verification boundary

Official OpenAI website. KeepRouter's live catalog is authoritative for the customer price and enabled endpoint shown here; the maker remains authoritative for upstream model capabilities and limits.

Pricing and implementation guides

Related models

All models & pricing · Quickstart · KeepRouter vs OpenRouter · Glossary · Get an API key

Catalog facts and prices last changed .

Page content reviewed .