OpenAICertifiedReleased 10/06/2025

GPT Image 1 Mini

A cost-efficient version of GPT Image 1. It is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.

View API reference ↓
Input / output priceFrom$2.00 / $8.00per 1M
24h uptime100.00%
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.images.generate({
  model: "openai/gpt-image-1-mini",
  prompt: "A lighthouse at dusk, oil painting",
  size: "1024x1024",
});

// Base64 only: images are returned, never stored.
const png = Buffer.from(res.data[0].b64_json, "base64");

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
OpenAI00——$2.00$8.00Read $0.20Write —2 featuresNoYesGlobalCertified

Uptime

24 hours

Request success rate per provider.

OpenAI100.00%

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.images.generate({
  model: "openai/gpt-image-1-mini",
  prompt: "A lighthouse at dusk, oil painting",
  size: "1024x1024",
});

// Base64 only: images are returned, never stored.
const png = Buffer.from(res.data[0].b64_json, "base64");

GPT Image 1 Mini answers POST /v1/images/generations, and edits images with POST /v1/images/edits, not chat completions. It is billed per output token: the balance held for a request is the most tokens the size and quality asked for were measured to take.

Tokens per image

Measured on OpenAI at $8.00 per 1M output tokens. Other sizes are refused; set the quality with providerOptions.openai.quality.

OutputOutput tokens
1024x1024 · low272 tokens ≈ $0.002
1024x1024 · medium1,056 tokens ≈ $0.008
1024x1024 · high4,160 tokens ≈ $0.033
1024x1536 · low408 tokens ≈ $0.003
1024x1536 · medium1,584 tokens ≈ $0.013
1024x1536 · high6,240 tokens ≈ $0.050
1536x1024 · low400 tokens ≈ $0.003
1536x1024 · medium1,568 tokens ≈ $0.013
1536x1024 · high6,208 tokens ≈ $0.050
Size not set · high6,208 tokens ≈ $0.050

More models by OpenAI

ModelContextInputOutputCacheRelease
openai/gpt-image-2.6-flare0$5.00$30.00Read $1.25Write —11/04/2026
openai/gpt-image-2.6-sunburst0$5.00$30.00Read $1.25Write —11/04/2026
openai/gpt-image-2.5-flare0$5.00$30.00Read $1.25Write —09/08/2026
openai/gpt-image-2.5-sunburst0$5.00$30.00Read $1.25Write —09/08/2026
openai/gpt-image-20$5.00$30.00Read $1.25Write —04/21/2026
openai/gpt-image-1.50$5.00$32.00Read $1.25Write —12/16/2025