GPT Image 2

GPT Image 2.0, OpenAI's latest image model, is capable of creating extremely detailed images with fine typography.

By OpenAI

Pricing: $0.211 per image

Overview

GPT Image 2 by OpenAI is a text-to-image model with exceptional typography rendering, strong prompt adherence, and fine-grained control over composition, lighting, and detail.

Key capabilities

• **$0.009–$0.133 per image** (low/medium/high quality) — usage-based, pay only for what you generate.
• **Multi-region failover**, Runflow runs optimized inference across multiple regions. If one region has an outage, traffic routes to another automatically.
• **Best-in-class text rendering**, readable typography, accurate signage, and controlled layouts.
• **Up to 10 images per request**, set the `num_images` parameter for batch generation.

GPT Image family

| Model | Details |

|---|---|

| **GPT Image 2** (this model) | Latest generation, text-to-image, improved typography and detail |

| **GPT Image 2 Edit** | Same model for image editing — provide reference image(s) and edit prompt |

| **GPT Image 1.5** | Previous generation, text-to-image |

| **GPT Image 1.5 Edit** | Previous generation, image editing |

Technical specifications

| Spec | Details |

|---|---|

| Quality tiers | low, medium, high (default) |

| Output formats | png, jpeg, webp |

| Max images per request | 10 |

| Pricing | $0.009 (low), $0.034 (medium), $0.133 (high) per image |

Examples

• A hand-drawn storefront sign reading 'CIRCUIT & GRAIN — specialty coffee' on polished brass, warm morning sunlight, shallow depth of field, the shop window visible behind with pastry trays, cinematic photograph

Frequently asked questions

What is GPT Image 2?

GPT Image 2 is OpenAI's latest text-to-image model, delivering state-of-the-art typography rendering, strong prompt adherence, and fine-grained control over composition, lighting, and detail. Available via the Runflow API.

How much does GPT Image 2 cost on Runflow?

GPT Image 2 uses tiered per-image pricing on Runflow: $0.009 per image at low quality, $0.034 at medium, and $0.133 at high quality (the default). Usage-based — you pay only for images you generate.

How long does GPT Image 2 take to generate an image?

GPT Image 2 typically completes in 10–30 seconds depending on quality tier and output format. High quality takes longest; low quality is fastest.

Can I use GPT Image 2 commercially?

Yes. GPT Image 2 is offered under a commercial license via Runflow. Generated images can be used in commercial products, marketing, and client work, subject to OpenAI's usage policies.

Do I need to manage GPUs or OpenAI credits to use GPT Image 2?

No. Runflow handles all infrastructure — routing, queueing, and underlying OpenAI API billing. One API key, fixed per-image pricing, no AI team or DevOps required.

How do I get started with GPT Image 2 on Runflow?

Sign up for Runflow, grab an API key, and POST a prompt to the `/v1/models/openai/gpt-image-2/runs` endpoint. Receive back a run ID; poll until the images are ready. See the API tab on this page for copy-paste code samples in Node, Python, and curl.

Related models

• GPT Image 2 Edit, GPT Image 2.0, OpenAI's latest image model, is capable of making fine-grained, detailed edits to images.
• GPT Image 1.5, GPT Image 1.5 generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail.
• FLUX 1.1 [pro] Ultra, Ultra-resolution variant of FLUX 1.1 [pro] with 4MP+ outputs and richer detail. Drop-in upgrade when the standard FLUX 1.1 [pro] resolution is the bottleneck.
• FLUX 1.1 [pro], Black Forest Labs' production-grade FLUX 1.1. State-of-the-art prompt adherence and photoreal quality at competitive per-image pricing.

Discoverable surfaces

• Dispatch endpoint: POST https://api.runflow.io/v1/models/gpt-image-2/runs
• Per-model spec (markdown): https://app.runflow.io/models/gpt-image-2/llms.txt
• Docs page: https://docs.runflow.io/models/gpt-image-2
• Public OpenAPI spec: https://docs.runflow.io/api/openapi.public.json
• Agent skill (start here): https://www.runflow.io/.well-known/agent-skills/runflow/SKILL.md