← Models

GPT Image 1.5

OpenAI · GPT Image

OpenAI's previous premium GPT Image tier for higher-fidelity generation and iterative editing workflows.

Part of GPT Image family · Other versions: GPT Image 2 , gpt-image-1-mini , GPT-Image-1
Type
image
Context
N/A
Max Output
N/A
Status
current
API Access
Yes
License
proprietary
image-generation image-editing creative api openai
Released February 2026 · Updated April 24, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on April 24, 2026.

GPT Image 1.5 is OpenAI’s previous premium image-generation model in the GPT Image family. OpenAI’s current model catalog positions it above earlier GPT-Image-1 generation routes and presents it as a higher-fidelity option for teams building image generation and editing into products or internal creative tooling. For new work, GPT Image 2 is now the newer ChatGPT Images 2.0 route to evaluate first.

Capabilities

GPT Image 1.5 is designed for prompt-driven image generation plus edit-heavy workflows. The practical advantage is not just “make an image.” It is the combination of generation, refinement, and integration with an API-first stack that already handles text, audio, and agent workflows elsewhere in OpenAI’s platform.

For product teams, that matters because image creation often sits inside a larger system: campaign generation pipelines, design-ops tooling, ecommerce asset variants, or content workflows where text and visual generation need to stay in the same platform.

Technical Details

This is an image-native model, so token-style context and max-output fields are not meaningful in the same way they are for language models. In this repository, contextWindow and maxOutput are stored as 0 intentionally and should be interpreted as N/A for UI display and comparisons.

OpenAI’s current model page explicitly documents a gpt-image-1.5-2026-02-27 snapshot, which is the clearest public release marker available in the current docs surface.

Pricing & Access

OpenAI’s pricing docs describe GPT Image 1.5 using per-image pricing rather than token pricing:

  • Low quality: $0.01 per image
  • Medium quality: $0.04 per image
  • High quality: $0.17 per image

Access is through OpenAI API model endpoints and the surrounding platform docs. Teams should verify image-size and quality settings before rollout because cost scales with generation settings rather than a single flat model price.

Best Use Cases

Use GPT Image 1.5 when image quality and editability matter more than lowest-possible generation cost and your implementation is already built around the 1.5 tier. For greenfield high-quality image workflows, start by comparing it with GPT Image 2 rather than assuming the older premium tier is still the default.

Comparisons

  • GPT Image 2 (OpenAI): Newer ChatGPT Images 2.0 route and the first model to evaluate for new premium image workflows.
  • gpt-image-1-mini (OpenAI): Better fit for lower-cost, higher-volume generation where premium quality is not the first priority.
  • GPT-Image-1 (OpenAI): Earlier family entry retained for historical comparison and compatibility context.
  • Imagen 4 (Google): Strong alternative for API-backed image generation, with tradeoffs usually centered on ecosystem fit and style preference.