GPT-5 Image

OpenAI· released 14 Oct 2025

openai/gpt-5-image
Input / 1M tokens
$10
Output / 1M tokens
$10
Context window400K tokens

Longest answer: 128K tokens

reads imagereads textreads filevisionreasoning

About

GPT-5 Image is an OpenAI model that combines GPT-5 with image-generation capabilities. It accepts text, images, and files, and can return both text and images. The model supports reasoning and vision, with a 400,000-token context window and a maximum output of 128,000 tokens. Its listed rates are USD 10 per 1M input tokens and USD 10 per 1M output tokens. The summary highlights improvements in reasoning, code quality, and user experience, alongside instruction following associated with GPT Image 1. Its model ID is openai/gpt-5-image, and its family is OpenAI. Builders can consider it where a workflow needs both image and text outputs alongside text, image, or file inputs. The listed release date is 2025-10-14.

Who it is for

It suits builders developing workflows that need image generation alongside text, or that accept image and file inputs. Its reasoning support and 400,000-token context may also fit tasks needing those capabilities.

What is good

  • Generates both image and text outputs
  • Accepts text, image, and file inputs
  • 400,000-token context window
  • Reasoning and vision are supported

What to know first

  • Input costs USD 10 per 1M tokens
  • Output costs USD 10 per 1M tokens

Verdict

GPT-5 Image combines multimodal inputs with image and text generation, reasoning, and a large context window. Its listed input and output rates are both USD 10 per 1M tokens.

Details

Lab
OpenAIopenrouter.ai · 3 Oct 2026
Context
400Kopenrouter.ai · 3 Oct 2026
Input price
$10 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$10 / 1Mopenrouter.ai · 3 Oct 2026
Max output
128,000 tokensopenrouter.ai · 3 Oct 2026
Inputs
image, text, fileopenrouter.ai · 3 Oct 2026
Open weights
Noopenrouter.ai · 3 Oct 2026

More newest models

See the list