Introducing GPT-Image-2.5 Sunburst (and Flare)OpenAIReleased March 20, 2026

GPT-Image-2.5 Sunburst (and Flare)

OpenAI’s premier image synthesis and conversational in-painting model, supporting pinpoint region edits and variable quality modes.

text-to-imageProprietary API$0.045 / image (Precision Editing)Context: 262.144K (262,144 tokens)

Technical Specifications

Architecture Type
High-Precision Visual Reasoning & Editing Model
Total Parameters
Undisclosed
Context Window
262.144K (262,144 tokens)
Max Output Tokens
16.384K (16,384 tokens)
Knowledge Cutoff
October 2025
Supported Modalities
vision, image-gen, text
License & Access
OpenAI Business Terms

Benchmark Evaluations

Gen Eval
0.92
Editing Precision Score
97.4

Deep Architectural Overview

GPT-Image-2.5 Sunburst delivers professional creative production standards. It supports quality tiers from rapid drafts to ultra-high rendering, featuring sub-pixel region in-painting and layered visual prompt understanding.

Strengths & Considerations

Core Strengths
  • Highest editing precision in OpenAI lineup (97.4%)
  • Quality modes from low to max
  • Interprets multi-image references natively
Known Limitations
  • Max quality mode requires higher generation compute latency

Token & API Pricing

Input Tokens (1M)$5.00
Output Tokens (1M)$30.00
Cached Input (1M)$1.2500
Pricing is verified directly against OpenAI's developer documentation and API rate sheets.

Similar & Alternative Models

Explore other frontier models from OpenAI and comparable reasoning engines.

Browse all models
OpenAI

OpenAI GPT-6 model for focused, high-volume workloads where cost efficiency is the priority.

1.05M ctxUSD 0.10 / 1M input tok; USD 0.50 / 1M output tok
OpenAI

OpenAI GPT-6 model built for complex coding and agentic workflows, balancing intelligence and cost.

1.05M ctxUSD 2 / 1M input tok; USD 10 / 1M output tok
OpenAI

OpenAI’s premier sixth-generation frontier model, built for the most demanding end-to-end software engineering and scientific research tasks.

1.05M ctx$10.00 / 1M tok (GPT-6 Frontier)