GPT Image 2
OpenAI 當前旗艦圖片模型，適合高質量圖像生成與編輯。
輸入類型
文本 + 圖片
既可生成，也可編輯
輸出類型
圖片
高質量圖像輸出
流式返回
不支持
圖片任務以完整結果返回
模型別名
gpt-image-2
當前默認模型代號
gpt-image-2試玩區
gpt-image-2Click or drag
分辨率 (sent to backend)
Aspect Ratio (sent to backend)
Quality (sent to backend)
Output format (sent to backend)
暫無輸出
定價
| 模態 | 輸入 | 緩存輸入 | 輸出 |
|---|---|---|---|
| 文本 | $45.9$5 / 1M tokens10% off | $1.1259$1.25 / 1M tokens10% off | - |
| 圖片 | $72.9$8 / 1M tokens10% off | $18.9$2 / 1M tokens10% off | $270.9$30 / 1M tokens10% off |
Text Input · $4.5 · 1M tokens
Text Cached · $1.125 · 1M tokens
Image Input · $7.2 · 1M tokens
Image Cached · $1.8 · 1M tokens
Image Output · $27 · 1M tokens
README
- OpenAI 將 GPT Image 2 定位爲當前最先進的圖片生成模型，主打高質量生成與編輯能力。
- 它支持文本與圖片輸入、圖片輸出、靈活尺寸設定，以及高保真圖片輸入編輯工作流。
- 在 OpenAI 的圖片接口指南中，GPT Image 2 是當前推薦用於生產環境圖片生成與編輯的默認模型。
API
API
端點
POST /v1/images/generations認證
Authorization: Bearer YOUR_REACH_API_KEY
示例
curl -X POST "https://direct.reachapi.ai/v1/images/generations" \
-H "Authorization: Bearer YOUR_REACH_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2",
"prompt": "A precise editorial product shot of a cobalt blue mechanical keyboard on a slate desk"
}'相關模型
GPT-6.1 Sol
OpenAI's balanced flagship for coding, reasoning, and agentic work with tiered short- and long-context pricing.
GPT-6 Astra
OpenAI's flagship model for demanding end-to-end work.
GPT-6 Luna
OpenAI's cost-efficient flagship for high-volume, cost-sensitive workloads.
GPT-6 Sol
OpenAI's balanced flagship for high-volume coding, reasoning, and agentic work.
GPT-5.6 Luna
OpenAI's GPT-5.6 model for efficient, cost-sensitive, high-volume workloads.
GPT-5.6 Sol
OpenAI's GPT-5.6 flagship model for the most demanding production reasoning, coding, and agent workflows.
GPT-5.6 Terra
OpenAI's GPT-5.6 model for strong intelligence with a balanced cost profile.
GPT-5.5
OpenAI's newest frontier model for the most complex coding, reasoning, and professional workflows.
GPT-5.4
OpenAI's frontier model for complex professional, coding, and agentic work at scale.
GPT-5.4 Mini
OpenAI's strongest mini model for coding, computer use, and high-volume agent tasks.
GPT-5.3 Codex
OpenAI's most capable agentic coding model to date.
GPT-5.2
OpenAI's stronger GPT-5-family model for professional, general-purpose, and agentic work.
GPT-5.1
OpenAI's flagship model for coding and agentic tasks with configurable reasoning.
GPT-5.1 Codex
OpenAI's GPT-5.1 variant optimized for agentic coding in Codex workflows.
GPT-5
OpenAI's previous intelligent reasoning model for coding and agentic tasks.
GPT-5 Mini
OpenAI's faster, cost-efficient GPT-5 variant for low-latency and high-volume work.
GPT Image 2.5 Flare
OpenAI's fastest model for high-quality, everyday image generation and editing.
GPT Image 2.5 Sunburst
OpenAI's most capable image model for high-quality generation and precision editing.
GPT Image 2 Async
ReachAPI's asynchronous GPT Image 2 workflow for task-based image generation and editing with callback-ready results.