replicate / image
gpt-image-2
OpenAI's state-of-the-art image generation model. Create and edit images from text with strong instruction following, sharp text rendering, and detailed editing.
openai/gpt-image-2
来源检查时间: 2026-09-13 · 供应商端点记录，不代表独立效果评测。
价格与适用条件。
以下是来源观察记录，不能直接相互替代。Token、计算耗时、输出时长与按次价格不能仅比较数值；输入和可选功能可能另行计费。
| 来源标价 | 计费单位 | 条件 | 依据 |
|---|---|---|---|
| $0.128 USD | output image | model variant: auto · or around 78 images for $10 | 公开结构化来源 |
| $0.012 USD | output image | model variant: low · or around 83 images for $1 | 公开结构化来源 |
| $0.047 USD | output image | model variant: medium · or around 21 images for $1 | 公开结构化来源 |
| $0.128 USD | output image | model variant: high · or around 78 images for $10 | 公开结构化来源 |
来源提供的参数
| quality | The quality of the generated image · Options: low, medium, high, auto · Default: auto |
|---|---|
| aspect_ratio | The size of the generated image. Use 'auto' to let the model pick. Sizes above 2560x1440 are experimental and may give more variable results. · Options: 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, auto, 1024x1024, 1536x1024, 1024x1536, 1536x1152, 1152x1536, 2048x2048, 2048x1152, 1152x2048, 3840x2160, 2160x3840 · Default: 1:1 |
| output_format | Output format · Options: png, jpeg, webp · Default: webp |
未列出的参数、地区可用性、最低充值、税费和商用条款仍待核实，购买前请核对精确端点。