GPT Image 2 API
Est.价格: $0.0017 - 0.817(~ 0.11383 - 55.58049 credits) per image
Token-based billing — range covers all Playground combinations at n=1 (quality / resolution / ratio / up to 16 reference images). Multiply by Count for n>1.
稳定性最高,保证 99.9% 可用性。推荐用于生产环境。
Use the same API endpoint. The model parameter selects the variant.
GPT Image 2 API 定价与接入
通过 EvoLink 运行 GPT Image 2,用于文生图、图生图、图像编辑和异步任务交付。查看定价,在 Playground 测试提示词,并用一套 API 流程进入生产环境。

Upload up to 16 images (max 50MB each)
Click to upload or drag and drop
Supported formats: JPEG, JPG, PNG, WEBP
Maximum file size: 50MB; Maximum files: 16
Ratio mode: w×h ≈ Resolution tier pixel budget (1K≈1.05MP, 2K≈4.19MP, 4K=8.29MP). Auto lets the model decide (resolution ignored; cost estimated as 2048×2048 conservative cap). Custom takes any WxH — both multiples of 16, 655K~8.29M total pixels, edges ≤ 3840px, aspect ≤ 3:1.
Anchor-edge tier for aspect-ratio sizes. Combinations exceeding the 8.29 MP budget are scaled down (e.g. 4K 1:1 → 2880×2880). Ignored in Auto and Custom modes.
Rendering effort / thinking depth. Directly affects output token count and cost.
Number of images to generate (1-10)
Click Generate to see preview
History
最多保留20条0 运行中 · 0 已完成
Billing Model
- •Token-based — charged by the token counts reported in the upstream usage object.
- •Image Output tokens scale with size and quality (low/medium/high).
- •Image Input tokens apply only in image-to-image / edit mode.
- •Cached Input is charged only when the upstream usage object reports cached tokens.
Pricing
| Model | Mode | Token Category | Price |
|---|---|---|---|
| GPT Image 2 | Token-based billing | Image Output | $0.027/ 1K tokens(1.836 Credits) |
| GPT Image 2 | Token-based billing | Image Input | $0.0072/ 1K tokens(0.4896 Credits) |
| GPT Image 2 | Token-based billing | Image Cached Input | $0.0018/ 1K tokens(0.1224 Credits) |
| GPT Image 2 | Token-based billing | Text Input | $0.0045/ 1K tokens(0.306 Credits) |
| GPT Image 2 | Token-based billing | Text Cached Input | $0.0011/ 1K tokens(0.0765 Credits) |
If it's down, we automatically use the next cheapest available—ensuring 99.9% uptime at the best possible price.
Figures are pre-bill estimates. Actual charges follow the upstream response.usage returned by the model.
利用 GPT Image 2 可以构建什么
为什么通过 EvoLink 使用 GPT Image 2
EvoLink 把 GPT Image 2 变成一个更容易决策的接入页:一条路由、清晰定价、Playground 验证,以及适合生产图像任务的异步工作流。
从测试到生产只用一条 API 路由
你可以先在 Playground 验证提示词和请求结构,再进入 API 集成,而不需要切换工具或重构调用流程。
更清楚的价格与计费视图
这个页面把定价、Playground 入口和请求模型名放在一起,方便团队在扩大图像工作负载之前先判断成本。
更适合真实任务的异步流程
EvoLink 上的 GPT Image 2 采用异步任务流,更适合耗时更长的生成和编辑请求,而不是把所有请求都假设成即时同步返回。
如何接入 GPT Image 2
三步完成路由测试、请求发送和异步图像结果获取。
创建 API Key
登录 EvoLink 后创建一个 API Key,即可同时用于 Playground 测试和生产请求。这也是平台内其他支持模型的统一接入方式。
发送 GPT Image 2 请求
请求里使用 `gpt-image-2` 作为模型名,并传入 prompt、size、quality;如果要做参考图编辑或图生图工作流,再额外传入 `image_urls`。
轮询任务结果并保存素材
图像生成通过异步任务返回。你的应用需要轮询任务状态,在结果完成后及时保存资产,因为生成后的图片链接有时效限制。
GPT Image 2 核心能力
在评估图像 API 是否适合生产使用时,真正重要的控制项和交付能力。
文生图与图像编辑
同一条路由既可用于全新图像生成,也可处理参考图编辑和图生图类工作流。
参考图支持
当工作流需要受控编辑、变体生成或基于已有素材做 prompt 驱动修改时,可以附加一张或多张参考图 URL。
尺寸与质量控制
可以选择支持的纵横比或像素尺寸,并按输出要求和成本容忍度调整质量参数。
异步任务交付
请求会返回任务 ID 以便轮询,这让团队可以更清晰地管理耗时较长的生成和编辑任务。
单图输出流程
这条路由围绕单次请求输出一张结果图来设计,更适合审批、存储和自动化流水线中的后处理。
有时效的结果链接
生成完成后的图片 URL 是临时的,生产集成应及时把输出保存到应用自己的存储或素材管理流程中。
费用示例
使用低质量进行提示词迭代(0.11 倍成本),仅在最终输出时使用高质量。
常见问题
Everything you need to know about the product and billing.
查看 GPT Image 家族
GPT Image 2 是 EvoLink 上 GPT Image 家族里最新的路线。 如果你下一步的问题是应该选哪条路线,先去家族页查看;然后再对比 GPT Image 1.5 或 GPT Image 1,判断当前更适合生产默认还是作为旧版基线。
API Reference
Select endpoint
Authentication
All APIs require Bearer Token authentication.
Authorization:
Bearer YOUR_API_KEY/v1/images/generationsGenerate Image
Create an image generation task using text prompts. Supports text-to-image and reference-image-assisted generation.
Asynchronous processing mode, use the returned task ID to query status.
Generated image links are valid for 24 hours, please save them promptly.
Request Parameters
modelstringRequiredDefault: gpt-image-2Image generation model name.
| Value | Description |
|---|---|
| gpt-image-2 | Official Azure GPT Image 2 — token-based billing |
gpt-image-2promptstringRequiredPrompt describing the image to be generated or how to edit the reference image.
Notes
- Max 32,000 characters (counted by Unicode code points — works for CJK and other languages)
A beautiful colorful sunset over the oceansizestringOptionalDefault: autoAspect ratio or explicit pixel dimensions (WxH).
| Value | Description |
|---|---|
| auto | Default — let the model decide |
| 1:1 / 1:2 / 2:1 / 1:3 / 3:1 / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 21:9 / 9:21 | Aspect ratio — pixel size decided together with the resolution tier |
| 1024x1024 (or any WxH) | Explicit pixels — multiples of 16, pixel budget 655K~8.29M, edges ≤3840, aspect ≤3:1 |
Notes
- When size is explicit WxH pixels, the resolution parameter is ignored.
- In auto mode the model decides the final size; resolution has no effect.
- Combinations that exceed the 8.29 MP pixel budget are proportionally scaled down (e.g. 4K 1:1 → 2880×2880).
autoresolutionstringOptionalDefault: 1KResolution tier shortcut. Only effective when size is a ratio; ignored for explicit pixels and auto.
| Value | Description |
|---|---|
| 1K | Pixel budget ≈ 1024² = 1.05MP (1:1 → 1024×1024, 16:9 → 1360×768) |
| 2K | Pixel budget ≈ 2048² = 4.19MP (1:1 → 2048×2048, 16:9 → 2736×1536) |
| 4K | Pixel budget = 8.29MP / MaxPixels (1:1 → 2880×2880, 16:9 → 3840×2160 UHD) |
2KqualitystringOptionalDefault: mediumRendering quality / reasoning depth. Directly drives output token count (tile base 16/48/96 for low/medium/high).
| Value | Description |
|---|---|
| low | Tile base 16 — fastest, ~0.11× cost vs medium |
| medium | Tile base 48 — balanced (default) |
| high | Tile base 96 — highest fidelity, ~4× cost vs medium |
mediumnintegerOptionalDefault: 1Number of images to generate (1-10). Each image is billed independently; text input tokens scale linearly with n.
1image_urlsarrayOptionalReference image URL list for image-to-image and image editing features.
Notes
- 1–16 images per request
- Each image ≤ 50 MB
- Supported formats: .jpeg, .jpg, .png, .webp
- URLs must be directly accessible by the server, or URLs that trigger direct download (typically URLs ending with image extensions like .png, .jpg)
- Reference images themselves consume additional image-input tokens in edit / image-to-image mode
https://example.com/image1.pngcallback_urlstringOptionalHTTPS callback address after task completion.
Notes
- Triggered on completion, failure, or cancellation
- Sent after billing confirmation
- HTTPS only, no internal IPs
- Max length: 2048 chars
- Timeout: 10s, Max 3 retries
https://your-domain.com/webhooks/image-task-completed

