microsoft/mai-image-2.5-pro/text-to-image

文生图

PRO

MAI-Image 2.5 Pro Text-to-Image API by MICROSOFT

microsoft/mai-image-2.5-pro/text-to-image

Text-to-image

Microsoft AI's highest-fidelity text-to-image model, generating photorealistic, visually dense scenes from natural language with strong object and character consistency and accurate in-image text.

模型对比

MAI-Image 2.5 Pro Text-to-Image 由 Microsoft 开发。Atlas Cloud（由 Atlas Cloud AI LLC 运营）仅提供接入服务，并不拥有该模型。所有商标均归其各自所有者所有。

输入

提示词 *

尺寸

宽度

高度

1024 × 1024 px范围: 768 - 1360

1.05 MP≤ 1.05 MP

输出

空闲

生成的图片将在这里显示

配置参数后点击运行开始生成

每次运行将花费 $0.12。$10 可运行约 83 次。

你可以继续：

图生视频图生图

参数

代码示例
import requests
import time

# Step 1: Start image generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "microsoft/mai-image-2.5-pro/text-to-image",  # Required. model name
    "prompt": "A beautiful landscape with mountains and lake",  # Required. Text prompt describing the image to generate
    "size": "1024*1024",  # Image dimensions in width*height format (e. (min: 768, max: 1360)
    "enable_base64_output": False,  # If enabled, the output will be encoded into a BASE64 string instead of a URL
    "enable_sync_mode": False,  # If set to true, the function will wait for the result to be generated and uploaded before returning the response
}

generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]

# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"

def check_status():
    while True:
        response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
        result = response.json()

        if result["data"]["status"] == "completed":
            print("Generated image:", result["data"]["outputs"][0])
            return result["data"]["outputs"][0]
        elif result["data"]["status"] == "failed":
            raise Exception(result["data"]["error"] or "Generation failed")
        else:
            # Still processing, wait 2 seconds
            time.sleep(2)

image_url = check_status()

安装

安装所需的依赖包。

pip install requests

认证

所有 API 请求需要通过 API Key 进行认证。您可以在 Atlas Cloud 控制台获取 API Key。

export ATLASCLOUD_API_KEY="your-api-key-here"

HTTP 请求头

import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

保护好您的 API Key

切勿在客户端代码或公开仓库中暴露您的 API Key。请使用环境变量或后端代理。

提交请求

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "your-model",
    "prompt": "A beautiful landscape"
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

提交请求

提交一个异步生成请求。API 返回一个 prediction ID，您可以用它来检查状态和获取结果。

POST/api/v1/model/generateImage

请求体

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}

data = {
    "model": "microsoft/mai-image-2.5-pro/text-to-image",
    "prompt": "A beautiful landscape with mountains and lake"
}

response = requests.post(url, headers=headers, json=data)
result = response.json()

print(f"Prediction ID: {result['data']['id']}")
print(f"Status: {result['data']['status']}")

响应

{
  "code": 200,
  "data": {
    "id": "pred_abc123",
    "status": "processing",
    "model": "model-name",
    "created_at": "2025-01-01T00:00:00Z"
  }
}

检查状态

轮询 prediction 端点以检查请求的当前状态。

GET/api/v1/model/prediction/{prediction_id}

轮询示例

import requests
import time

prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

while True:
    response = requests.get(url, headers=headers)
    result = response.json()
    status = result["data"]["status"]
    print(f"Status: {status}")

    if status in ["completed", "succeeded"]:
        output_url = result["data"]["outputs"][0]
        print(f"Output URL: {output_url}")
        break
    elif status == "failed":
        print(f"Error: {result['data'].get('error', 'Unknown')}")
        break

    time.sleep(3)

状态值

processing请求仍在处理中。

completed生成完成，输出可用。

succeeded生成成功，输出可用。

failed生成失败，请检查 error 字段。

完成响应

{
  "data": {
    "id": "pred_abc123",
    "status": "completed",
    "outputs": [
      "https://storage.atlascloud.ai/outputs/result.png"
    ],
    "metrics": {
      "predict_time": 8.3
    },
    "created_at": "2025-01-01T00:00:00Z",
    "completed_at": "2025-01-01T00:00:10Z"
  }
}

上传文件

将文件上传到 Atlas Cloud 存储，获取可在 API 请求中使用的 URL。使用 multipart/form-data 上传。

POST/api/v1/model/uploadMedia

上传示例

import requests

url = "https://api.atlascloud.ai/api/v1/model/uploadMedia"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

with open("image.png", "rb") as f:
    files = {"file": ("image.png", f, "image/png")}
    response = requests.post(url, headers=headers, files=files)

result = response.json()
download_url = result["data"]["download_url"]
print(f"File URL: {download_url}")

响应

{
  "data": {
    "download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
    "file_name": "image.png",
    "content_type": "image/png",
    "size": 1024000
  }
}

Input Schema

以下参数在请求体中被接受。

总计: 5必填: 2可选: 3

modelstringrequired

model name

Default: "microsoft/mai-image-2.5-pro/text-to-image"

promptstringrequired

Text prompt describing the image to generate. Maximum context length: 32,000 tokens.

sizestring

Image dimensions in width*height format (e.g., 1024*1024, 1280*720). Minimum 768. The product of width × height must not exceed 1,048,576.

Default: "1024*1024"Min: 768Max: 1360

enable_base64_outputboolean

If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Default: false

enable_sync_modeboolean

If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.

Default: false

请求体示例

{
  "model": "microsoft/mai-image-2.5-pro/text-to-image",
  "prompt": "A beautiful landscape",
  "size": "1024*1024",
  "enable_base64_output": false,
  "enable_sync_mode": false
}

Output Schema

API 返回包含生成输出 URL 的 prediction 响应。

codeinteger

HTTP status code of the response.

messagestring

Human-readable message; non-empty on failure.

dataobject

响应示例

{
  "id": "pred_abc123",
  "status": "completed",
  "model": "model-name",
  "outputs": [
    "https://storage.atlascloud.ai/outputs/result.png"
  ],
  "metrics": {
    "predict_time": 8.3
  },
  "created_at": "2025-01-01T00:00:00Z",
  "completed_at": "2025-01-01T00:00:10Z"
}

Atlas Cloud Skills

Atlas Cloud Skills 将 400+ AI 模型直接集成到您的 AI 编程助手中。一条命令安装，即可用自然语言生成图像、视频和与 LLM 对话。

支持的客户端

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ 支持的客户端

安装

npx skills add AtlasCloudAI/atlas-cloud-skills

设置 API Key

从 Atlas Cloud 控制台获取 API Key，并将其设置为环境变量。

export ATLASCLOUD_API_KEY="your-api-key-here"

功能

安装后，您可以在 AI 助手中使用自然语言访问所有 Atlas Cloud 模型。

图像生成使用 Nano Banana 2、Z-Image 等模型生成图像。

视频创作使用 Kling、Vidu、Veo 等模型从文本或图像创建视频。

LLM 对话与 Qwen、DeepSeek 等大语言模型对话。

媒体上传上传本地文件用于图像编辑和图生视频工作流。

MCP Server

Atlas Cloud MCP Server 通过 Model Context Protocol 将您的 IDE 与 400+ AI 模型连接。支持任何兼容 MCP 的客户端。

支持的客户端

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ 支持的客户端

安装

npx -y atlascloud-mcp

配置

将以下配置添加到您的 IDE 的 MCP 设置文件中。

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": [
        "-y",
        "atlascloud-mcp"
      ],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

可用工具

atlas_generate_image从文本提示生成图像。

atlas_generate_video从文本或图像创建视频。

atlas_chat与大语言模型对话。

atlas_list_models浏览 400+ 可用 AI 模型。

atlas_quick_generate一步式内容创建，自动选择最佳模型。

atlas_upload_media上传本地文件用于 API 工作流。

了解更多

github.com/AtlasCloudAI/mcp-server

API Schema

{
  "info": {
    "description": "The AtlasCloud API.",
    "title": "AtlasCloud API",
    "version": "1.0.0"
  },
  "paths": {
    "/api/v1/model/generateImage": {
      "post": {
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/Input"
              }
            }
          },
          "required": true
        },
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/PredictionResponse"
                }
              }
            },
            "description": "The request status."
          }
        }
      },
      "x-api-name": "model_run"
    },
    "/api/v1/model/prediction/{request_id}": {
      "get": {
        "parameters": [
          {
            "in": "path",
            "name": "request_id",
            "required": true,
            "schema": {
              "description": "Request ID",
              "type": "string"
            }
          }
        ],
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/PredictionResponse"
                }
              }
            },
            "description": "Result of the request."
          }
        }
      },
      "x-api-name": "model_result"
    }
  },
  "openapi": "3.0.0",
  "servers": [
    {
      "url": "https://api.atlascloud.ai"
    }
  ],
  "components": {
    "schemas": {
      "Input": {
        "properties": {
          "model": {
            "type": "string",
            "description": "model name",
            "default": "microsoft/mai-image-2.5-pro/text-to-image"
          },
          "prompt": {
            "type": "string",
            "description": "Text prompt describing the image to generate. Maximum context length: 32,000 tokens."
          },
          "size": {
            "default": "1024*1024",
            "description": "Image dimensions in width*height format (e.g., 1024*1024, 1280*720). Minimum 768. The product of width × height must not exceed 1,048,576.",
            "maximum": 1360,
            "minimum": 768,
            "totalMinimum": 589824,
            "totalMaximum": 1048576,
            "type": "string",
            "x-hidden": true
          },
          "enable_base64_output": {
            "type": "boolean",
            "default": false,
            "disabled": true,
            "description": "If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API."
          },
          "enable_sync_mode": {
            "type": "boolean",
            "default": false,
            "disabled": true,
            "description": "If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API."
          }
        },
        "required": [
          "model",
          "prompt"
        ],
        "type": "object",
        "x-order-properties": [
          "model",
          "prompt",
          "size",
          "enable_base64_output",
          "enable_sync_mode"
        ]
      },
      "PredictionResponse": {
        "type": "object",
        "properties": {
          "code": {
            "description": "HTTP status code of the response.",
            "type": "integer"
          },
          "message": {
            "description": "Human-readable message; non-empty on failure.",
            "type": "string"
          },
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "description": "Unique identifier for the prediction.",
                "type": "string"
              },
              "model": {
                "description": "Model ID used for the prediction.",
                "type": "string"
              },
              "outputs": {
                "description": "Array of URLs to the generated content. Null when status is not completed.",
                "type": "array",
                "items": {
                  "type": "string"
                },
                "nullable": true
              },
              "urls": {
                "description": "Object containing related API endpoints.",
                "type": "object",
                "properties": {
                  "get": {
                    "description": "URL to poll for the prediction result.",
                    "type": "string",
                    "format": "uri"
                  }
                }
              },
              "status": {
                "description": "Status of the task: created, processing, completed, timeout, or failed.",
                "type": "string"
              },
              "created_at": {
                "description": "ISO timestamp of when the request was created (e.g., \"2023-04-01T12:34:56.789Z\").",
                "format": "date-time",
                "type": "string"
              },
              "error": {
                "description": "Error message if the task failed, empty string otherwise.",
                "type": "string"
              },
              "error_code": {
                "description": "Error code if the task failed.",
                "type": "integer"
              },
              "executionTime": {
                "description": "Total execution time in milliseconds.",
                "type": "number"
              },
              "timings": {
                "description": "Detailed timing breakdown.",
                "type": "object",
                "properties": {
                  "inference": {
                    "description": "Inference time in milliseconds.",
                    "type": "number"
                  }
                }
              }
            }
          }
        }
      }
    },
    "securitySchemes": {
      "apiKeyAuth": {
        "in": "header",
        "name": "Authorization",
        "type": "apiKey"
      }
    }
  }
}

LLM 友好的提示词模板

# microsoft/mai-image-2.5-pro/text-to-image

> Microsoft AI's highest-fidelity text-to-image model, generating photorealistic, visually dense scenes from natural language with strong object and character consistency and accurate in-image text.


## Overview

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateImage` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `microsoft/mai-image-2.5-pro/text-to-image`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  model name
  - Default: `"microsoft/mai-image-2.5-pro/text-to-image"`

- **`prompt`** (`string`, _required_):
  Text prompt describing the image to generate. Maximum context length: 32,000 tokens.

- **`size`** (`string`, _optional_):
  Image dimensions in width*height format (e.g., 1024*1024, 1280*720). Minimum 768. The product of width × height must not exceed 1,048,576.
  - Default: `"1024*1024"`
  - Min: 768
  - Max: 1360

- **`enable_base64_output`** (`boolean`, _optional_):
  If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.
  - Default: `false`

- **`enable_sync_mode`** (`boolean`, _optional_):
  If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "model": "microsoft/mai-image-2.5-pro/text-to-image",
  "prompt": ""
}
```


**Full Example**:

```json
{
  "model": "microsoft/mai-image-2.5-pro/text-to-image",
  "prompt": "",
  "size": "1024*1024",
  "enable_base64_output": false,
  "enable_sync_mode": false
}
```


### Output Schema

The API returns the following output format:


- **`code`** (`integer`, _optional_):
  HTTP status code of the response.

- **`message`** (`string`, _optional_):
  Human-readable message; non-empty on failure.

- **`data`** (`object`, _optional_):
  - Properties:
    - **`id`** (`string`, _optional_):
      Unique identifier for the prediction.

    - **`model`** (`string`, _optional_):
      Model ID used for the prediction.

    - **`outputs`** (`array[string]`, _optional_):
      Array of URLs to the generated content. Null when status is not completed.

    - **`urls`** (`object`, _optional_):
      Object containing related API endpoints.
      - Properties:
        - **`get`** (`string`, _optional_):
          URL to poll for the prediction result.


    - **`status`** (`string`, _optional_):
      Status of the task: created, processing, completed, timeout, or failed.

    - **`created_at`** (`string`, _optional_):
      ISO timestamp of when the request was created (e.g., "2023-04-01T12:34:56.789Z").

    - **`error`** (`string`, _optional_):
      Error message if the task failed, empty string otherwise.

    - **`error_code`** (`integer`, _optional_):
      Error code if the task failed.

    - **`executionTime`** (`number`, _optional_):
      Total execution time in milliseconds.

    - **`timings`** (`object`, _optional_):
      Detailed timing breakdown.
      - Properties:
        - **`inference`** (`number`, _optional_):
          Inference time in milliseconds.





**Example Response**:

```json
{
  "code": 0,
  "message": "",
  "data": {
    "id": "",
    "model": "",
    "outputs": [
      ""
    ],
    "urls": {
      "get": ""
    },
    "status": "",
    "created_at": "",
    "error": "",
    "error_code": 0,
    "executionTime": 0,
    "timings": {
      "inference": 0
    }
  }
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "microsoft/mai-image-2.5-pro/text-to-image",
  "prompt": "",
  "size": "1024*1024",
  "enable_base64_output": false,
  "enable_sync_mode": false
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/microsoft/mai-image-2.5-pro/text-to-image)

A stylish male streetwear model captured in a dynamic mid-air dance pose, one knee lifted high, body slightly twisted, arms extended with powerful movement, wearing a white mesh tank top, oversized black athletic shorts, white crew socks, white sneakers, black gloves, futuristic blue sunglasses and a silver chain necklace. Athletic physique, braided hair, confident and energetic attitude. Minimalist cool-gray studio background, soft diffused lighting, subtle shadows, clean editorial composition. High-end sportswear campaign, contemporary street fashion, cinematic fashion photography, dynamic composition, realistic skin texture, detailed fabric mesh, crisp sneaker details, subtle motion blur, dramatic yet clean lighting, premium commercial aesthetic, ultra realistic, 4K, full body, high detail.

加载中...

MAI-Image-2.5-Pro Text-to-Image

MAI-Image-2.5-Pro is Microsoft AI's highest-fidelity image model to date — a text-to-image generation model built for work where quality is the top priority. It uses a diffusion-based generative approach that progressively refines the image, producing strong alignment between the input text and the generated output. Compared with the standard MAI-Image-2.5, the Pro tier is tuned for robust object consistency, stronger visual reasoning, and deeper world knowledge, which makes it especially reliable on visually dense, multi-object scenes and on prompts that leave details to be inferred.

Released in public preview on July 23, 2026 (model version 2026-06-19), it is the premium tier of the MAI-Image-2.5 family, alongside the balanced base model and the cost-efficient Flash variant.

Key Capabilities

Object consistency across complex scenes — Objects retain the same identity, materials, proportions, markings, and orientation throughout a visually dense composition.
Character consistency across views and moments — A person or character remains recognizably the same across poses, camera angles, expressions, clothing, and lighting conditions.
Material and physical-property accuracy — Materials look and behave according to their real-world properties, including reflection, translucency, weight, texture, and deformation.
Spatial and geometric reasoning — Objects are placed coherently in three-dimensional space, with credible scale, perspective, occlusion, and structural relationships.
Photorealistic image synthesis — Realistic imagery with consistent visual structure, natural lighting, accurate skin tones, depth, and texture.
High-fidelity portraits — Expressive, natural-looking portraits with accurate facial structure, lighting, and skin texture.
Accurate in-image text rendering — A standout strength of the 2.5 generation: legible, correctly spelled text in labels, posters, packaging, and signage.
World knowledge — Understands cultural references, real-world objects, and complex concepts, so vague or shorthand instructions still resolve into coherent scenes.
Product, branding & commercial design — Design-aware output suitable for product imagery, marketing visuals, brand assets, and commercial creative workflows.

Request Parameters

Parameter	Type	Required	Default	Description
`model`	string	Yes	`microsoft/mai-image-2.5-pro/text-to-image`	Model name.
`prompt`	string	Yes	—	Text prompt describing the image to generate. Maximum context length: 32,000 tokens.
`size`	string	No	`1024*1024`	Image dimensions in `widthheight` format (e.g., `10241024`, `1280*720`). Each dimension is a minimum of 768 and a maximum of 1360; the product of width × height must fall between 589,824 and 1,048,576.
`enable_base64_output`	boolean	No	`false`	If enabled, the output is returned as a BASE64 string instead of a URL. Available through the API only.
`enable_sync_mode`	boolean	No	`false`	If `true`, the request waits for the result to be generated and uploaded before returning, so the result arrives directly in the response. Available through the API only.

Because the total pixel budget is capped rather than the shape, either dimension can exceed 1024 as long as the product stays within the limit — which is how non-square aspect ratios such as 1280*720 are expressed.

Response

A generation request returns a prediction object with a status of created, processing, completed, timeout, or failed. Poll the returned urls.get endpoint (or use enable_sync_mode) until the task completes; data.outputs then holds the array of generated image URLs, or BASE64 strings when enable_base64_output is set. The response also carries has_nsfw_contents flags per output, executionTime, and a timings.inference breakdown in milliseconds.

Pricing

Pricing for this model has two components: the input text tokens in the prompt, and a fixed per-image output fee.

SKU	Description	Unit Price
`sku_input_1m_token`	Price per 1M input (prompt) tokens	$5.00
`sku_output_image`	Fixed fee per generated image	$0.12

Pricing Formula

cost = countTokens(prompt) / 1,000,000 × $5.00 + $0.12

For typical prompts of a few hundred tokens the token component is negligible, so the effective cost is approximately $0.12 per generated image.

Examples

Prompt Length	Token Count	Token Cost	Output Image Fee	Total
Short	50	~$0.000250	$0.12	~$0.1203
Medium	500	~$0.002500	$0.12	~$0.1225
Long	2,000	~$0.010000	$0.12	~$0.1300

Best Use Cases

Hero and campaign imagery — Flagship marketing visuals where fidelity and material realism matter more than cost per image.
Complex multi-object scenes — Interiors, storefronts, table-top spreads, and crowded compositions that require every object to stay consistent.
Character-driven series — Storyboards, comics, and campaign sets where the same person or character must recur across shots.
Product & packaging visualization — Product renders that need accurate reflections, translucency, and surface behavior.
Signage, posters & packaging — Designs that depend on legible, correctly rendered in-image text.
Concept art & production design — Translating abstract or shorthand briefs into coherent, richly detailed visuals.

Pro Tips

Lead with the subject, then the environment, then the style, lighting, and mood — the model resolves prompts in roughly that hierarchy.
Name materials explicitly ("brushed aluminum", "frosted glass", "wet asphalt") to take advantage of the model's material-property accuracy.
For in-image text, keep the inscription short and quote it exactly in the prompt.
Specify camera language (focal length, angle, depth of field) when you want photographic realism rather than illustration.
For recurring characters, repeat the same descriptive block verbatim across requests to help identity carry over.
Pick a size whose aspect ratio matches the deliverable — portrait for people, landscape for scenes — while staying inside the total pixel budget.

Technical Specifications

Spec	Value
Model Developer	Microsoft AI
Model Version	`2026-06-19`
Release Date	July 23, 2026 (public preview)
Architecture	Diffusion-based generative model
Input	Text prompt (natural language)
Output	PNG image (URL, or BASE64 when requested)
Max Prompt Length	32,000 tokens
Resolution Range	768–1360 px per dimension; 589,824–1,048,576 total pixels
Default Resolution	1024×1024
Supported Languages	English (primary)

Responsible Use

Despite data filtering and system-level content classifiers, image generation models can still produce unexpected or harmful output. Apply content safety mitigations appropriate to your use case, respect copyright and trademark when prompting, and disclose that images are AI-generated when publishing them.

MAI-Image-2.5-Pro Edit — The same Pro model driving image-to-image editing.
MAI-Image-2.5 Text-to-Image — The balanced base tier, tuned for surgical edits and consistency.
MAI-Image-2.5-Flash Text-to-Image — Faster, lower-cost text-to-image variant.

MAI-Image 2.5 Pro Text-to-Image API by MICROSOFT

输入

输出

参数

代码示例

安装

认证

HTTP 请求头

提交请求

提交请求

请求体

响应

检查状态

轮询示例

状态值

完成响应

上传文件

上传示例

响应

Input Schema

请求体示例

Output Schema

响应示例

Atlas Cloud Skills

支持的客户端

安装

设置 API Key

功能

MCP Server

支持的客户端

安装

配置

可用工具

API Schema

LLM 友好的提示词模板

MAI-Image-2.5-Pro Text-to-Image

Key Capabilities

Request Parameters

Response

Pricing

Pricing Formula

Examples

Best Use Cases

Pro Tips

Technical Specifications

Responsible Use

Related Models

探索类似模型

MAI-Image-2.6-Flash Text-to-image

MAI-Image-2.6-Flash Edit

MAI-Image-2.6 Text-to-image

MAI-Image-2.6 Edit

MAI-Image-2.5-Pro Edit

MAI-Image-2.5-Flash Edit

MAI-Image-2.5-Flash Text-to-image

MAI-Image-2.5 Edit

MAI-Image-2.5 Text-to-image

GPT Image 2.5 Sunburst Text-to-Image

GPT Image 2.5 Sunburst Edit

GPT Image 2.5 Flare Text-to-Image

GPT Image 2.5 Flare Edit

Openai GPT Image 2 Text-to-Image

Openai GPT Image 2 Edit

GPT Image 2.5 Flare Developer Edit

一个 API，畅享全模态 AI。

输入

输出

参数

代码示例

安装

认证

HTTP 请求头

提交请求

提交请求

请求体

响应

检查状态

轮询示例

状态值

完成响应