请求体 modelstring（必选）模型名称。支持的模型：gui-plus。messagesarray（必选）传递给大模型的上下文，按对话顺序排列。
System Messageobject（可选）系统消息，用于设定大模型的角色、语气、任务目标或约束条件等。一般放在messages数组的第一位。
contentstring（必选）系统指令，用于明确模型的角色、行为规范、回答风格和任务约束等。rolestring（必选）系统消息的角色，固定为system。 object（必选）用户消息。
contentarray（必选）消息内容。
typestring（必选）可选值：
-
text
输入文本时需设为text。
-
image_url
输入图片时需设为image_url。
textstring（可选）输入的文本。当type为text时，是必选参数。image_urlobject输入的图片信息。当type为image_url时是必选参数。
url string（必选）图片的 URL或 Base64 Data URL。传入本地文件请参考传入本地文件。 integer（可选）用于设定输入图像的最小像素阈值，单位为像素。当输入图像像素小于min_pixels时，会将图像进行放大，直到总像素高于min_pixels。默认值和最小值均为 3136 。max_pixelsinteger（可选）用于设定输入图像的最大像素阈值，单位为像素。当输入图像像素在[min_pixels, max_pixels]区间内时，模型会按原图进行识别。当输入图像像素大于max_pixels时，会将图像进行缩小，直到总像素低于max_pixels。默认值和最大值和vl_high_resolution_images的取值有关： string（必选）用户消息的角色，固定为user。 object（可选）模型的回复。通常用于在多轮对话中作为上下文回传给模型。
contentstring（必选）模型回复的文本内容。rolestring（必选）助手消息的角色，固定为assistant。 boolean（可选） 默认值为 false是否以流式方式输出回复。可选值：
false：等待模型生成完整回复后一次性返回。true：模型边生成边返回数据块。客户端需逐块读取，以还原完整回复。 stream_optionsobject（可选）流式输出的配置项，仅在 stream 为 true 时生效。
include_usageboolean（可选）默认值为 false是否在最后一个数据块包含Token消耗信息。可选值： integer（可选）用于限制模型输出的最大 Token 数。若生成内容超过此值，响应将被截断。默认值与最大值均为模型的最大输出长度，请参见模型选型。vl_high_resolution_imagesboolean（可选）默认值为false是否将输入图像的像素上限提升至 16384 Token 对应的像素值。
vl_high_resolution_images为true，使用固定分辨率策略，像素上限固定为12845056，忽略 max_pixels 设置，超过此分辨率时会将图像总像素缩小至此上限内。vl_high_resolution_images为false，像素上限由max_pixels决定，输入图像的像素超过max_pixels会将图像缩小至max_pixels内。模型的默认像素上限即max_pixels的默认值。 enable_thinking boolean （可选）使用混合思考（回复前既可思考也可不思考）模型时，是否开启思考模式。在界面交互系列模型中，仅gui-plus-2026-02-26为混合思考模型。相关文档：视觉推理可选值：
-
true：开启
开启后，思考内容将通过reasoning_content字段返回。
-
false：不开启
该参数非OpenAI标准参数。通过 Python SDK调用时，请放入 extra_body 对象中。配置方式为：extra_body={"enable_thinking": xxx}。
seedinteger（可选）随机数种子。用于确保在相同输入和参数下生成结果可复现。若调用时传入相同的 seed 且其他参数不变，模型将尽可能返回相同结果。取值范围：[0,2 31 −1]。temperaturefloat（可选）默认值为0.01采样温度，控制模型生成文本的多样性。temperature越高，生成的文本更多样，反之，生成的文本更确定。取值范围： [0, 2)temperature与top_p均可以控制生成文本的多样性，建议只设置其中一个值。top_pfloat（可选）默认值为0.01核采样的概率阈值，控制模型生成文本的多样性。top_p越高，生成的文本更多样。反之，生成的文本更确定。取值范围：（0,1.0]temperature与top_p均可以控制生成文本的多样性，建议只设置其中一个值。top_kinteger（可选）默认值为1生成过程中采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个Token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。取值为None或当top_k大于100时，表示不启用top_k策略，此时仅有top_p策略生效。取值需要大于或等于0。该参数非OpenAI标准参数。通过 Python SDK调用时，请放入 extra_body 对象中，配置方式为：extra_body={"top_k": xxx}；通过 Node.js SDK 或 HTTP 方式调用时，请作为顶层参数传递。repetition_penaltyfloat（可选）默认值为1.0模型生成时连续序列中的重复度。提高repetition_penalty时可以降低模型生成的重复度，1.0表示不做惩罚。该参数对模型效果影响较大，建议保持默认值。presence_penalty float（可选）控制模型生成文本时的内容重复度。默认值为1.5取值范围：[-2.0, 2.0]。正值降低重复度，负值增加重复度。在创意写作或头脑风暴等需要多样性、趣味性或创造力的场景中，建议调高该值；在技术文档或正式文本等强调一致性与术语准确性的场景中，建议调低该值。
如果参数值是正数，模型将对目前文本中已存在的Token施加一个惩罚值（惩罚值与文本出现的次数无关），减少这些Token重复出现的几率，从而减少内容重复度，增加用词多样性。
提示词：把这句话翻译成中文“This movie is good. The plot is good, the acting is good, the music is good, and overall, the whole movie is just good. It is really good, in fact. The plot is so good, and the acting is so good, and the music is so good.”参数值为2.0：这部电影很好。剧情很棒，演技棒，音乐也非常好听，总的来说，整部电影都好得不得了。实际上它真的很优秀。剧情非常精彩，演技出色，音乐也是那么的动听。参数值为0.0：这部电影很好。剧情好，演技好，音乐也好，总的来说，整部电影都很好。事实上，它真的很棒。剧情非常好，演技也非常出色，音乐也同样优秀。参数值为-2.0：这部电影很好。情节很好，演技很好，音乐也很好，总的来说，整部电影都很好。实际上，它真的很棒。情节非常好，演技也非常好，音乐也非常好。 string 或 array（可选）用于指定停止词。当模型生成的文本中出现stop 指定的字符串或token_id时，生成将立即终止。可传入敏感词以控制模型的输出。
stop为数组时，不可将token_id和字符串同时作为元素输入，比如不可以指定为["你好",104307]。
| import os
from openai import OpenAI
system_prompt = """# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{"type": "function", "function": {"name": "computer_use", "description": "Use a mouse and keyboard to interact with a computer, and take screenshots.\\n* This is an interface to a desktop GUI. You do not have access to a terminal or applications menu. You must click on desktop icons to start applications.\\n* Some applications may take time to start or process actions, so you may need to wait and take successive screenshots to see the results of your actions. E.g. if you click on Firefox and a window doesn't open, try wait and taking another screenshot.\\n* The screen's resolution is 1000x1000.\\n* Make sure to click any buttons, links, icons, etc with the cursor tip in the center of the element. Don't click boxes on their edges unless asked.", "parameters": {"properties": {"action": {"description": "The action to perform. The available actions are:\\n* `key`: Performs key down presses on the arguments passed in order, then performs key releases in reverse order.\\n* `type`: Type a string of text on the keyboard.\\n* `mouse_move`: Move the cursor to a specified (x, y) pixel coordinate on the screen.\\n* `left_click`: Click the left mouse button at a specified (x, y) pixel coordinate on the screen.\\n* `left_click_drag`: Click and drag the cursor to a specified (x, y) pixel coordinate on the screen.\\n* `right_click`: Click the right mouse button at a specified (x, y) pixel coordinate on the screen.\\n* `middle_click`: Click the middle mouse button at a specified (x, y) pixel coordinate on the screen.\\n* `double_click`: Double-click the left mouse button at a specified (x, y) pixel coordinate on the screen.\\n* `triple_click`: Triple-click the left mouse button at a specified (x, y) pixel coordinate on the screen (simulated as double-click since it's the closest action).\\n* `scroll`: Performs a scroll of the mouse scroll wheel.\\n* `hscroll`: Performs a horizontal scroll (mapped to regular scroll).\\n* `wait`: Wait specified seconds for the change to happen.\\n* `terminate`: Terminate the current task and report its completion status.\\n* `answer`: Answer a question.\\n* `interact`: Resolve the blocking window by interacting with the user.", "enum": ["key", "type", "mouse_move", "left_click", "left_click_drag", "right_click", "middle_click", "double_click", "triple_click", "scroll", "hscroll", "wait", "terminate", "answer", "interact"], "type": "string"}, "keys": {"description": "Required only by `action=key`.", "type": "array"}, "text": {"description": "Required only by `action=type`, `action=answer` and `action=interact`.", "type": "string"}, "coordinate": {"description": "(x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by `action=mouse_move` and `action=left_click_drag`.", "type": "array"}, "pixels": {"description": "The amount of scrolling to perform. Positive values scroll up, negative values scroll down. Required only by `action=scroll` and `action=hscroll`.", "type": "number"}, "time": {"description": "The seconds to wait. Required only by `action=wait`.", "type": "number"}, "status": {"description": "The status of the task. Required only by `action=terminate`.", "type": "string", "enum": ["success", "failure"]}}, "required": ["action"], "type": "object"}}}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
# Response format
Response format for every step:
1) Action: a short imperative describing what to do in the UI.
2) A single <tool_call>...</tool_call> block containing only the JSON: {"name": <function-name>, "arguments": <args-json-object>}.
Rules:
- Output exactly in the order: Action, <tool_call>.
- Be brief: one for Action.
- Do not output anything else outside those two parts.
- If finishing, use action=terminate in the tool call."""
messages = [
{
"role": "system",
"content": system_prompt
},
{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": "https://img.alicdn.com/imgextra/i2/O1CN016iJ8ob1C3xP1s2M6z_!!6000000000026-2-tps-3008-1758.png"}},
{"type": "text", "text": "帮我打开浏览器"}
]
}
]
client = OpenAI(
# 若没有配置环境变量，请用阿里云百炼API Key将下行替换为：api_key="sk-xxx",
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
model="gui-plus-2026-02-26",
messages=messages,
extra_body={"vl_high_resolution_images": True}
)
print(completion.choices[0].message.content)
import OpenAI from "openai";
const systemPrompt = `# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{"type": "function", "function": {"name": "computer_use", "description": "Use a mouse and keyboard to interact with a computer, and take screenshots.\\n* This is an interface to a desktop GUI. You do not have access to a terminal or applications menu. You must click on desktop icons to start applications.\\n* Some applications may take time to start or process actions, so you may need to wait and take successive screenshots to see the results of your actions. E.g. if you click on Firefox and a window doesn't open, try wait and taking another screenshot.\\n* The screen's resolution is 1000x1000.\\n* Make sure to click any buttons, links, icons, etc with the cursor tip in the center of the element. Don't click boxes on their edges unless asked.", "parameters": {"properties": {"action": {"description": "The action to perform. The available actions are:\\n* \`key\`: Performs key down presses on the arguments passed in order, then performs key releases in reverse order.\\n* \`type\`: Type a string of text on the keyboard.\\n* \`mouse_move\`: Move the cursor to a specified (x, y) pixel coordinate on the screen.\\n* \`left_click\`: Click the left mouse button at a specified (x, y) pixel coordinate on the screen.\\n* \`left_click_drag\`: Click and drag the cursor to a specified (x, y) pixel coordinate on the screen.\\n* \`right_click\`: Click the right mouse button at a specified (x, y) pixel coordinate on the screen.\\n* \`middle_click\`: Click the middle mouse button at a specified (x, y) pixel coordinate on the screen.\\n* \`double_click\`: Double-click the left mouse button at a specified (x, y) pixel coordinate on the screen.\\n* \`triple_click\`: Triple-click the left mouse button at a specified (x, y) pixel coordinate on the screen (simulated as double-click since it's the closest action).\\n* \`scroll\`: Performs a scroll of the mouse scroll wheel.\\n* \`hscroll\`: Performs a horizontal scroll (mapped to regular scroll).\\n* \`wait\`: Wait specified seconds for the change to happen.\\n* \`terminate\`: Terminate the current task and report its completion status.\\n* \`answer\`: Answer a question.\\n* \`interact\`: Resolve the blocking window by interacting with the user.", "enum": ["key", "type", "mouse_move", "left_click", "left_click_drag", "right_click", "middle_click", "double_click", "triple_click", "scroll", "hscroll", "wait", "terminate", "answer", "interact"], "type": "string"}, "keys": {"description": "Required only by \`action=key\`.", "type": "array"}, "text": {"description": "Required only by \`action=type\`, \`action=answer\` and \`action=interact\`.", "type": "string"}, "coordinate": {"description": "(x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by \`action=mouse_move\` and \`action=left_click_drag\`.", "type": "array"}, "pixels": {"description": "The amount of scrolling to perform. Positive values scroll up, negative values scroll down. Required only by \`action=scroll\` and \`action=hscroll\`.", "type": "number"}, "time": {"description": "The seconds to wait. Required only by \`action=wait\`.", "type": "number"}, "status": {"description": "The status of the task. Required only by \`action=terminate\`.", "type": "string", "enum": ["success", "failure"]}}, "required": ["action"], "type": "object"}}}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
# Response format
Response format for every step:
1) Action: a short imperative describing what to do in the UI.
2) A single <tool_call>...</tool_call> block containing only the JSON: {"name": <function-name>, "arguments": <args-json-object>}.
Rules:
- Output exactly in the order: Action, <tool_call>.
- Be brief: one for Action.
- Do not output anything else outside those two parts.
- If finishing, use action=terminate in the tool call.`;
const client = new OpenAI({
apiKey: process.env.DASHSCOPE_API_KEY,
baseURL: "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
});
const messages = [
{
role: "system",
content: systemPrompt,
},
{
role: "user",
content: [
{
type: "image_url",
image_url: {
url: "https://img.alicdn.com/imgextra/i2/O1CN016iJ8ob1C3xP1s2M6z_!!6000000000026-2-tps-3008-1758.png",
},
},
{ type: "text", text: "帮我打开浏览器" },
],
},
];
const completion = await client.chat.completions.create({
model: "gui-plus-2026-02-26",
messages: messages,
extra_body: { vl_high_resolution_images: true },
});
console.log(completion.choices[0].message.content);
curl -X POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gui-plus-2026-02-26",
"messages": [
{
"role": "system",
"content": "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"computer_use\", \"description\": \"Use a mouse and keyboard to interact with a computer, and take screenshots.\\n* This is an interface to a desktop GUI. You do not have access to a terminal or applications menu. You must click on desktop icons to start applications.\\n* Some applications may take time to start or process actions, so you may need to wait and take successive screenshots to see the results of your actions. E.g. if you click on Firefox and a window doesn'\''t open, try wait and taking another screenshot.\\n* The screen'\''s resolution is 1000x1000.\\n* Make sure to click any buttons, links, icons, etc with the cursor tip in the center of the element. Don'\''t click boxes on their edges unless asked.\", \"parameters\": {\"properties\": {\"action\": {\"description\": \"The action to perform. The available actions are:\\n* `key`: Performs key down presses on the arguments passed in order, then performs key releases in reverse order.\\n* `type`: Type a string of text on the keyboard.\\n* `mouse_move`: Move the cursor to a specified (x, y) pixel coordinate on the screen.\\n* `left_click`: Click the left mouse button at a specified (x, y) pixel coordinate on the screen.\\n* `left_click_drag`: Click and drag the cursor to a specified (x, y) pixel coordinate on the screen.\\n* `right_click`: Click the right mouse button at a specified (x, y) pixel coordinate on the screen.\\n* `middle_click`: Click the middle mouse button at a specified (x, y) pixel coordinate on the screen.\\n* `double_click`: Double-click the left mouse button at a specified (x, y) pixel coordinate on the screen.\\n* `triple_click`: Triple-click the left mouse button at a specified (x, y) pixel coordinate on the screen (simulated as double-click since it'\''s the closest action).\\n* `scroll`: Performs a scroll of the mouse scroll wheel.\\n* `hscroll`: Performs a horizontal scroll (mapped to regular scroll).\\n* `wait`: Wait specified seconds for the change to happen.\\n* `terminate`: Terminate the current task and report its completion status.\\n* `answer`: Answer a question.\\n* `interact`: Resolve the blocking window by interacting with the user.\", \"enum\": [\"key\", \"type\", \"mouse_move\", \"left_click\", \"left_click_drag\", \"right_click\", \"middle_click\", \"double_click\", \"triple_click\", \"scroll\", \"hscroll\", \"wait\", \"terminate\", \"answer\", \"interact\"], \"type\": \"string\"}, \"keys\": {\"description\": \"Required only by `action=key`.\", \"type\": \"array\"}, \"text\": {\"description\": \"Required only by `action=type`, `action=answer` and `action=interact`.\", \"type\": \"string\"}, \"coordinate\": {\"description\": \"(x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by `action=mouse_move` and `action=left_click_drag`.\", \"type\": \"array\"}, \"pixels\": {\"description\": \"The amount of scrolling to perform. Positive values scroll up, negative values scroll down. Required only by `action=scroll` and `action=hscroll`.\", \"type\": \"number\"}, \"time\": {\"description\": \"The seconds to wait. Required only by `action=wait`.\", \"type\": \"number\"}, \"status\": {\"description\": \"The status of the task. Required only by `action=terminate`.\", \"type\": \"string\", \"enum\": [\"success\", \"failure\"]}}, \"required\": [\"action\"], \"type\": \"object\"}}}\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>\n\n# Response format\n\nResponse format for every step:\n1) Action: a short imperative describing what to do in the UI.\n2) A single <tool_call>...</tool_call> block containing only the JSON: {\"name\": <function-name>, \"arguments\": <args-json-object>}.\n\nRules:\n- Output exactly in the order: Action, <tool_call>.\n- Be brief: one for Action.\n- Do not output anything else outside those two parts.\n- If finishing, use action=terminate in the tool call."
},
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {
"url": "https://img.alicdn.com/imgextra/i2/O1CN016iJ8ob1C3xP1s2M6z_!!6000000000026-2-tps-3008-1758.png"
}
},
{
"type": "text",
"text": "帮我打开浏览器"
}
]
}
],
"vl_high_resolution_images": true
}'
{
"choices": [
{
"message": {
"content": "<tool_call>\n{\"name\": \"computer_use\", \"arguments\": {\"action\": \"left_click\", \"coordinate\": [2530, 314]}}\n</tool_call>",
"role": "assistant"
},
"finish_reason": "stop",
"index": 0,
"logprobs": null
}
],
"object": "chat.completion",
"usage": {
"prompt_tokens": 7750,
"completion_tokens": 36,
"total_tokens": 7786,
"prompt_tokens_details": {
"image_tokens": 6743,
"text_tokens": 1007
},
"completion_tokens_details": {
"text_tokens": 36
}
},
"created": 1773133741,
"system_fingerprint": null,
"model": "gui-plus",
"id": "chatcmpl-8b375016-abb8-9791-856c-74b2825c22d5"
}
import os
from openai import OpenAI
system_prompt = """# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{"type": "function", "function": {"name": "computer_use", "description": "Use a mouse and keyboard to interact with a computer, and take screenshots.\\n* This is an interface to a desktop GUI. You do not have access to a terminal or applications menu. You must click on desktop icons to start applications.\\n* Some applications may take time to start or process actions, so you may need to wait and take successive screenshots to see the results of your actions. E.g. if you click on Firefox and a window doesn't open, try wait and taking another screenshot.\\n* The screen's resolution is 1000x1000.\\n* Make sure to click any buttons, links, icons, etc with the cursor tip in the center of the element. Don't click boxes on their edges unless asked.", "parameters": {"properties": {"action": {"description": "The action to perform. The available actions are:\\n* `key`: Performs key down presses on the arguments passed in order, then performs key releases in reverse order.\\n* `type`: Type a string of text on the keyboard.\\n* `mouse_move`: Move the cursor to a specified (x, y) pixel coordinate on the screen.\\n* `left_click`: Click the left mouse button at a specified (x, y) pixel coordinate on the screen.\\n* `left_click_drag`: Click and drag the cursor to a specified (x, y) pixel coordinate on the screen.\\n* `right_click`: Click the right mouse button at a specified (x, y) pixel coordinate on the screen.\\n* `middle_click`: Click the middle mouse button at a specified (x, y) pixel coordinate on the screen.\\n* `double_click`: Double-click the left mouse button at a specified (x, y) pixel coordinate on the screen.\\n* `triple_click`: Triple-click the left mouse button at a specified (x, y) pixel coordinate on the screen (simulated as double-click since it's the closest action).\\n* `scroll`: Performs a scroll of the mouse scroll wheel.\\n* `hscroll`: Performs a horizontal scroll (mapped to regular scroll).\\n* `wait`: Wait specified seconds for the change to happen.\\n* `terminate`: Terminate the current task and report its completion status.\\n* `answer`: Answer a question.\\n* `interact`: Resolve the blocking window by interacting with the user.", "enum": ["key", "type", "mouse_move", "left_click", "left_click_drag", "right_click", "middle_click", "double_click", "triple_click", "scroll", "hscroll", "wait", "terminate", "answer", "interact"], "type": "string"}, "keys": {"description": "Required only by `action=key`.", "type": "array"}, "text": {"description": "Required only by `action=type`, `action=answer` and `action=interact`.", "type": "string"}, "coordinate": {"description": "(x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by `action=mouse_move` and `action=left_click_drag`.", "type": "array"}, "pixels": {"description": "The amount of scrolling to perform. Positive values scroll up, negative values scroll down. Required only by `action=scroll` and `action=hscroll`.", "type": "number"}, "time": {"description": "The seconds to wait. Required only by `action=wait`.", "type": "number"}, "status": {"description": "The status of the task. Required only by `action=terminate`.", "type": "string", "enum": ["success", "failure"]}}, "required": ["action"], "type": "object"}}}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
# Response format
Response format for every step:
1) Action: a short imperative describing what to do in the UI.
2) A single <tool_call>...</tool_call> block containing only the JSON: {"name": <function-name>, "arguments": <args-json-object>}.
Rules:
- Output exactly in the order: Action, <tool_call>.
- Be brief: one for Action.
- Do not output anything else outside those two parts.
- If finishing, use action=terminate in the tool call."""
messages = [
{
"role": "system",
"content": system_prompt
},
{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": "https://img.alicdn.com/imgextra/i2/O1CN016iJ8ob1C3xP1s2M6z_!!6000000000026-2-tps-3008-1758.png"}},
{"type": "text", "text": "帮我打开浏览器"}
]
}
]
client = OpenAI(
# 若没有配置环境变量，请用阿里云百炼API Key将下行替换为：api_key="sk-xxx",
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
model="gui-plus-2026-02-26",
messages=messages,
stream=True,
stream_options={"include_usage":True}
)
for chunk in completion:
print(chunk.model_dump_json())
|
