模型能力

流式输出

所有具有文本输出能力的模型（如聊天、图像理解等）都支持流式输出。而具有图像输出能力的模型（如图像生成）不支持流式输出。

流式输出使用服务器发送事件 (SSE)，允许服务器在事件流中发送内容的增量。

流式响应有助于提供实时反馈，通过在文本生成时立即显示内容来增强用户交互。

要启用流式输出，您必须在请求中设置 "stream": true。

[!警告]

当使用推理模型进行流式输出时，您可能需要手动覆盖请求超时，以避免过早关闭连接。

import os

from xai_sdk import Client
from xai_sdk.chat import user, system

client = Client(
    api_key=os.getenv('XAI_API_KEY'),
    timeout=3600, # Override default timeout with longer timeout for reasoning models
)

chat = client.chat.create(model="grok-4.5")
chat.append(
    system("You are Grok, a helpful and maximally truthful AI built by xAI."),
)
chat.append(
    user("Explain how neural networks learn in two sentences.")
)

for response, chunk in chat.stream():
    print(chunk.content, end="", flush=True) # Each chunk's content
    print(response.content, end="", flush=True) # The response object auto-accumulates the chunks

print(response.content) # The full response

import os
import httpx
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("XAI_API_KEY"),
    base_url="https://api.x.ai/v1",
    timeout=httpx.Timeout(3600.0) # Timeout after 3600s for reasoning models
)

stream = client.chat.completions.create(
    model="grok-4.5",
    messages=[
        {"role": "system", "content": "You are Grok, a helpful and maximally truthful AI built by xAI."},
        {"role": "user", "content": "Explain how neural networks learn in two sentences."},
    ],
    stream=True # Set streaming here
)

for chunk in stream:
    print(chunk.choices[0].delta.content, end="", flush=True)

import OpenAI from "openai";
const openai = new OpenAI({
    apiKey: "<api key>",
    baseURL: "https://api.x.ai/v1",
    timeout: 360000, // Timeout after 3600s for reasoning models
});

const stream = await openai.chat.completions.create({
    model: "grok-4.5",
    messages: [
        { role: "system", content: "You are Grok, a helpful and maximally truthful AI built by xAI." },
        {
            role: "user",
            content: "Explain how neural networks learn in two sentences.",
        }
    ],
    stream: true
});

for await (const chunk of stream) {
    console.log(chunk.choices[0].delta.content);
}

import { xai } from '@ai-sdk/xai';
import { streamText } from 'ai';

const result = streamText({
  model: xai.responses('grok-4.5'),
  system:
    "You are Grok, a helpful and maximally truthful AI built by xAI.",
  prompt: 'Explain how neural networks learn in two sentences.',
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

curl https://api.x.ai/v1/chat/completions \\
-H "Content-Type: application/json" \\
-H "Authorization: Bearer $XAI_API_KEY" \\
-m 3600 \\
-d '{
    "messages": [
        {
            "role": "system",
            "content": "You are Grok, a helpful and maximally truthful AI built by xAI."
        },
        {
            "role": "user",
            "content": "Explain how neural networks learn in two sentences."
        }
    ],
    "model": "grok-4.5",
    "stream": true
}'

您将获得如下事件流：

data: {
    "id":"<completion_id>","object":"chat.completion.chunk","created":<creation_time>,
    "model":"grok-4.5",
    "choices":[{"index":0,"delta":{"content":"Ah","role":"assistant"}}],
    "usage":{"prompt_tokens":41,"completion_tokens":1,"total_tokens":42,
    "prompt_tokens_details":{"text_tokens":41,"audio_tokens":0,"image_tokens":0,"cached_tokens":0}},
    "system_fingerprint":"fp_xxxxxxxxxx"
}

data: {
    "id":"<completion_id>","object":"chat.completion.chunk","created":<creation_time>,
    "model":"grok-4.5",
    "choices":[{"index":0,"delta":{"content":",","role":"assistant"}}],
    "usage":{"prompt_tokens":41,"completion_tokens":2,"total_tokens":43,
    "prompt_tokens_details":{"text_tokens":41,"audio_tokens":0,"image_tokens":0,"cached_tokens":0}},
    "system_fingerprint":"fp_xxxxxxxxxx"
}

data: [DONE]

建议您使用客户端 SDK 来解析事件流。

Python/JavaScript 中的流式响应示例：

Neural networks learn by adjusting connection weights to minimize prediction error. Through backpropagation, they propagate gradients backward through layers so each weight updates in the direction that improves accuracy on training data.