流式输出

设置 stream: true 时，Bitdeer AI API 会以 Server-Sent Events（SSE）逐段返回 token。流结束时发送 data: [DONE]。

支持的模型

所有文本生成模型均支持流式输出。

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api-inference.bitdeer.ai/v1",
    api_key="YOUR_API_KEY",
)

stream = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[{"role": "user", "content": "Write a short poem about clouds."}],
    max_tokens=256,
    stream=True,
)

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

JavaScript / TypeScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.BITDEER_API_KEY,
  baseURL: 'https://api-inference.bitdeer.ai/v1',
});

const stream = await client.chat.completions.create({
  model: 'deepseek-ai/DeepSeek-V4-Pro',
  messages: [{ role: 'user', content: 'Write a short poem about clouds.' }],
  max_tokens: 256,
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) process.stdout.write(content);
}

流式选项

设置 stream_options.include_usage: true 可在最后一个数据块中收到用量统计：

stream = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[{"role": "user", "content": "Hello"}],
    max_tokens=256,
    stream=True,
    stream_options={"include_usage": True},
)

[DONE] 前的最后一个 chunk 会包含完整的 usage 对象（prompt_tokens、completion_tokens、total_tokens）。

cURL

curl https://api-inference.bitdeer.ai/v1/chat/completions \
  -H "Authorization: Bearer $BITDEER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Pro",
    "messages": [{"role": "user", "content": "Write a short poem about clouds."}],
    "max_tokens": 256,
    "stream": true
  }'

响应中每一行以 data: 开头，后跟 JSON 片段，流以 data: [DONE] 结束。

支持的模型

Python

JavaScript / TypeScript

流式选项

cURL

本页目录