> ## Documentation Index
> Fetch the complete documentation index at: https://docs.qingbo.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Streaming

> Receive text generation results in real time over SSE

## Overview

Text generation endpoints support Server-Sent Events (SSE) streaming. Set `stream: true` to receive output token by token as it's generated.

## Streaming-Enabled Endpoints

* `/v1/chat/completions` — OpenAI compatible
* `/v1/messages` — Claude Messages
* `/v1/responses` — OpenAI Responses API

## Example

<CodeGroup>
  ```python Python theme={"system"}
  from openai import OpenAI

  client = OpenAI(
      base_url="https://www.qingbo.dev/v1",
      api_key="your-api-key"
  )

  stream = client.chat.completions.create(
      model="gpt-4o",
      messages=[{"role": "user", "content": "写一首短诗"}],
      stream=True
  )

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

  ```javascript JavaScript theme={"system"}
  import OpenAI from 'openai';

  const client = new OpenAI({
    baseURL: 'https://www.qingbo.dev/v1',
    apiKey: 'your-api-key'
  });

  const stream = await client.chat.completions.create({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: '写一首短诗' }],
    stream: true
  });

  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || '');
  }
  ```
</CodeGroup>

## SSE Data Format

Each chunk is a single `data: {json}` SSE event:

```
data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"你"},"index":0}]}

data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"好"},"index":0}]}

data: [DONE]
```

When the stream ends, you'll receive `data: [DONE]`.

## Final Frame Usage & Billing (cost)

The last data frame before `[DONE]` carries the usage and the charge of the call:

```
data: {"id":"chatcmpl-xxx","choices":[],"usage":{"prompt_tokens":12,"completion_tokens":8,"total_tokens":20,"cost":150}}

data: [DONE]
```

* `usage.cost` is the actual quota charged for this call (integer); use it for per-call reconciliation
* It is sent by default; explicitly passing `stream_options: {"include_usage": false}` disables it
* With the OpenAI SDK, the final chunk's `chunk.usage` contains this data