Streaming

Enable Streaming

{
  "model": "claude-sonnet-4-6",
  "messages": [{"role": "user", "content": "Write a poem"}],
  "stream": true
}

Response Format

Each chunk is a data: line:

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","choices":[{"delta":{"content":"Hello"},"index":0}]}

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","choices":[{"delta":{"content":" world"},"index":0}]}

data: [DONE]

Python Example

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.boundlessapi.com/v1",
)

stream = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Count to 5"}],
    stream=True,
)

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

TypeScript Example

const stream = await client.chat.completions.create({
  model: "claude-sonnet-4-6",
  messages: [{ role: "user", content: "Count to 5" }],
  stream: true,
});

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

Billing

Streaming requests are billed on total tokens when the stream completes, same as non-streaming.

If stream is interrupted client-side, you are billed for tokens generated up to cancellation.

Errors During Stream

Errors may appear as:

data: {"error": {"message": "...", "code": "..."}}

Handle in your stream parser. See Error Codes.

Related

• API Reference
• Quickstart