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

# Anthropic Streaming

> Real-time Server-Sent Events (SSE) stream using Anthropic Messages API.

The `/anthropic/v1/messages` endpoint supports native [Anthropic](https://www.anthropic.com/?utm_source=neosantara-docs\&utm_medium=referral) event-based token streaming, fully compatible with official Anthropic Python and TypeScript SDKs.

<CodeGroup>
  ```python Python (Anthropic SDK) icon="python" theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
  from anthropic import Anthropic
  import os

  client = Anthropic(
      base_url="https://api.neosantara.xyz/anthropic",
      api_key=os.environ["NEOSANTARA_API_KEY"]
  )

  with client.messages.stream(
      model="claude-sonnet-4-6",
      max_tokens=1024,
      messages=[{"role": "user", "content": "Write a guide to microservices architecture."}]
  ) as stream:
      for text in stream.text_stream:
          print(text, end="", flush=True)
  print()
  ```

  ```javascript TypeScript (Node.js) icon="js" theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
  import Anthropic from "@anthropic-ai/sdk";

  const client = new Anthropic({
    baseURL: "https://api.neosantara.xyz/anthropic",
    apiKey: process.env.NEOSANTARA_API_KEY,
  });

  const stream = await client.messages.stream({
    model: "claude-sonnet-4-6",
    max_tokens: 1024,
    messages: [{ role: "user", content: "Explain event-driven architecture." }],
  });

  for await (const event of stream) {
    if (
      event.type === "content_block_delta" &&
      event.delta.type === "text_delta"
    ) {
      process.stdout.write(event.delta.text);
    }
  }
  console.log();
  ```

  ```bash cURL icon="terminal" theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
  curl -N -X POST https://api.neosantara.xyz/anthropic/v1/messages \
    -H "x-api-key: $NEOSANTARA_API_KEY" \
    -H "anthropic-version: 2023-06-01" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "claude-sonnet-4-6",
      "max_tokens": 1024,
      "messages": [{"role": "user", "content": "Hello"}],
      "stream": true
    }'
  ```
</CodeGroup>

## Anthropic Streaming Event Sequence

Unlike OpenAI streams that transmit raw text deltas, Anthropic streams content block lifecycle events:

1. `message_start`: Initial message metadata (id, model, role).
2. `content_block_start`: Beginning of a new content block (text or thinking).
3. `content_block_delta`: Content chunk updates (`text_delta` or `thinking_delta`).
4. `content_block_stop`: Closes the current block.
5. `message_delta`: Trailing metadata (`stop_reason` and final token counts).
6. `message_stop`: Stream closing signal.

## Next Steps

| Task                   | Guide                                                         |
| :--------------------- | :------------------------------------------------------------ |
| Extended Thinking      | [Extended Thinking](/en/gateway/anthropic-messages/thinking)  |
| Anthropic Tool Use     | [Anthropic Tool Use](/en/gateway/anthropic-messages/tool-use) |
| Messages Specification | [Anthropic Messages](/en/gateway/anthropic-messages)          |


## Related topics

- [Anthropic Messages API](/en/gateway/anthropic-messages.md)
- [Streaming Responses](/en/gateway/chat-completions/streaming.md)
- [Anthropic Extended Thinking](/en/gateway/anthropic-messages/thinking.md)