Clade Model Inference

Anthropic Messages API — Streaming & Advanced Patterns

Overview

The Messages API is the only inference endpoint. Every Claude interaction goes through client.messages.create(). This skill covers streaming, system prompts, vision, and structured output.

Prerequisites

• Completed clade-install-auth
• Familiarity with clade-hello-world

Instructions

Step 1: Streaming Responses

import Anthropic from '@claude-ai/sdk';

const client = new Anthropic();

const stream = client.messages.stream({
  model: 'claude-sonnet-4-20250514',
  max_tokens: 1024,
  messages: [{ role: 'user', content: 'Write a haiku about TypeScript.' }],
});

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

const finalMessage = await stream.finalMessage();
console.log('\n\nTokens:', finalMessage.usage);

Step 2: Vision — Sending Images

const message = await client.messages.create({
  model: 'claude-sonnet-4-20250514',
  max_tokens: 1024,
  messages: [{
    role: 'user',
    content: [
      {
        type: 'image',
        source: {
          type: 'base64',
          media_type: 'image/png',
          data: fs.readFileSync('screenshot.png').toString('base64'),
        },
      },
      { type: 'text', text: 'Describe what you see in this image.' },
    ],
  }],
});

Step 3: JSON / Structured Output

const message = await client.messages.create({
  model: 'claude-sonnet-4-20250514',
  max_tokens: 1024,
  system: `Respond with valid JSON only. Schema: { "summary": string, "sentiment": "positive"|"negative"|"neutral", "confidence": number }`,
  messages: [{ role: 'user', content: 'Analyze: "This product exceeded my expectations!"' }],
});

const result = JSON.parse(message.content[0].text);
// { summary: "Very positive review", sentiment: "positive", confidence: 0.95 }

Python Streaming

import anthropic

client = anthropic.Anthropic()

with client.messages.stream(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Write a haiku about Python."}],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

print(f"\nTokens: {stream.get_final_message().usage}")

Output

• Non-streaming: Full Message object with content, usage, stop_reason
• Streaming events:
  • message_start — message metadata
  • content_block_start — new content block beginning
  • content_block_delta — incremental text (text_delta) or tool input (input_json_delta)
  • message_delta — final stop_reason and usage
  • message_stop — stream complete

Error Handling

Key Parameters

Examples

See Step 1 (streaming), Step 2 (vision with base64 images), and Step 3 (structured JSON output) above. Python streaming example included.

Resources

• Messages API
• Streaming
• Vision

Next Steps

See clade-embeddings-search for tool use and function calling patterns.