# Claude Sonnet 4 - Core.Today AI API

> Balanced Sonnet 4 model offering strong reasoning and coding abilities at an efficient price point. Ideal for everyday production workloads that need a good mix of speed and intelligence.

- **Provider**: Anthropic
- **Model ID**: claude-sonnet-4
- **Category**: LLM
- **Credits**: 3 per 1K tokens (avg)
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 200K tokens
- **Max Output**: 16K tokens
- **Training Cutoff**: 2025-03
- **Supported Formats**: text, markdown, xml
- **Compatible SDK**: Anthropic

### Capabilities
- Vision (image input)
- Function Calling
- Streaming
- System Prompt

### Token Pricing (per 1M tokens)
- **Input Tokens**: 5,574 credits ($3.72)
- **Output Tokens**: 27,870 credits ($18.58)
- **Cached Tokens**: 557.4 credits ($0.37)

## Features
- 200K context window
- 16K max output tokens
- Vision capabilities
- Function calling & tool use
- Balanced speed and intelligence
- Streaming support

## Use Cases
- Production chatbots
- Code generation and review
- Document analysis
- Data extraction
- Content generation
- Workflow automation

## API Endpoint

Base URL: https://api.core.today
Endpoint: POST /llm/anthropic/v1/messages

## Authentication
Header: Authorization: Bearer YOUR_API_KEY

Note: LLM endpoints use OpenAI-compatible format with Authorization Bearer token.

## Input Parameters

### Required
- **messages**: array - Array of message objects with role and content
- **model**: string (default: claude-sonnet-4) - Model identifier
- **max_tokens**: integer - Maximum tokens in response (required, up to 16384)

### Optional
- **temperature**: float (default: 1.0) - Sampling temperature (0-1)
- **stream**: boolean (default: false) - Enable streaming responses
- **system**: string - System prompt for setting behavior
- **top_p**: float (default: 0.999) - Nucleus sampling parameter (0-1)

## Examples

### General Conversation
Balanced conversation with Claude Sonnet 4
```json
{
  "model": "claude-sonnet-4",
  "max_tokens": 2000,
  "system": "You are a helpful assistant that provides clear and concise answers.",
  "messages": [
    {
      "role": "user",
      "content": "Explain the key differences between microservices and monolithic architecture, with pros and cons of each."
    }
  ]
}
```

### Code Review
Review and improve code
```json
{
  "model": "claude-sonnet-4",
  "max_tokens": 3000,
  "messages": [
    {
      "role": "user",
      "content": "Review this Python function for bugs, performance issues, and suggest improvements:\n\ndef process_data(items):\n    result = []\n    for item in items:\n        if item not in result:\n            result.append(item)\n    return sorted(result)"
    }
  ],
  "temperature": 0.3
}
```

## Response Format
```json
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Response text here"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 100,
    "completion_tokens": 50,
    "total_tokens": 150
  }
}
```

## Tips
- Good balance of cost and capability for production use
- max_tokens is required - always specify it
- Use system prompt for persona and constraints
- Temperature max is 1.0 (not 2.0 like OpenAI)
- Consider Sonnet 4.5 for tasks needing higher intelligence
- Great for high-volume production workloads

## Documentation
https://docs.anthropic.com/en/docs/about-claude/models