# Claude Sonnet 4.5 - Core.Today AI API

> Anthropic's most intelligent and capable Sonnet model. Best-in-class for complex reasoning, nuanced understanding, and coding tasks with exceptional instruction following.

- **Provider**: Anthropic
- **Model ID**: claude-sonnet-4-5
- **Category**: LLM
- **Credits**: 4 per 1K tokens (avg)
- **Speed**: Fast
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 200K tokens
- **Max Output**: 16K tokens
- **Training Cutoff**: 2025-04
- **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
- Computer use
- Superior code generation
- Exceptional instruction following

## Use Cases
- Complex document analysis
- Code generation and review
- Research and analysis
- Technical writing
- Agentic workflows
- Data extraction

## 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-4-5) - Model identifier
- **max_tokens**: integer - Maximum tokens in response (required, up to 16384)

### Optional
- **system**: string - System prompt for setting behavior
- **temperature**: float (default: 1.0) - Sampling temperature (0-1)
- **stream**: boolean (default: false) - Enable streaming responses
- **tools**: array - List of tools the model can use

## Examples

### Document Analysis
Analyze complex documents
```json
{
  "model": "claude-sonnet-4-5",
  "max_tokens": 4000,
  "system": "You are an expert analyst. Provide detailed, structured analysis.",
  "messages": [
    {
      "role": "user",
      "content": "Analyze the key themes and implications of this research paper: [paper text]"
    }
  ]
}
```

### Code Generation
Generate production-quality code
```json
{
  "model": "claude-sonnet-4-5",
  "max_tokens": 4000,
  "messages": [
    {
      "role": "user",
      "content": "Create a TypeScript React component for a data table with sorting, filtering, and pagination. Use modern best practices."
    }
  ],
  "temperature": 0.3
}
```

### Tool Use
Use tools/functions with Claude
```json
{
  "model": "claude-sonnet-4-5",
  "max_tokens": 1000,
  "messages": [
    {
      "role": "user",
      "content": "Look up the current stock price of Apple."
    }
  ],
  "tools": [
    {
      "name": "get_stock_price",
      "description": "Get the current stock price for a given symbol",
      "input_schema": {
        "type": "object",
        "properties": {
          "symbol": {
            "type": "string",
            "description": "Stock ticker symbol"
          }
        },
        "required": [
          "symbol"
        ]
      }
    }
  ]
}
```

## 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
- max_tokens is required - always specify it
- Use system prompt for persona and constraints
- XML tags in prompts improve structured responses
- Temperature max is 1.0 (not 2.0 like OpenAI)
- Excellent at following complex, multi-step instructions
- Use caching for repeated context to reduce costs

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