# Claude Opus 4.5 - Core.Today AI API

> Anthropic's most powerful model for highly complex tasks. Exceptional at research, analysis, and creative projects requiring deep expertise.

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

## Model Specifications
- **Context Window**: 200K tokens
- **Max Output**: 33K 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**: 9,290 credits ($6.19)
- **Output Tokens**: 46,450 credits ($30.97)
- **Cached Tokens**: 929 credits ($0.62)

## Features
- 200K context window
- 32K max output tokens
- Vision capabilities
- Deepest reasoning
- Expert-level analysis
- Creative excellence

## Use Cases
- Advanced research
- Expert-level writing
- Complex strategy
- Deep analysis
- Creative projects
- High-stakes decisions

## 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
- **max_tokens**: integer - Maximum tokens in response (up to 32768)

### Optional
- **system**: string - System prompt
- **temperature**: float (default: 1.0) - Sampling temperature (0-1)

## Examples

### Research Analysis
Deep research analysis
```json
{
  "model": "claude-opus-4-5",
  "max_tokens": 4000,
  "system": "You are a world-class researcher with deep expertise across multiple domains.",
  "messages": [
    {
      "role": "user",
      "content": "Provide a comprehensive analysis of recent advances in quantum error correction, including implications for practical quantum computing."
    }
  ]
}
```

## 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
- Best for tasks requiring deepest reasoning
- Use for high-stakes, complex decisions
- More expensive but highest quality
- Consider Claude Sonnet 4.5 for most tasks first

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