# Claude Opus 4.6 - Core.Today AI API

> Anthropic's most capable model. Delivers breakthrough performance in reasoning, coding, and complex analysis with enhanced safety and instruction following.

- **Provider**: Anthropic
- **Model ID**: claude-opus-4-6
- **Category**: LLM
- **Credits**: 5 per 1K tokens (avg)
- **Speed**: Medium
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 200K tokens
- **Max Output**: 32K tokens
- **Training Cutoff**: 2025-05
- **Supported Formats**: text, json, markdown
- **Compatible SDK**: Anthropic, OpenAI

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

### Token Pricing (per 1M tokens)
- **Input Tokens**: 9,290 credits ($6.19)
- **Output Tokens**: 46,450 credits ($30.97)

## Features
- Most capable Anthropic model
- 200K context window
- Enhanced reasoning and coding
- Superior instruction following
- Advanced safety features
- Streaming support

## Use Cases
- Complex research and analysis
- Advanced code generation
- Long-form content creation
- Multi-step reasoning tasks
- Enterprise-grade applications

## 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 (OpenAI format)

### Optional
- **temperature**: float (default: 1.0) - Sampling temperature (0-1)
- **max_tokens**: integer (default: 4096) - Maximum tokens in response (up to 32000)
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming

## Examples

### Complex Analysis
Deep analysis with Claude Opus 4.6
```json
{
  "model": "claude-opus-4-6",
  "messages": [
    {
      "role": "system",
      "content": "You are a research analyst with expertise in technology and economics."
    },
    {
      "role": "user",
      "content": "Provide a comprehensive analysis of how large language models are transforming software development practices, including potential risks and mitigation strategies."
    }
  ],
  "temperature": 0.7,
  "max_tokens": 4000
}
```

### Code Generation
Generate production-quality code
```json
{
  "model": "claude-opus-4-6",
  "messages": [
    {
      "role": "system",
      "content": "You are a senior software engineer. Write clean, well-tested code."
    },
    {
      "role": "user",
      "content": "Implement a rate limiter in Python using the sliding window algorithm with Redis backend."
    }
  ],
  "temperature": 0.3,
  "max_tokens": 3000
}
```

## 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
- Most capable Anthropic model for complex tasks
- Use system messages for precise behavior control
- Lower temperature (0.1-0.3) for coding and factual tasks
- Streaming recommended for long responses
- Compatible with OpenAI SDK format

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