# Claude Haiku 4.5 - Core.Today AI API

> Fast, cost-effective model for everyday tasks. Great balance of speed, intelligence, and cost for high-volume applications.

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

## Model Specifications
- **Context Window**: 200K tokens
- **Max Output**: 8K tokens
- **Training Cutoff**: 2024-04
- **Supported Formats**: text, markdown, xml
- **Compatible SDK**: Anthropic

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

### Token Pricing (per 1M tokens)
- **Input Tokens**: 1,858 credits ($1.24)
- **Output Tokens**: 9,290 credits ($6.19)
- **Cached Tokens**: 185.8 credits ($0.12)

## Features
- 200K context window
- 8K max output tokens
- Vision capabilities
- Fastest Claude model
- Most cost-effective
- Tool use support

## Use Cases
- High-volume chatbots
- Quick Q&A
- Simple classification
- Data labeling
- Real-time interactions
- Content moderation

## 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

### Optional
- **temperature**: float (default: 1.0) - Sampling temperature (0-1)

## Examples

### Quick Response
Fast conversational response
```json
{
  "model": "claude-haiku-4-5",
  "max_tokens": 500,
  "messages": [
    {
      "role": "user",
      "content": "What are the main benefits of renewable energy?"
    }
  ]
}
```

## 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 high-volume, cost-sensitive use cases
- Great for prototyping before using larger models
- Fastest response times in Claude family
- Use for simple tasks that don't need Sonnet/Opus

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