# Claude Sonnet 5.5 - Core.Today AI API

> Anthropic's newest Sonnet model (September 2026), balancing speed, cost, and intelligence at $2/$10 per M tokens. 1M-token context window and 128K max output tokens, with prompt caching (read $0.20/M, 5-minute write $2.50/M) and web search. Compatible with the Anthropic Messages and OpenAI Chat Completions formats.

- **Provider**: Anthropic
- **Model ID**: claude-sonnet-5-5
- **Category**: LLM
- **Credits**: 2 per 1K tokens (avg)
- **Speed**: Fast
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 1M tokens
- **Max Output**: 128K tokens
- **Training Cutoff**: Not published
- **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**: 3,716 credits ($2.48)
- **Output Tokens**: 18,580 credits ($12.39)
- **Cached Tokens**: 371.6 credits ($0.25)

## Features
- Balanced speed, cost, and intelligence
- 1M token context window
- 128K max output tokens
- Prompt caching (read 10% / 5-min write 125% of input price)
- Web search tool support
- Vision and tool use
- Streaming support

## Use Cases
- High-volume production workloads
- Long-context document understanding (up to 1M tokens)
- Code generation and review
- Multi-step agentic workflows
- Cost-sensitive reasoning tasks

## 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
- **max_tokens**: integer (default: 4096) - Maximum tokens in response (up to 128000)
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming

## Examples

### High-throughput Analysis
Fast, cost-efficient analysis over large documents with Claude Sonnet 5.5
```json
{
  "model": "claude-sonnet-5-5",
  "messages": [
    {
      "role": "system",
      "content": "You are a research analyst. Provide structured, source-aware analysis."
    },
    {
      "role": "user",
      "content": "Summarize the key findings and open questions from this 200-page technical report and flag any inconsistencies."
    }
  ],
  "max_tokens": 6000
}
```

### Production Code Generation
Generate production-ready code with a strong quality-to-cost ratio
```json
{
  "model": "claude-sonnet-5-5",
  "messages": [
    {
      "role": "system",
      "content": "You are a senior software engineer. Write clean, well-tested, production code."
    },
    {
      "role": "user",
      "content": "Implement a token-bucket rate limiter in TypeScript backed by Redis, with unit tests."
    }
  ],
  "max_tokens": 6000
}
```

## 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 default Anthropic model when you want strong reasoning at Sonnet-tier speed and cost ($2/$10 per M)
- 128K output (vs 64K on Sonnet 5) enables long-form drafts in a single response
- Prompt caching: read $0.20/M (10%), 5-minute write $2.50/M — cache large repeated contexts
- Web search costs about 18.6 credits per request ($10 per 1,000 searches) on top of token usage
- Sampling params (`temperature`, `top_p`, `top_k`) are not accepted by Claude 4.7+ models — omit them (the console strips `temperature` automatically)
- Streaming recommended for long responses
- Compatible with both Anthropic Messages and OpenAI SDK formats
- US-only inference (inference_geo: us) bills token charges at 1.1x

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