# Claude Opus 4.8 - Core.Today AI API

> Anthropic's most capable Opus-tier model, with a 1M-token context window (200K on some surfaces), 128K max output tokens, and knowledge cutoff to January 2026. Builds on Opus 4.7 with stronger long-horizon agentic coding, better tool triggering, and adaptive thinking that reasons only when a turn needs it. Compatible with the Anthropic Messages and OpenAI Chat Completions formats.

- **Provider**: Anthropic
- **Model ID**: claude-opus-4-8
- **Category**: LLM
- **Credits**: 5 per 1K tokens (avg)
- **Speed**: Medium
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 1M tokens
- **Max Output**: 128K tokens
- **Training Cutoff**: 2026-01
- **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
- 1M token context window
- 128K max output tokens
- Knowledge cutoff: January 2026
- Adaptive thinking (effort-controlled)
- Vision and tool use
- Streaming support

## Use Cases
- Frontier research and analysis
- Long-context document understanding (up to 1M tokens)
- Advanced code generation and refactoring
- Multi-step agentic workflows
- Enterprise-grade 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

### Long-context Analysis
Deep multi-step analysis over large documents with Claude Opus 4.8
```json
{
  "model": "claude-opus-4-8",
  "messages": [
    {
      "role": "system",
      "content": "You are a principal research analyst. Provide rigorous, source-aware analysis."
    },
    {
      "role": "user",
      "content": "Compare the safety and capability trade-offs of frontier closed-weight models versus open-weight alternatives for enterprise deployment in 2026, with mitigations."
    }
  ],
  "max_tokens": 8000
}
```

### Production Code Generation
Generate production-ready code with full reasoning
```json
{
  "model": "claude-opus-4-8",
  "messages": [
    {
      "role": "system",
      "content": "You are a senior software engineer. Write clean, well-tested, production code."
    },
    {
      "role": "user",
      "content": "Implement a distributed rate limiter in Go using Redis Cluster with the leaky bucket algorithm. Include 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
- Most capable Anthropic model — pick this for the hardest reasoning and long-horizon agentic tasks
- 1M context window handles very large codebases and document sets in a single request
- 128K output enables long-form drafts in a single response
- Sampling params (`temperature`, `top_p`, `top_k`) are unsupported — omit them; a non-default value returns a 400
- Thinking is adaptive-only: use `thinking: {type: "adaptive"}` and control depth with the `effort` parameter (defaults to `high`); fixed `budget_tokens` returns a 400
- Streaming recommended for long responses
- Compatible with both Anthropic Messages and OpenAI SDK formats

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