Skip to main content
Core.Today
|
AnthropicFastUltra

Claude Sonnet 4.6

The successor to Claude Sonnet 4.5. Anthropic's frontier Sonnet-tier model for complex reasoning, nuanced understanding, and coding tasks with exceptional instruction following, at the same token pricing as Sonnet 4.5.

5,574/27,870credits
input / output ยท per 1M tokens
200K context window
16K max output tokens
Vision capabilities
Computer use
Superior code generation
Exceptional instruction following
Prompt caching โ€” cache writes โ‰ˆ6,967.5 credits per 1M tokens ($3.75), cache reads 557.4 credits per 1M tokens
Server-side web search โ€” 18.58 credits per request

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Model Specifications

Context Window
200K
tokens
Max Output
16K
tokens
Training Cutoff
2025-04
Compatible SDK
Anthropic

Capabilities

Vision
Function Calling
Streaming
JSON Mode
System Prompt

Token Pricing (per 1M tokens)

Token TypeCreditsUSD Equivalent
Input Tokens5,574$3.72
Output Tokens27,870$18.58
Cached Tokens557.4$0.37

* 1,500 credits โ‰ˆ $1 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/anthropic/v1/messages" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "claude-sonnet-4-6",
  "max_tokens": 4000,
  "system": "You are an expert analyst. Provide detailed, structured analysis.",
  "messages": [
    {
      "role": "user",
      "content": "Analyze the key themes and implications of this research paper: [paper text]"
    }
  ]
}'

Parameters

ParameterTypeRequiredDefaultDescription
messagesarrayYes-Array of message objects with role and content
modelstringYesclaude-sonnet-4-6Model identifier
max_tokensintegerYes-Maximum tokens in response (required, up to 16384)
systemstringNo-System prompt for setting behavior
temperaturefloatNo1.0Sampling temperature (0-1)
streambooleanNofalseEnable streaming responses
toolsarrayNo-List of tools the model can use

Examples

Document Analysis

Analyze complex documents

curl -X POST "https://api.core.today/llm/anthropic/v1/messages" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "claude-sonnet-4-6",
  "max_tokens": 4000,
  "system": "You are an expert analyst. Provide detailed, structured analysis.",
  "messages": [
    {
      "role": "user",
      "content": "Analyze the key themes and implications of this research paper: [paper text]"
    }
  ]
}'

Code Generation

Generate production-quality code

curl -X POST "https://api.core.today/llm/anthropic/v1/messages" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "claude-sonnet-4-6",
  "max_tokens": 4000,
  "messages": [
    {
      "role": "user",
      "content": "Create a TypeScript React component for a data table with sorting, filtering, and pagination. Use modern best practices."
    }
  ],
  "temperature": 0.3
}'

Tool Use

Use tools/functions with Claude

curl -X POST "https://api.core.today/llm/anthropic/v1/messages" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "claude-sonnet-4-6",
  "max_tokens": 1000,
  "messages": [
    {
      "role": "user",
      "content": "Look up the current stock price of Apple."
    }
  ],
  "tools": [
    {
      "name": "get_stock_price",
      "description": "Get the current stock price for a given symbol",
      "input_schema": {
        "type": "object",
        "properties": {
          "symbol": {
            "type": "string",
            "description": "Stock ticker symbol"
          }
        },
        "required": [
          "symbol"
        ]
      }
    }
  ]
}'

Tips & Best Practices

1Use the official Anthropic SDK with base_url https://ai.api.core.today/llm/anthropic โ€” no other code changes needed
2max_tokens is required - always specify it
3Use system prompt for persona and constraints
4XML tags in prompts improve structured responses
5Temperature max is 1.0 (not 2.0 like OpenAI)
6Use prompt caching for repeated context โ€” cache reads cost a tenth of regular input tokens

Use Cases

Complex document analysis
Code generation and review
Research and analysis
Technical writing
Agentic workflows
Data extraction