Skip to main content
Core.Today
|
AnthropicFastHigh

Claude 3.7 Sonnet

Enhanced Claude 3.7 Sonnet with improved reasoning and coding capabilities. A strong mid-tier model offering reliable performance across a wide range of tasks.

3 credits
per 1K tokens (avg)
200K context window
16K max output tokens
Vision capabilities
Extended thinking mode
Strong coding abilities
Streaming support

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txt

Model Specifications

Context Window
200K
tokens
Max Output
16K
tokens
Training Cutoff
2024-11
Compatible SDK
Anthropic

Capabilities

Vision
Function Calling
Streaming
JSON Mode
System Prompt

Token Pricing (per 1M tokens)

Token TypeCreditsUSD Equivalent
Input Tokens6,000$6.00
Output Tokens30,000$30.00
Cached Tokens600$0.60

* 1 credit โ‰ˆ $0.001 (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-3-7-sonnet",
  "max_tokens": 3000,
  "messages": [
    {
      "role": "user",
      "content": "Write a Python async function that fetches multiple URLs concurrently using aiohttp and returns results as a dictionary mapping URL to response status and body."
    }
  ],
  "temperature": 0.3
}'

Parameters

ParameterTypeRequiredDefaultDescription
messagesarrayYes-Array of message objects with role and content
modelstringYesclaude-3-7-sonnetModel identifier
temperaturefloatNo1.0Sampling temperature (0-1)
max_tokensintegerYes-Maximum tokens in response (required, up to 16384)
streambooleanNofalseEnable streaming responses
systemstringNo-System prompt for setting behavior
top_pfloatNo0.999Nucleus sampling parameter (0-1)

Examples

Code Generation

Generate code with Claude 3.7 Sonnet

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-3-7-sonnet",
  "max_tokens": 3000,
  "messages": [
    {
      "role": "user",
      "content": "Write a Python async function that fetches multiple URLs concurrently using aiohttp and returns results as a dictionary mapping URL to response status and body."
    }
  ],
  "temperature": 0.3
}'

Data Analysis

Analyze data with structured output

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-3-7-sonnet",
  "max_tokens": 2000,
  "system": "You are a data analyst. Provide insights in a structured format.",
  "messages": [
    {
      "role": "user",
      "content": "Analyze the following sales data and identify trends, anomalies, and actionable recommendations: [sales data]"
    }
  ]
}'

Tips & Best Practices

1Strong coding and reasoning at an efficient price
2max_tokens is required - always specify it
3Use extended thinking for complex multi-step problems
4Temperature max is 1.0 (not 2.0 like OpenAI)
5Great for everyday development and analysis tasks
6Use caching for repeated context to reduce costs

Use Cases

Code generation and debugging
Technical documentation
Data analysis
Conversational AI
Content summarization
Task automation

Model Info

ProviderAnthropic
Version20250219
CategoryLLM
Price3 credits

API Endpoint

POST /llm/anthropic/v1/messages
Try in PlaygroundBack to Docs