Claude 4.5 Sonnet

Approved Data Classifications

Description

Claude Sonnet 4.5 is Anthropic’s most advanced hybrid-reasoning model to date, designed to excel at agents, coding, and computer use. It combines near-instant response generation with extended, visible step-by-step reasoning for long-running tasks, and supports up to 64K output tokens for rich code generation, planning, and analysis. Sonnet 4.5 advances the state of the art in coding with a 77.2% score on SWE-bench Verified, delivers frontier performance in computer use with 61.4% on OSWorld, and extends its domain expertise in finance and cybersecurity for enterprise-grade workflows. It is priced at $3 per million input tokens and $15 per million output tokens, with up to 90% cost savings through prompt caching and 50% savings via batch processing. Available through the Claude API, Amazon Bedrock, and Google Cloud Vertex AI, Sonnet 4.5 powers everything from autonomous agents and financial analysis to complex software development lifecycles, making it Anthropic’s most capable and versatile model yet.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
claude-4.5-sonnet	July 2025	Image, Text	Text	200,000	$3.00/1M input $15.00/1M output

info

• 1M represents 1 Million Tokens
• All prices listed are based on 1 Million Tokens

Availability

Cloud Provider

Usage

curl

curl -X POST https://api.ai.it.ufl.edu/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <API_TOKEN>" \
-d '{
    "model": "claude-4.5-sonnet",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Write a haiku about an Alligator."
        }
    ]
}'

python

from openai import OpenAI
  client = OpenAI(
      api_key="your_api_key",
      base_url="https://api.ai.it.ufl.edu/v1"
  )

  response = client.chat.completions.create(
      model="claude-4.5-sonnet", # model to send to the proxy
      messages = [
          { role: "system", content: "You are a helpful assistant." },
          {
              "role": "user",
              "content": "Write a haiku about an Alligator."
          }
      ]
  )

  print(response.choices[0].message)

javascript

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'your_api_key',
  baseURL: 'https://api.ai.it.ufl.edu/v1'
});

const completion = await openai.chat.completions.create({
    model: "claude-4.5-sonnet",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

print(completion.choices[0].message)

When to use

• Cost-sensitive coding and development workflows
• Long-form contexts without breaking the bank
• Agentic subagent in automated pipelines
• Balanced speed and depth
• Visual data extraction and analysis
• General-purpose chatbots and content generation

---

References

1. Anthropic
   https://www.anthropic.com
2. LLM Stats
   https://llm-stats.com
3. Artificial Analysis
   https://artificialanalysis.ai