Claude 4.6 Opus

Approved Data Classifications

Description

Claude Opus 4.6 is Anthropic’s most capable hybrid-reasoning and agentic model, designed for complex coding, long-running AI agents, and enterprise workflows, with a standard 200K token context window and an optional 1M-token extended context (beta), adaptive reasoning levels to balance cost and depth, stronger planning and debugging on large codebases, higher single-response outputs, and improved reliability on multi-step tasks; it sets top-tier performance across coding and computer-use benchmarks (including ~80% on SWE-bench Verified and ~70% on OSWorld), is available via the Claude API and major cloud platforms (Amazon Bedrock, Google Cloud Vertex AI, Microsoft Foundry), and is priced at $5 per million input tokens and $25 per million output tokens for standard context, with premium pricing for extended context and up to 90% savings via prompt caching and 50% via batch processing.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
claude-4.6-opus	August 2025	Image, Text	Text	200,000	$5.00/1M input $25.00/1M 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-4.6-opus",
    "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-4.6-opus", # 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-4.6-opus",
    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

• Frontier-intelligence tasks where accuracy matters most
• Professional software engineering and architecture
• Complex, multi-step agentic workflows
• High-stakes enterprise decision support
• Advanced computer-use and tool orchestration
• Large-context tasks needing a 200K window

---

References

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