Claude Sonnet 5

Approved Data Classifications

This model is only approved for Open Data. When leveraging NaviGator AI’s suite offerings, please ensure you are selecting models that meet the compliance requirements in accordance with UF’s Data Classifications, grant awards or project specifications, and state and federal law.

Description

Claude Sonnet 5 is Anthropic’s latest Sonnet model, designed to provide a strong balance of intelligence, speed, and cost. It is particularly focused on coding, agentic workflows, tool use, reasoning, and long-running multi-step tasks, with a 1-million-token context window and up to 128K-token outputs.

Capabilities

Model	Knowledge Cutoff	Input	Output	Context Length	Cost (per 1 million tokens)
claude-sonnet-5	January 2026	Text, Image, Pdf	Text	1,000,000	$2.20/1M input $11.00/1M output

info

• 1M represents 1 Million Tokens
• All prices listed are based on 1 Million Tokens
• Maximum output: 128,000 tokens
• Cache reads: $0.22 per 1M tokens
• Cache writes: $2.75 per 1M 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-sonnet-5",
    "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-sonnet-5", # 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-sonnet-5",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

console.log(completion.choices[0].message)

When to use

• Coding & software development — debugging, refactoring, implementing features, and working across larger codebases
• AI agents & automation — multi-step tasks that require planning, tool use, and sustained execution
• Document & knowledge work — analyzing complex documents, research, spreadsheets, and business content
• Computer/browser use — workflows that require interacting with websites or desktop applications
• High-volume production workloads — when you need strong capabilities while keeping inference costs relatively efficient

---

References

1. Anthropic https://www.anthropic.com/claude-sonnet-5-system-card
2. LLM Stats https://llm-stats.com/models/claude-sonnet-5
3. Artificial Analysis https://artificialanalysis.ai/models/claude-sonnet-5