Anthropic models
Available on Julius

Anthropic: Claude Sonnet 5.5

A balance of speed and reasoning for everyday analysis, writing, and working through your files.

Available on Pro, Max, Ultra, and Business. Compare plans

Reviewed · Sources

Cleaned six-order worksheet and monthly chart showing net sales growing from $1,300 to $1,600 after refunds and deduplication.
Cleaned sales worksheetIllustrative output · Fictional dataView full size
Best suited to
Everyday work with a balance of speed and cost
Published context
1,000,000 tokens
Native inputs
Text and images
Released
September 28, 2026

Claude Sonnet 5.5 pricing

Compare the provider’s API rates with access through Julius.

Anthropic API

Input / 1M tokens
$2
Output / 1M tokens
$10

Standard API rates per million tokens. Cache writes, cache reads, batch processing, and optional tools are billed separately.

Check provider pricing (opens in a new tab)

Use your Julius plan

Available on Pro, Max, Ultra, and Business. Credits cover the work performed with models and tools.

View Julius plans and credits

Prices in USD, reviewed October 13, 2026. API token charges are separate from Julius subscriptions and credits.

What is Claude Sonnet 5.5?

Claude Sonnet 5.5 is Anthropic’s model for work that needs both speed and reasoning. It supports text and image input, a one-million-token context window, and up to 128K output tokens.

Sonnet is a useful starting point for an iterative task: ask a question, inspect the result, and refine it. In Julius, try it for spreadsheet exploration, a first research pass, or a presentation outline before deciding whether the task needs a more intensive model.

A practical starting point

Anthropic positions Sonnet around speed and intelligence, with lower API token prices than Opus 5.5 and Fable 5.1.

Adaptive thinking

Reasoning effort can be adjusted to the task. In Julius, use the thinking settings offered in the model menu.

Clean a sales export before reporting growth

A sales export contains a repeated order and fully refunded purchases. Is February really growing?

Worked example · Fictional sample data · Expected results calculated from the CSVs

  1. 1. Input

    Orders, including refunds

  2. 2. Check

    Remove the duplicate order

  3. 3. Deliver

    Monthly net sales and growth

Expected result

Remove 1 duplicate row. Net sales are $1,300 in January and $1,600 in February: 23.1% growth.

Unique orders
6
Net sales growth
23.1%
Net sales after cleanup · USD
January
$1,300
February
$1,600

What the analysis needs to catch

Summing the raw export double-counts order A02 and includes refunded revenue. Keep one record per order before calculating the monthly totals.

Make this deliverable

A cleaned sales table, a monthly chart, and an audit note.

Clean and analyze your own sales workbook with Julius for Excel.

Try this example in Julius

The prompt includes the sample data. Review it in chat before sending. Results may vary; compare your answer with the calculations shown here.

View the prompt and sample data

Inspect this order export. Remove exact duplicate order records, flag any conflicting duplicates instead of guessing, and subtract refunds once per order. Compare January and February net sales, calculate growth, and create a chart. Include a small audit log explaining each cleanup step.

orders.csv

order_id,month,gross_sales,refund
A01,January,500,0
A02,January,800,0
A02,January,800,0
A03,January,200,200
A04,February,700,0
A05,February,900,0
A06,February,100,100

These expected results come from the downloadable Python calculations. This example illustrates a workflow; it is not a measured benchmark of Claude Sonnet 5.5.

Using Claude Sonnet 5.5 in Julius

Start with your task

The try buttons carry Claude Sonnet 5.5 into a new chat when your plan includes it. Example buttons also fill the composer with the sample data. Review the prompt, or replace it with your own files and question, before sending.

If the model is unavailable on your plan, Julius explains the access requirement. You can choose another option in the model menu.

Know the boundaries

  • For especially demanding work, compare a result with Opus or Fable using the same sources and task.
  • Model context limits and API pricing describe Anthropic’s service. Julius file handling and credit usage follow Julius’s own product limits.

Model details and official research

Go to the original documentation for specifications, release details, and evaluation methods.

Claude Sonnet 5.5: frequently asked questions

Is Claude Sonnet 5.5 available on Julius?
Yes. It appears as Claude Sonnet 5.5 in the model menu. Available on Pro, Max, Ultra, and Business plans.
How much does Claude Sonnet 5.5 cost?
Anthropic lists $2 per million input tokens and $10 per million output tokens. Standard API rates per million tokens. Cache writes, cache reads, batch processing, and optional tools are billed separately. Julius subscriptions and credits are separate.
How does Claude Sonnet 5.5 compare with Opus 5.5?
Anthropic positions Sonnet for a balance of speed and intelligence, and Opus for longer-running coding and knowledge work. Standard API prices are $2/$10 for Sonnet and $4/$20 for Opus per million input/output tokens. Both are available in Julius on eligible paid plans.

Turn your next question into a finished task

Bring your files or question and get started with Claude Sonnet 5.5.