Enterprise DNAEnterprise DNA
LModelsBest vision
Anthropic logo

Claude Sonnet 5.5

by Anthropic

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fix

Visit AnthropicSubmit your build →
CS

Models

Claude Sonnet 5.5

Added 29 Sept 2026

#anthropic

Overview

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...

Best for

Best for
Scoped features and debugging

How to use / API access

Call via OpenRouter with model id `anthropic/claude-sonnet-5.5`.

  • openrouter · anthropic/claude-sonnet-5.5 Docs

OpenRouter id: anthropic/claude-sonnet-5.5

Benchmarks

  • Intelligence Index (artificial-analysis): 56 index
  • Design Arena 3d (other): 1463 elo · #2
  • Design Arena codecategories (other): 1366 elo · #3
  • Design Arena dataviz (other): 1387 elo · #2
  • Design Arena gamedev (other): 1480 elo · #1

Notes

Claude Sonnet 5.5 is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Implementing a bounded feature from clear acceptance criteria
  • text, image, file input; text output on the listed OpenRouter route

Cons

  • Assuming a Sonnet label proves task accuracy
  • Giving ambiguous requirements to an unattended build
  • Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →

USAGE / OPENROUTER

How much Claude Sonnet 5.5 is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
2.5T ▲1.1%
Requests, last 7 days
40.4M
Tool calls, last 7 days
16M
Intelligence score
56
People's vote
1470
Average cost per request
$3.25
Price per million tokens
$2 in · $10 out
0500B1T28 Sept: 14.1B tokens, 354K requests29 Sept: 98.7B tokens, 2.2M requests30 Sept: 138B tokens, 2.7M requests1 Oct: 154B tokens, 3.3M requests2 Oct: 141B tokens, 3.1M requests3 Oct: 130B tokens, 2.7M requests4 Oct: 114B tokens, 2.7M requests5 Oct: 152B tokens, 3.4M requests6 Oct: 363B tokens, 5.4M requests7 Oct: 344B tokens, 5M requests8 Oct: 247B tokens, 4.3M requests9 Oct: 366B tokens, 5.4M requests10 Oct: 428B tokens, 4.4M requests11 Oct: 531B tokens, 4.8M requests12 Oct: 375B tokens, 5.3M requests13 Oct: 372B tokens, 6.6M requests14 Oct: 389B tokens, 6.1M requests15 Oct: 318B tokens, 6.6M requests16 Oct: 397B tokens, 6.3M requests17 Oct: 315B tokens, 4.7M requests18 Oct: 291B tokens, 4.8M requests28 Sept12 Oct18 OctSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Claude Sonnet 5.5.

Specifications reviewed; no EDNA task evaluation has been run. Sources checked 2026-10-20. Hosting routes and app features can differ.

DeveloperAnthropic
Exact model identifieranthropic/claude-sonnet-5.5
Inputtext, image, file
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient

Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.

Consider it for

  • Implementing a bounded feature from clear acceptance criteria
  • Turning a document outline into a structured draft

Watch for

  • Assuming a Sonnet label proves task accuracy
  • Giving ambiguous requirements to an unattended build

PRACTICAL EXERCISE / NOT RUN BY ENTERPRISE DNA

Try the model on a small, checkable task.

Design a CSV import preview for columns invoice_id, amount and currency. Show validation rules and a sample error for a duplicate invoice_id; do not write imported records.

Check the result: The preview distinguishes invalid numbers, missing currencies and duplicate identifiers without saving anything.

Compare another approach

openai gpt 6 1 sol ↗google gemini 3 8 flash ↗
Inspect the sources and their scope
provider source ↗

Developer documentation for model family or task. OpenRouter route-specific properties remain catalogue claims; EDNA has not executed a task evaluation.

Checked 2026-10-19
catalogue source ↗

anthropic/claude-sonnet-5.5: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-10-20
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Write a clear business documentWorkflow & starter prompt ↗Analyse a spreadsheetWorkflow & starter prompt ↗Research a companyWorkflow & starter prompt ↗Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

Check the source

Price date: 2026-10-20. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 56 (2026-10-18) ↗
Compare this model with alternatives →