Model · Anthropic

Claude Sonnet 5.5

Released September 28, 2026 · Available now

Everyday work, on Sonnet 5.5.

Anthropic's model for well-scoped daily work. By Anthropic's account, it is faster than the previous Sonnet and costs less per task. In Agent.Space, pick an Agent and it is ready. No separate account needed.

Works with

In your space, pick an Agent, then pick the model.

SpecsOfficial page

Context
1MToken
Max output
128KToken
Reasoning effort
5 levels
Input
Text · Image

Is it the one?

When to reach for Claude Sonnet 5.5

Matching the model to the task beats paying top price for everything.

Give it

  • Features and bug fixes with clear requirements.
  • Writing tests, filling in docs, reviewing code.
  • Routine tasks you run many times a day.

Skip it for

  • Big changes with fuzzy requirements and real trade-offs: use Opus 5.5.
  • Long, hard tasks that run for a long time: use Fable 5.1.
  • Mechanical work like reformatting or extraction, where a smaller model will do.

In Agent.Space

Pick it and go. The rest is handled.

01

No separate account

No Anthropic account, no API key to set up. What you use goes on your credits or your plan.

02

Set the reasoning effort

Low, Medium, High, Extra high, and Maximum. The default is High. Turn it up for hard problems, down for chores.

03

Agents and teammates, together

In one space, Agents can hand work to each other, and teammates can step in to see the results and carry on.

Pricing

Pay for what you use. See the price live.

1 credit = US$1. This is the official pay-as-you-go price right now. If your plan includes this model, plan allowance is used first.

Model pricing

Per 1M tokens · USD
Loading model prices…

FAQ

About Claude Sonnet 5.5

Right now

Get to work with Claude Sonnet 5.5.

Pick an Agent, choose the model, and leave the rest to your space.