Claude Sonnet 5.5: what's new and how to set its effort

The fast, affordable model of the Claude 5.5 family. Released September 28, 2026, at the same price as Sonnet 5, with a big jump in agentic coding.

Model ID
claude-sonnet-5-5
Context
1M
Max output
128K
Price / MTok
$2 / $10
Default effort
high

What it's good at

  • Strongest at well-scoped everyday tasks, fixing bugs, and polished documents, slides and spreadsheets.
  • 70.6% on Terminal-Bench 4.0, an agentic coding evaluation.
  • More than 30% faster than Sonnet 5 and up to 30% cheaper for most work, per Anthropic.
  • Same $2 / $10 per million tokens as Sonnet 5, with a 1M-token context window.

What changed

  • A new lowest thinking setting, between_tools, turns off up-front thinking (at high effort or below).
  • Forced tool use (tool_choice any / tool) returns an error.
  • Text between tool calls comes back as thinking blocks.
  • Non-default temperature, top_p or top_k returns an error.

Which effort to use

Claude Code and the Claude apps run Sonnet 5.5 at medium by default; the API defaults to high. For bug fixes and everyday edits, medium is plenty. Move to high or xhigh when a task spans many files.

How to set effort in Claude Code

low

Fastest, fewest tokens. Simple edits, quick questions, subagents.

medium

Everyday work. The default on Opus 5.5, and on Sonnet 5.5 in Claude Code.

high

More reasoning for multi-file changes. The default on most models.

xhigh

Complex coding and long agentic runs. Deeper than high, without the full cost of max.

max

Hard debugging and architecture decisions. Session-only in Claude Code.

Five ways to set it

/effort

Open the slider. Or /effort xhigh to set a level, /effort auto to go back to the model's default.

/model

Use the left and right arrow keys on the effort slider while picking a model.

claude --effort high

One run only. The level doesn't carry into your next session.

"effortLevel": "xhigh"

In your settings file, to make it your standing default.

CLAUDE_CODE_EFFORT_LEVEL=high

As an environment variable (a level name, or auto).

A level set with /effort carries into your next session; max doesn't, unless you set it through the environment variable. If Claude skipped a file or stopped halfway, raise the effort. If it had everything and still got it wrong, try a more capable model.

Questions

When was Claude Sonnet 5.5 released?

September 28, 2026. Claude Sonnet 5 is now a legacy model.

What is the default effort for Sonnet 5.5?

Medium in Claude Code and the Claude apps, high on the Claude API.

How much does Claude Sonnet 5.5 cost?

$2 per million input tokens and $10 per million output tokens, the same as Sonnet 5. Batch requests are 50% off.

Sonnet 5.5 or Opus 5.5?

Sonnet 5.5 for well-scoped tasks where speed and price matter; Opus 5.5 for complex work that needs careful judgment.

Sources

Use Claude in Claude Code today

A day pass — no Anthropic account, no waiting for your limit.

Get a Claude day pass
Claude Sonnet 5.5: what's new and how to set its effort | HaryAI