Claude Platform Docs
Models & pricingModels

Claude Opus 5.5Latest

For long-running agentic coding and knowledge work

Try in playground
Context window
1Mtokens
Max output
128Ktokens
Input pricing
$4/ MTok
Output pricing
$20/ MTok

Overview

Claude Opus 5.5 is built for long-running agentic coding and knowledge work, priced at $4 / $20 USD per million input / output tokens. Four breaking changes affect code already running on Claude Opus 5: thinking can't be disabled, forced tool use returns an error, thinking blocks are tied to the model and the conversation, and, on the Claude API and Google Cloud, the earlier computer_20251124 computer use tool is not accepted. The first three also apply on Claude Fable 5.1. A further change alters the response shape without failing any request: text between tool calls comes back in thinking blocks whose text is empty at the default display setting. An application that streams that text to its users as progress updates goes quiet between tool calls until it sets a display value that returns the text.

What's new in Claude Opus 5.5

How it compares

ModelContextMax outputPrice / MTokLatencyThinkingDefault effortKnowledge cutoff
Claude Fable 5.11M128K$10 / $50SlowerAdaptive (always on)highJun 2026
Claude Opus 5.5This model1M128K$4 / $20ModerateAdaptive (always on)mediumJun 2026
Claude Sonnet 51M128K$2 / $10FastAdaptivehighJan 2026
Claude Haiku 4.5200K64K$1 / $5FastestExtendedFeb 2025

Specifications

Model IDs

Claude API
Amazon Bedrock
Google Cloud
Microsoft Foundry
Claude Platform on AWS

Pricing

Input
$4 / MTok
Output
$20 / MTok
Cache read
$0.20 / MTok
Batch API
50% discount on input and output
Full price list
Pricing

Capabilities

Max output
128K tokens
Thinking
Adaptive (always on)
Comparative latency
Moderate
Input → output
Text and images → text
Reliable knowledge cutoff
Jun 2026
Training data cutoff
Jun 2026

Availability

Status
Active (latest)
Released
September 22, 2026
Retirement
Not sooner than September 22, 2027

Good to know

  • Adaptive thinking is always on and can't be turned off. Control thinking depth with the effort parameter.
  • On the Message Batches API, Claude Opus 5.5 supports up to 300k output tokens with the output-300k-2026-03-24 beta header.
  • The minimum cacheable prompt length is 512 tokens. See Prompt caching.
  • Query limits and capabilities programmatically with the Models API.

Resources

Behavioral differences and prompting patterns specific to Claude Opus 5.5.

The control for thinking depth, latency, and cost. Choose a level per workload.

How adaptive thinking works and how thinking blocks are preserved.

Lower-latency Claude Opus 5.5 on the Claude API (research preview), priced separately.

Reference

The system prompt Claude Opus 5.5 uses on claude.ai and the Claude apps.

Safety evaluations and deployment decisions for Claude Opus 5.5.

Full price list, including batch discounts and prompt caching rates.

How model IDs, aliases, and pinned snapshots work.

Lifecycle status and retirement commitments for every Claude model.

Was this page helpful?