Claude Platform Docs
Although Claude Opus 4.6 is still available, you should consider migrating to Claude Opus 5 for improved performance.
See Claude Opus 5
Models & pricingLegacy models

Claude Opus 4.6Legacy

Migrate to Claude Opus 5
Context window
1Mtokens
Max output
128Ktokens
Input pricing
$5/ MTok
Output pricing
$25/ MTok

How it compares to the current lineup

ModelContextMax outputPrice / MTokThinkingDefault effortKnowledge cutoff
Claude Fable 5.11M128K$10 / $50Adaptive (always on)highJun 2026
Claude Opus 51M128K$5 / $25AdaptivehighMay 2026
Claude Opus 4.6This modelLegacy1M128K$5 / $25Adaptive (extended deprecated)highMay 2025
Claude Sonnet 51M128K$2 / $10AdaptivehighJan 2026
Claude Haiku 4.5200K64K$1 / $5ExtendedFeb 2025

Specifications

Model IDs

Claude API
Amazon Bedrock (InvokeModel)
Google Cloud
Microsoft Foundry
Claude Platform on AWS

Pricing

Input
$5 / MTok
Output
$25 / MTok
5m cache write
$6.25 / MTok
1h cache write
$10 / MTok
Cache read
$0.50 / MTok
Batch API
50% discount on input and output
Full price list
Pricing

Capabilities

Max output
128K tokens
Thinking
Adaptive (extended deprecated)
Input → output
Text and images → text
Reliable knowledge cutoff
May 2025
Training data cutoff
Aug 2025

Availability

Status
Active (legacy)
Released
February 5, 2026
Retirement
Not sooner than February 5, 2027

Resources

What changes when moving from Claude Opus 4.6 and earlier Opus models to Claude Opus 5.

The current Opus model: overview, specs, and resources.

Reference

The system prompt Claude Opus 4.6 uses on claude.ai and the Claude apps.

Safety evaluations and deployment decisions for Claude Opus 4.6.

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.

Claude Opus 4.6 uses the InvokeModel Bedrock integration and Bedrock-style model IDs.

Was this page helpful?