Claude Opus 5.5

anthropic/claude-opus-5-5

most intelligent Opus for agents and coding.

cmd --model claude-opus-5-5
Intelligence index
not yet scored
Output speed
not yet scored
Input
$4 /M
Output
$20 /M
Cache read
$0.20 /M
Agent-loop cost
$1.34 /M in
Context window
1M tokens
Released
Modalities

vs. the lineup

Claude Opus 5.5 beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.

pin a rival:
ModelIntelligenceCodingSpeedInput $/MOutput $/MBlended $/MContext
Claude Fable 5.153.481.668.2$10$50$201M
Claude Opus 550.77859.6$5$25$101M
Claude Fable 549.776.570$10$50$201M
Claude Sonnet 538.471.587.5$2$10$41M
Claude Sonnet 4.630.563$3$15$61M
Claude Opus 5.5$4$20$81M
DeepSeek V4 Pro (latest)pinned36.368.865.3$0.66$1.98$0.991M
DeepSeek V4 Flash (latest)pinned3569.1236.4$0.15$0.60$0.261M

usage calculator

How far a month of credits goes on Claude Opus 5.5.

Claude Opus 5.5 runs on Max and up — from $100/mo.
Input tokensfresh prompt
800
Output tokensmodel reply
180
Cache read tokensre-read context
50K
cost / request $0.017 · in $4 · out $20 · cache $0.20 per M
fresh input 19%output 21%cache reads 60%
Requests / 30 days
6.0K
$100 credits ÷ $0.017 per request
~1.2K quick fixes~238 bug fixes~40 feature PRs

what real work costs

Real coding tasks priced end to end on Claude Opus 5.5, from a quick lookup to a full-repo agent run.

One agent task
$0.45
180K in at 75% cache hit, 12K out
What you pay
$2.33 /M
all-in across every token that task touched
Sticker input
$4 /M
cache reads bill at $0.20 /M instead
TaskTokens in · outClaude Opus 5.5Muse Spark 1.3Claude Haiku 4.5
Quick lookup / one-liner8K · 1K$0.02$0.0063$0.0065
Review a 500-line PR60K · 4K$0.16$0.05$0.04
Fix a bug (agent loop)180K · 12K$0.45$0.13$0.12
Refactor a module320K · 20K$0.80$0.23$0.21
Full-repo agent run900K · 45K$1.83$0.54$0.49

frequently asked

How much does Claude Opus 5.5 cost?
$4/M input and $20/M output, cache reads $0.20/M. In an agent loop most input is cache-read, so the effective input rate is about $1.34/M.
Which plan do I need?
Available on Max and above.
How do I switch to it?
Run cmd --model claude-opus-5-5, or type /model in a session and pick it. You can switch mid-session without losing context.

Ship code that matches your taste

Command Code is the AI coding agent that continuously learns your taste. Start for $1.

Benchmarks from Artificial Analysis (v4.3)commandcode.ai/models/claude-opus-5-5