Claude Opus 4.6

anthropic/claude-opus-4-6

previous Opus generation, superseded by Opus 4.8.

cmd --model claude-opus-4-6
Intelligence index
43.7
Output speed
62.9 tok/s
Input
$5 /M
Output
$25 /M
Cache read
$0.50 /M
Agent-loop cost
$1.85 /M in
Context window
1M tokens
Released
February 5, 2026
Modalities
→

vs. the lineup

Claude Opus 4.6 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 559.9◆76.5◆60.2$10$50$201M◆
Claude Opus 4.855.774.365.9$5$25$101M◆
Claude Sonnet 553.471.582.1$2$10$41M◆
Claude Sonnet 4.647.26367.8$3$15$61M◆
Claude Opus 4.6 ◆43.7—62.9$5$25$101M◆
Claude Opus 5———$5$25$101M◆
DeepSeek V4 Propinned44.359.470.9$0.43$0.87$0.541M◆
DeepSeek V4 Flashpinned40.356.2122◆$0.14◆$0.28◆$0.18◆1M◆
Compare all 50 models →

coding performance

The Intelligence Index and its sub-scores, ranked against every scored model in the catalog. A metric that has not been measured for Claude Opus 4.6 has been left empty.

IFBench
53.1
instruction following
Intelligence Index
43.7
#0 of 40 scored
Long-context reasoning
70.7
reasoning across a long context
SciCode
51.9
scientific coding
GPQA Diamond
89.6
graduate-level QA

usage calculator

How far a month of credits goes on Claude Opus 4.6.

Input tokensfresh prompt
800
Output tokensmodel reply
180
Cache read tokensre-read context
50K
cost / request $0.034 · in $5 · out $25 · cache $0.50 per M
fresh input 12%output 13%cache reads 75%
Requests / 30 days
448
$15 credits ÷ $0.034 per request
~90 quick fixes~18 bug fixes~3 feature PRs

what real work costs

Real coding tasks priced end to end on Claude Opus 4.6, from a quick lookup to a full-repo agent run.

One agent task
$0.59
180K in at 75% cache hit, 12K out
What you pay
$3.09 /M
all-in across every token that task touched
Sticker input
$5 /M
cache reads bill at $0.50 /M instead
TaskTokens in · outClaude Opus 4.6Kimi K3Claude Haiku 4.5
Quick lookup / one-liner8K · 1K$0.03$0.02$0.0065
Review a 500-line PR60K · 4K$0.21$0.13$0.04
Fix a bug (agent loop)180K · 12K$0.59$0.36$0.12
Refactor a module320K · 20K$1.06$0.64$0.21
Full-repo agent run900K · 45K$2.47$1.48$0.49

frequently asked

What is Claude Opus 4.6 best for?+
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations. Beyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.
How much does Claude Opus 4.6 cost?+
$5/M input and $25/M output, cache reads $0.50/M. In an agent loop most input is cache-read, so the effective input rate is about $1.85/M.
Which plan do I need?+
Available on Provider and above.
How do I switch to it?+
Run cmd --model claude-opus-4-6, or type /model in a session and pick it. You can switch mid-session without losing context.
Claude Sonnet 5→
best combo of speed & intelligence (recommended) · $2/$10 per M
Claude Sonnet 4.6→
prev Sonnet, still fast & capable · $3/$15 per M
All supported models→
sortable by score, speed and price

Ship code that matches your taste

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

Start nowSee pricing
commandcode.ai/models/claude-opus-4-6