Claude Sonnet 5

anthropic/claude-sonnet-5

best combo of speed & intelligence (recommended).

cmd --model claude-sonnet-5
Intelligence index
55.3
Output speed
82.8 tok/s
Input
$2 /M
Output
$10 /M
Cache read
$0.20 /M
Agent-loop cost
$0.74 /M in
Context window
1M tokens
Released
June 30, 2026
Modalities

vs. the lineup

Claude Sonnet 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 Opus 563.17852.6$5$25$101M
Claude Fable 562.176.566.8$10$50$201M
Claude Opus 4.857.374.3$5$25$101M
Claude Sonnet 555.371.582.8$2$10$41M
Claude Opus 4.75573.6$5$25$101M
Claude Sonnet 4.648.463$3$15$61M
DeepSeek V4 Pro (latest)pinned45.359.463.3$0.43$0.87$0.541M
DeepSeek V4 Flash (latest)pinned5269.1115.9$0.14$0.28$0.181M

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 Sonnet 5 has been left empty.

Coding Index
71.5
#12 of 40 scored
Terminal-Bench
80.5
#11 of 40 scored
Intelligence Index
55.3
#11 of 46 scored
Long-context reasoning
77
reasoning across a long context
SciCode
53.6
scientific coding
GPQA Diamond
91.1
graduate-level QA

usage calculator

How far a month of credits goes on Claude Sonnet 5.

Claude Sonnet 5 runs on Pro and up — from $20/mo.
Input tokensfresh prompt
800
Output tokensmodel reply
180
Cache read tokensre-read context
50K
cost / request $0.013 · in $2 · out $10 · cache $0.20 per M
fresh input 12%output 13%cache reads 75%
Requests / 30 days
1.5K
$20 credits ÷ $0.013 per request
~299 quick fixes~60 bug fixes~10 feature PRs

what real work costs

Real coding tasks priced end to end on Claude Sonnet 5, from a quick lookup to a full-repo agent run.

One agent task
$0.24
180K in at 75% cache hit, 12K out
What you pay
$1.23 /M
all-in across every token that task touched
Sticker input
$2 /M
cache reads bill at $0.20 /M instead
TaskTokens in · outClaude Sonnet 5Muse Spark 1.2Claude Haiku 4.5
Quick lookup / one-liner8K · 1K$0.01$0.0063$0.0065
Review a 500-line PR60K · 4K$0.08$0.05$0.04
Fix a bug (agent loop)180K · 12K$0.24$0.13$0.12
Refactor a module320K · 20K$0.43$0.23$0.21
Full-repo agent run900K · 45K$0.99$0.54$0.49

frequently asked

What is Claude Sonnet 5 best for?
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.
How much does Claude Sonnet 5 cost?
$2/M input and $10/M output, cache reads $0.20/M. In an agent loop most input is cache-read, so the effective input rate is about $0.74/M.
Which plan do I need?
Available on Pro and above.
How do I switch to it?
Run cmd --model claude-sonnet-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 (v4.1)commandcode.ai/models/claude-sonnet-5