Claude Fable 5.1

anthropic/claude-fable-5-1

most capable for demanding reasoning & long-horizon agents.

cmd --model claude-fable-5-1
Intelligence index
not yet scored
Output speed
not yet scored
Input
$10 /M
Output
$50 /M
Cache read
$0.25 /M
Agent-loop cost
$3.18 /M in
Context window
1M tokens
Released
Modalities

vs. the lineup

Claude Fable 5.1 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 563.17855.5$5$25$101M
Claude Fable 562.176.567.8$10$50$201M
Claude Opus 4.857.374.3$5$25$101M
Claude Sonnet 555.371.589.6$2$10$41M
Claude Sonnet 4.648.463$3$15$61M
Claude Fable 5.1$10$50$201M
DeepSeek V4 Pro (latest)pinned53.268.861$0.66$1.98$0.991M
DeepSeek V4 Flash (latest)pinned5269.1129$0.22$0.66$0.331M

usage calculator

How far a month of credits goes on Claude Fable 5.1.

Claude Fable 5.1 runs on Max and up — from $100/mo.
Input tokensfresh prompt
800
Output tokensmodel reply
180
Cache read tokensre-read context
50K
cost / request $0.030 · in $10 · out $50 · cache $0.25 per M
fresh input 27%output 31%cache reads 42%
Requests / 30 days
3.4K
$100 credits ÷ $0.030 per request
~678 quick fixes~136 bug fixes~23 feature PRs

what real work costs

Real coding tasks priced end to end on Claude Fable 5.1, from a quick lookup to a full-repo agent run.

One agent task
$1.08
180K in at 75% cache hit, 12K out
What you pay
$5.64 /M
all-in across every token that task touched
Sticker input
$10 /M
cache reads bill at $0.25 /M instead
TaskTokens in · outClaude Fable 5.1Claude Opus 5Claude Haiku 4.5
Quick lookup / one-liner8K · 1K$0.06$0.03$0.0065
Review a 500-line PR60K · 4K$0.39$0.21$0.04
Fix a bug (agent loop)180K · 12K$1.08$0.59$0.12
Refactor a module320K · 20K$1.95$1.06$0.21
Full-repo agent run900K · 45K$4.41$2.47$0.49

frequently asked

How much does Claude Fable 5.1 cost?
$10/M input and $50/M output, cache reads $0.25/M. In an agent loop most input is cache-read, so the effective input rate is about $3.18/M.
Which plan do I need?
Available on Max and above.
How do I switch to it?
Run cmd --model claude-fable-5-1, 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-fable-5-1