Grok 4.7

xai/grok-4.7

coding and knowledge work, built for multi-hour tasks.

cmd --model xai/grok-4.7
Intelligence index
not yet scored
Output speed
not yet scored
Input
$2 /M
Output
$6 /M
Cache read
$0.50 /M
Agent-loop cost
$0.95 /M in
Context window
500K tokens
Released
Modalities

vs. the lineup

Grok 4.7 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
Muse Spark 1.348.275.8418.4$1.25$4.25$21.05M
Grok 4.644.476.871.4$2$6$3500K
Grok 4.539.172.458.4$2$6$3500K
Claude Haiku 4.515.492.1$1$5$2200K
Grok 4.7$2$6$3500K
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

price bands

Grok 4.7 is not billed at one flat rate — the price changes with how much context a request carries. The header quotes the standard band; here is every band.

BandContextInput $/MOutput $/MCache read $/M
Standard≤ 200K$2.00$6.00$0.50
Long context> 200K$4.00$12.00$1.00

usage calculator

How far a month of credits goes on Grok 4.7.

Grok 4.7 runs on GOAT and up — from $10/mo.
Input tokensfresh prompt
800
Output tokensmodel reply
180
Cache read tokensre-read context
50K
cost / request $0.028 · in $2 · out $6 · cache $0.50 per M
fresh input 6%output 4%cache reads 90%
Requests / 30 days
1.0K
$28 credits ÷ $0.028 per request
~202 quick fixes~40 bug fixes~7 feature PRs

what real work costs

Real coding tasks priced end to end on Grok 4.7, from a quick lookup to a full-repo agent run.

One agent task
$0.23
180K in at 75% cache hit, 12K out
What you pay
$1.20 /M
all-in across every token that task touched
Sticker input
$2 /M
cache reads bill at $0.50 /M instead
TaskTokens in · outGrok 4.7Muse Spark 1.3Claude 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$0.23$0.13$0.12
Refactor a module320K · 20K$0.41$0.23$0.21
Full-repo agent run900K · 45K$1.02$0.54$0.49

frequently asked

How much does Grok 4.7 cost?
$2/M input and $6/M output, cache reads $0.50/M. In an agent loop most input is cache-read, so the effective input rate is about $0.95/M.
Which plan do I need?
Available on GOAT and above.
How do I switch to it?
Run cmd --model xai/grok-4.7, 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/grok-4-7