modelbenchmark.io

grok-4-fast-reasoning

xAI · grok-4-fast-reasoning

Compare

Fast Grok model for responsive chat, reasoning, and tool-assisted work

Specification

most-agreed values

Context
2M
Max output
30K
Released
2025-12-18
Knowledge cutoff
2025-06
Retires
2026-05-01
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.20
Output
$0.50
Cache read
$0.05

Available from 6 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
jiekou$0.18$0.45——2M2M—
302ai$0.20$0.50——2M30K—
azure_ai$0.20$0.50————2026-05-01
helicone$0.20$0.50$0.05—2M2M—
poe$0.20$0.50$0.05—2M128K—
qiniu-ai · x-ai————2M2M—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02azure_aiInput$0.20
2026-09-26azure_aiInput$0.20
2026-09-02azure_aiOutput$0.50
2026-09-26azure_aiOutput$0.50

More from xAI

most-hosted first