modelbenchmark.io

Grok 3 Mini

xAI · grok-3-mini

Compare

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

Specification

xai listing

Context
131K
Max output
131K
Released
2025-04-11
Knowledge cutoff
2024-06
Retires
2026-02-28
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · xai list price

Input
$1.25
Output
$2.50
Cache read
$0.20

Long-context price tiers

the rate above each context threshold

AbovePrice$/M
200KCache read$0.40
200KInput$2.50
200KOutput$5.00

Quality

5 benchmarks · 1 source

Composite
63rd
percentile of 334 scored models
Rank
124 / 334
±0.06 sd
Evidence
5 × 1
one source, or fewer than 3 benchmarks
Effort range
one configuration only
reasoning79th1/4 bench
math59th4/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
MATH level 589.5 ±0.8default · 2 runsEpoch AI2025-04-10
OTIS Mock AIME 2024-202570.0 ±7.3default · 2 runsEpoch AI2025-04-10
GPQA diamond75.4 ±2.8default · 2 runsEpoch AI2025-05-26
FrontierMath-Tier-4-2025-07-010.0 ±0.0defaultEpoch AI2025-07-01
FrontierMath-v12.2 ±0.0default · 4 runsEpoch AI2025-04-10

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 6 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
xaivendor$1.25$2.50$0.20131K131K2026-02-28
azure_ai$0.25$1.27131K131K2026-05-01
helicone$0.30$0.50$0.075131K131K
oci · oci$0.30$0.50131K131K
poe$0.30$0.50$0.075131K8K
vercel_ai_gateway · vercel-ai-gateway$0.30$0.50131K131K

More from xAI

most-hosted first