modelbenchmark.io

Grok 4.5

xAI · grok-4-5

Compare

xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk

Specification

xai listing

Context
500K
Max output
500K
Released
2026-07-08
Knowledge cutoff
—
Retires
2026-10-19
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · xai list price

Input
$2.00
Output
$6.00
Cache read
$0.30
Cache write
$2.00

Long-context price tiers

the rate above each context threshold

AbovePrice$/M
200KCache read$0.60
200KInput$4.00
200KOutput$12.00

Quality

8 benchmarks · 2 sources

Composite
67th
percentile of 344 scored models
Rank
113 / 344
±0.08 sd
Evidence
8 × 2
3 or more benchmarks, from 2 or more sources
Effort range
—
one configuration only
reasoning85th2/4 bench
math72nd3/7 bench
knowledge63rd1/1 bench
general56th1/1 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
GPQA diamond93.4 ±1.4highEpoch AI2026-07-08
OTIS Mock AIME 2024-202597.8 ±1.3highEpoch AI2026-07-08
LiveBench77.1default · 23 runsLiveBench2026-06-25
SimpleQA Verified48.3 ±1.6highEpoch AI2026-08-27
Chess Puzzles35.0 ±4.8highEpoch AI2026-10-13
FrontierMath-Tiers-1-3-v257.2 ±2.9highEpoch AI2026-07-09
FrontierMath-Tier-4-v224.4 ±6.8highEpoch AI2026-07-09
Furniture Assembly22.5 ±5.4highEpoch AI2026-09-24

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

Available from 31 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
xaivendor$2.00$6.00$0.30—500K500K—
302ai$2.00$6.00$0.50—500K500K—
abacus$2.00$6.00$0.30—500K33K—
cloudflare-ai-gateway$2.00$6.00$0.30—500K500K—
commandcode$2.00$6.00$0.50—500K500K—
crossmodel · x-ai$2.00$6.00$0.30$2.00500K500K—
daoxe$2.00$6.00$0.50—500K500K—
edenai$2.00$6.00$0.30—500K500K—
github_copilot · github-copilot$2.00$6.00$0.50—500K500K2026-10-19
github-copilot$2.00$6.00$0.50—500K128K—
impossibl$2.00$6.00$0.30—500K500K—
kilo · x-ai$2.00$6.00$0.30—500K450K—
llmgateway$2.00$6.00$0.30—500K500K—
llmgateway-providers$2.00$6.00$0.30—500K500K—
merge-gateway$2.00$6.00$0.50—500K500K—
nano-gpt · x-ai$2.00$6.00$0.30—500K450K—
ofox · x-ai$2.00$6.00$0.30—500K66K—
opencode$2.00$6.00$0.30—500K500K—
openrouter · x-ai$2.00$6.00$0.30—500K450K—
opper$2.00$6.00$0.50—500K500K—
orcarouter · grok$2.00$6.00$0.30—500K500K—
perplexity$2.00$6.00$0.30————
perplexity-agent$2.00$6.00$0.30—500K500K—
requesty$2.00$6.00$0.50$2.00500K500K—
tempr$2.00$6.00$0.30—500K500K—
vercel · spacexai$2.00$6.00$0.30—500K500K—
zenmux · x-ai$2.00$6.00$0.50—500K500K—
aihubmix$2.20$6.60$0.55—500K1M—
venice$2.27$6.80$0.34—500K32K—
kenari$2.2857$6.8571$0.3429—500K500K—
kyma · kyma$2.73$8.189——500K8K—

Price history

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

DateHostField$/M
2026-09-02aihubmixCache read$0.50
2026-10-22aihubmixCache read$0.55
2026-09-02nano-gpt · x-aiCache read$0.50
2026-10-19nano-gpt · x-aiCache read$0.30
2026-09-02opperCache read$0.30
2026-09-22opperCache read$0.50
2026-09-02orcarouter · grokCache read$0.50
2026-10-22orcarouter · grokCache read$0.30
2026-09-02aihubmixInput$2.00
2026-10-22aihubmixInput$2.20
2026-09-02kenariInputfree
2026-10-22kenariInput$2.2857
2026-09-02aihubmixOutput$6.00
2026-10-22aihubmixOutput$6.60
2026-09-02kenariOutputfree
2026-10-22kenariOutput$6.8571

More from xAI

most-hosted first