Skip to content

Grok 4.5

ModelActive
by xAI · family “grok”

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. (description from the OpenRouter listing)

in: textin: imagein: fileout: textReasoningTool useStructured output
Epoch Capabilities Index
154.0 #34 of 268
90% CI 152.3 – 156.1
Listing ↗
Released
8 Jul 2026
Context window
500K tokens
Max output
450K tokens
Input $ / 1M tokens
$2.00
Output $ / 1M tokens
$6.00
Cached input $ / 1M
$0.30
Each benchmark shown separately with its own source

Benchmark results (15)

All benchmarks
BenchmarkDomainScorevs best recordedSettingRunSource
Furniture Assemblymultimodal22.5% ±5.4
27%
high24 Sep 2026Epoch ↗
LMCAagents45.2%
66%
high—External ↗
DTBenchreasoning96.5%
98%
high—External ↗
Surface Evolver Benchscience74.4%
78%
high—External ↗
FrontierMath-Tiers-1-3-v2-Privatemath57.2% ±2.9
61%
high9 Jul 2026Epoch ↗
FrontierMath-Tier-4-v2-Privatemath24.4% ±6.8
25%
high9 Jul 2026Epoch ↗
DeepSWEcoding53.8%
73%
high—External ↗
PostTrainBenchagents23.4%
56%
high—External ↗
ProofBenchmath31.0%
31%
high—External ↗
Chess Puzzlesgames36.0% ±4.8
50%
high8 Jul 2026Epoch ↗
SimpleQA Verifiedknowledge48.3% ±1.6
64%
high27 Aug 2026Eval log ↗
ARC-AGI-2reasoning52.6%
55%
high—External ↗
OTIS Mock AIME 2024-2025math97.8% ±1.3
98%
high8 Jul 2026Epoch ↗
GPQA diamondscience93.4% ±1.4
98%
high8 Jul 2026Epoch ↗
ARC-AGIreasoning85.7%
87%
high—External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

4 recorded prices on 17 Jul 2026 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 3h ago. Steps show when the price changed.

Events