SpaceXAI
Grok 4.3 (high)
Grok 4.3 is a new model matching the scale of Grok 4.20 with an improved architecture and a December 2025 knowledge cutoff.
xAI model releasesModel Snapshot
TypeLanguage
ReleaseApr 30, 2026
Context1,000,000
Tagsreasoning, tool-use, implicit-caching, file-input
Overall
Rank #93 across 600
37.6
Coding
Rank #131 across 266
42.2
Blended Price
Rank #228 across 379
$1.56/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Max Output1,000,000
Streaming speed is not measured for this model yet.
Pricing
Blended$1.56/M
Input$1.25/M
Output$2.50/M
Catalog$1.25/M in / $2.50/M out
Metadata
Modalities
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 37.6 | #93 |
| Artificial Analysis Coding Index | coding | 42.2 | #131 |
| LiveBench Mathematics | math | 84.3% | #21 |
| GPQA | reasoning | 90.1% | #36 |