xAI: Grok 4.5
Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.
Everything else
| Max output | — |
|---|---|
| Input / 1M | $2 |
| Output / 1M | $6 |
| Cache read / 1M | $0.3 |
| Cache write / 1M | — |
| 1M in + 1M out | $8 |
| Takes | text, image, file |
| Returns | text |
| Tools | yes |
| Reasoning | always on · high, medium, low |
| Open weights | no |
| Released | 2026-07-08 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | x-ai/grok-4.5 |
Benchmarks
| source | epoch |
|---|---|
| eci | 153.61 |
| confidence | Likely |
| accessibility | API access |
| gpqa | 0.934 |
| gpqaStderr | 0.0143 |
| aime | 0.978 |
| aimeStderr | 0.0127 |
| simpleQA | 0.535 |
| simpleQAStderr | 0.0158 |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.