Grok 4.3
| Maker | xAI |
|---|---|
| Family | Grok |
| Released | 2026-04-30 |
| Context | 1M |
| Max output | 30K |
| Open weights | Closed |
|---|---|
| Modalities | text, image, pdf → text |
| Input / 1M | $1.25 |
| Output / 1M | $2.50 |
| Above 200K in | $2.50 / $5.00 |
| Review call | $0.0388 |
|---|---|
| Reasoning efforts | none, low, medium, high, xhigh |
| Hosts | xAI (Grok), OpenRouter |
| Model id | grok-4.3 |
CodePanel's benchmark has not run Grok 4.3 as a pull-request reviewer yet, so this page has no recall, false-alarm or measured-cost figures for it. The methodology explains how ranked models are scored.
No xAI model is in the run yet. The ranked model closest to it in list price is Kimi K2.7 Code (Workers AI) from Moonshot, which caught 38% [28%–47%] of the known bugs at rank 11 of 17, with a measured review cost of $0.0567. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0388 on Grok 4.3 and $0.0346 on Kimi K2.7 Code (Workers AI), so this model's call is 12% more than that one's.
A newer Grok model is current: Grok 4.7.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| xAI (Grok) | grok-4.3 | $1.25 | $2.50 |
Source: xAI pricing, Oct 16, 2026
| Benchmark | Score | Range | Setting | Source | Date |
|---|---|---|---|---|---|
| Arena WebDev | 1358 Arena rating | 1351 to 1364 | – | LMArena CC BY 4.0 | Oct 16, 2026 |
| Model | Maker | Input / 1M | Output / 1M | Review call | Context |
|---|---|---|---|---|---|
| Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | $0.0383 | 200K |
| Inkling | Thinking Machines | $1.00 | $4.05 | $0.036 | 524.3K |
| Muse Spark 1.2 | Meta | $1.25 | $4.25 | $0.043 | 1M |
| Kimi K2.6 | Moonshot | $0.95 | $4.00 | $0.0346 | 262.1K |
Updated Oct 23, 2026