Grok 4.7
| Maker | xAI |
|---|---|
| Family | Grok |
| Released | 2026-09-21 |
| Context | 500K |
| Max output | 500K |
| Open weights | Closed |
|---|---|
| Modalities | text, image, pdf → text |
| Input / 1M | $2.00 |
| Output / 1M | $6.00 |
| Above 200K in | $4.00 / $12.00 |
| Review call | $0.0669 |
|---|---|
| Reasoning efforts | low, medium, high, xhigh |
| Hosts | xAI (Grok), OpenRouter |
| Model id | grok-4.7 |
CodePanel's benchmark has not run Grok 4.7 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 Claude Sonnet 5.5 from Anthropic, which caught 77% [64%–89%] of the known bugs at rank 1 of 17, with a measured review cost of $0.0571. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0669 on Grok 4.7 and $0.0766 on Claude Sonnet 5.5, so this model's call is 13% less than that one's.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| xAI (Grok) | grok-4.7 | $2.00 | $6.00 |
Source: xAI pricing, Oct 16, 2026
| Model | Maker | Input / 1M | Output / 1M | Review call | Context | Bugs caught |
|---|---|---|---|---|---|---|
| Qwen3.8 Max (OpenRouter) | Qwen | $2.00 | $6.00 | $0.0669 | 1M | – |
| Kimi K2.7 Code Highspeed | Moonshot | $1.90 | $8.00 | $0.0691 | 262.1K | – |
| Mistral Medium 3.5 | Mistral | $1.50 | $7.50 | $0.0574 | 256K | – |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $10.00 | $0.0766 | 1M | 77% |
Updated Oct 23, 2026