Grok 4.6 vs Grok 4.7
Grok 4.6 is from xAI. Grok 4.7 is from xAI. Grok 4.6 costs $6.00 per million output tokens. Grok 4.7 costs $6.00. Grok 4.6 leads on the Epoch Capabilities Index: Grok 4.6 scores 156.9 and Grok 4.7 scores 154.6. A typical request, about 1,000 words in and 400 words out, costs $0.0056 on Grok 4.6 and $0.0056 on Grok 4.7.
Prices updated . Benchmarks updated .
| Grok 4.6 | Grok 4.7 | |
|---|---|---|
| Lab | xAI | xAI |
| You send / 1M | $2.00 | $2.00 |
| It replies / 1M | $6.00 | $6.00 |
| Context | 200K | 500K |
| Launched | 2026-08-12 | 2026-09-21 |
| Weights | Closed | Closed |
| Typical request | $0.0056 | $0.0056 |
| ECI | 156.9 | 154.6 |
| GPQA | 94.0% | 92.7% |
| ARC-AGI-2 | 67.1% | 61.4% |
| HLE | n/a | n/a |
| AIME | 99.2% | 98.1% |
| SimpleQA | 49.3% | 56.0% |
| CritPt | 19.7% | 18.0% |
| Arena | 1,429 | 1,398 |
| Arena web | 1,616 | 1,637 |
Which is cheaper?
Grok 4.6 and Grok 4.7 cost the same for output tokens, $6.00 per million. Input tokens are $2.00 per million for Grok 4.6 and $2.00 per million for Grok 4.7. A typical request, about 1,000 words in and 400 words out, costs $0.0056 on Grok 4.6 and $0.0056 on Grok 4.7.
Which scores higher?
Grok 4.6 scores higher on Epoch Capabilities Index: 156.9 against 154.6 for Grok 4.7. That index is an independent composite from Epoch AI. Lab-reported scores are kept off this comparison. Context windows are 200K and 500K. Prices are US dollars per million tokens at current public rates.
Verdict
Grok 4.6 scores higher on Epoch Capabilities Index (156.9 vs 154.6). A public token price is missing for at least one model, so this page does not call a cheaper winner. Context is 200K for Grok 4.6 and 500K for Grok 4.7. Use the model pages for every score on file, including lab-reported numbers.
FAQ
Which is cheaper, Grok 4.6 vs Grok 4.7?
Grok 4.6 and Grok 4.7 cost the same for output tokens, $6.00 per million. Input tokens are $2.00 per million for Grok 4.6 and $2.00 per million for Grok 4.7. A typical request, about 1,000 words in and 400 words out, costs $0.0056 on Grok 4.6 and $0.0056 on Grok 4.7.
Which scores higher, Grok 4.6 vs Grok 4.7?
Grok 4.6 scores higher on Epoch Capabilities Index: 156.9 against 154.6 for Grok 4.7. That index is an independent composite from Epoch AI. Lab-reported scores are kept off this comparison. Context windows are 200K and 500K. Prices are US dollars per million tokens at current public rates.
What is the verdict for Grok 4.6 vs Grok 4.7?
Grok 4.6 scores higher on Epoch Capabilities Index (156.9 vs 154.6). A public token price is missing for at least one model, so this page does not call a cheaper winner. Context is 200K for Grok 4.6 and 500K for Grok 4.7. Use the model pages for every score on file, including lab-reported numbers.
Open this pair in the comparison view
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.