# Grok 4.6 vs Grok 4.7

As of October 21, 2026, Grok 4.6 and Grok 4.7 cost the same: $2.00 per 1M input tokens and $6.00 per 1M output tokens, and both have a 500K-token context window.

- Page: https://models.litellm.ai/compare/grok-4.6-vs-grok-4.7
- Grok 4.6: https://models.litellm.ai/models/grok-4.6
- Grok 4.7: https://models.litellm.ai/models/grok-4.7

## Side by side

| | Grok 4.6 | Grok 4.7 |
|---|---|---|
| Input, per 1M tokens | $2.00 | $2.00 |
| Output, per 1M tokens | $6.00 | $6.00 |
| Cache read, per 1M tokens | $0.50 | $0.50 |
| Cache write, per 1M tokens | – | – |
| Context window | 500,000 tokens | 500,000 tokens |
| Max output | 500,000 tokens | 500,000 tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 8 | 6 |
| Price shown is from | xAI | xAI |
| Added to LiteLLM | August 13, 2026 | September 21, 2026 |

Headline prices in USD per 1M tokens, from LiteLLM's model price file.

## Cheapest provider for each

- Grok 4.6: xAI at $2.00 input per 1M tokens (`xai/grok-4.6`)
- Grok 4.7: xAI at $2.00 input per 1M tokens (`xai/grok-4.7`)

## Benchmark scores

| Benchmark | Grok 4.6 | Grok 4.7 |
|---|---|---|
| Epoch Capabilities Index (Overall) | 156.6 | 154.4 |
| FrontierCode (Coding and agents) | 48.0% | 47.6% |
| FrontierSWE (Coding and agents) | 25.3% (xhigh) | 29.5% (xhigh) |
| APEX-Agents (Coding and agents) | 65.3% | 54.6% |
| GPQA Diamond (Reasoning and knowledge) | 94.0% (high) | 92.7% (xhigh) |
| ARC-AGI-2 (Reasoning and knowledge) | 67.1% (xhigh) | 61.4% (xhigh) |
| SimpleQA Verified (Reasoning and knowledge) | 49.3% (high) | 56.0% (xhigh) |
| FrontierMath (tiers 1-3) (Math) | 66.0% (xhigh) | 53.0% (xhigh) |
| FrontierMath (tier 4) (Math) | 31.7% (xhigh) | 17.1% (xhigh) |
| OTIS Mock AIME 2024-2025 (Math) | 99.2% (xhigh) | 98.1% (xhigh) |

From the Epoch AI Benchmarking Hub (https://epoch.ai/benchmarks), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), data as of September 22, 2026: Epoch's own runs and results it collects from each benchmark's leaderboard. Higher is better.

## FAQ

### Which is cheaper, Grok 4.6 or Grok 4.7?

They cost the same: $2.00 per 1M input tokens and $6.00 per 1M output tokens, as of October 21, 2026.

### Which has the larger context window, Grok 4.6 or Grok 4.7?

Both have a 500,000-token context window.

### Can I switch from Grok 4.6 to Grok 4.7 without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "xai/grok-4.6" to "xai/grok-4.7", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.