Grok 4.7
No shutdown before this date. Grok 4.7 stays on Amazon Bedrock until at least Sep 28, 2027.
≥ 11 mo- Earliest retirement
- ≥ 349 daysSep 28, 2027 · Amazon Bedrock
- Arena Text
- 1,443#46 of 128 · Arena
- GPQA Diamond
- 92.7%#19 of 108 · Epoch AI
- List price · $ per 1M
- $2.00 in $6.00 outxAI API · cached input $0.50
- Context window
- 500Ktokens
Dates on every platform
| Platform | Model ID and status | Deprecated | Shuts down | Replacement |
|---|---|---|---|---|
| Amazon BedrockAmazon Web Services: Amazon Bedrock ListFoundationModels, us-east-1 (opens in a new tab) · checked Oct 14, 2026 | xai.grok-4.7Active · also global.xai.grok-4.7, us.xai.grok-4.7 | – | ≥ 11 moNot sooner than | – |
| xAI APIxAI: grok-4.7 model page (opens in a new tab) · checked Oct 14, 2026us-east-1, us-west-2, us-central-1 | grok-4.7Active | – | None set | – |
In us-east-1, requests go through a cross-Region inference profile (listed in aliases).
Not measured on this platform under its terms.
On the Responses API, grok-4.7 always returns reasoning.encrypted_content, even when include does not list it.
Grok 4.7 Fast is the same model on faster infrastructure; it is available only in Cursor and Grok Build, not on the xAI API.
Batch API requests are not supported.
What breaks when you move off Grok 4.7
Intelligence
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| Arena Text | Arena | 1,443 ± 4 | #46 of 128 | Oct 8, 2026 |
| GPQA Diamond | Epoch AI | 92.7% ± 1.6% | #19 of 108 | Sep 22, 2026 |
| Arena WebDev | Arena | 1,639 ± 6 | #10 of 69 | Oct 8, 2026 |
| Arena Agent | Arena | 0 ± 0 | #15 of 35 | Oct 12, 2026 |
| FrontierMath Tier 4 | Epoch AI | 17.1% ± 5.9% | #45 of 58 | Sep 22, 2026 |
| FrontierMath Tiers 1-3 | Epoch AI | 53.0% ± 3.0% | #44 of 71 | Sep 22, 2026 |
| OTIS Mock AIME 2024-2025 | Epoch AI | 98.1% ± 1.4% | #20 of 105 | Sep 22, 2026 |
| SimpleQA Verified | Epoch AI | 56.0% ± 1.6% | #17 of 68 | Sep 22, 2026 |
Arena (arena.ai), https://arena.ai/leaderboard
Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource].
List prices
| Platform | Input | Cached | Output | In effect | Source |
|---|---|---|---|---|---|
Amazon Bedrockxai.grok-4.7 | $2.20 | $0.55 | $6.60 | Oct 1, 2026Current · Standard tier, in-Region or geographic cross-Region inference, which Bedrock prices 10% above global cross-Region inference. | Amazon Web Services: AWS Price List API: AmazonBedrock, us-east-1 (opens in a new tab) |
xAI APIgrok-4.7 | $2.00 | $0.50 | $6.00 | Sep 21, 2026Current · Requests whose prompt reaches 200k tokens are billed at twice these rates for all tokens in the request. The US regional endpoint charges a 10% premium. | xAI: Models (opens in a new tab) |
Change history
ReleaseGrok 4.7 available on Amazon BedrockAmazon Bedrock
Bedrock added Grok 4.7 as xai.grok-4.7, served through US and global cross-Region inference.
- Platform
- Amazon Bedrock
- Model
- Grok 4.7
Source: Amazon Web Services, Amazon Bedrock ListFoundationModels, us-east-1 (opens in a new tab)
ReleaseGrok 4.7 released on the xAI APIxAI API1 break
xAI released grok-4.7 on a new, larger base model than Grok 4.6, at the same token rates. It has a 500k context window, text and image input and a May 2026 knowledge cutoff.
- Platform
- xAI API
- Model
- Grok 4.7
- BehaviorOn the Responses API, grok-4.7 always returns reasoning.encrypted_content, even when include does not list it.
Source: xAI, Release Notes (opens in a new tab); xAI, Introducing Grok 4.7 (opens in a new tab); xAI, Grok 4.7 (opens in a new tab)