Grok 4.6
API ID grok-4.6
grok-4.6 is an xAI model, released August 2026. Standard price: from $2.00 input and from $6.00 output per 1M tokens.
- Status
- Active
- Released
- August 2026
- Shutdown
- none announced
- Replacement
- —
No deprecation or shutdown date has been announced as of October 15, 2026.
Benchmarks
Scores as each source published themComparing with Grok 4.5, the previous model in this line. A score is compared only with the same benchmark from the same source, at the same setting where both have it. Full comparison: prices, limits, features
Arena
| Arena | Grok 4.6 | Grok 4.5 | Change | Rank | Date | Source |
|---|---|---|---|---|---|---|
TextBy category
| 1455 ±5 | 1466 ±4 | −11 | 70 of 415 28,124 votes | Oct 13, 2026 | source |
| Text: Coding | 1510 ±8 | 1514 ±7 | −4 within range | 60 of 410 7,047 votes | Oct 13, 2026 | source |
| WebDev | 1617 ±8 | 1553 ±7 | +64 | 25 of 142 9,774 votes | Oct 13, 2026 | source |
| Vision | 1262 ±9 | 1280 ±7 | −18 | 45 of 165 6,495 votes | Oct 9, 2026 | source |
| Document | 1461 ±12 | 1464 ±9 | −3 within range | 24 of 44 2,258 votes | Sep 13, 2026 | source |
| Agent | 0.012 ±0.011 | 0.001 ±0.011 | +0.011 within range | 29 of 54 28,687 sessions | Oct 14, 2026 | source |
Rated as grok-4.6-high (high effort); Grok 4.5 as grok-4.5. Some were rated at different settings; ratings on one arena share one scale, so the difference still reads directly. Text, WebDev, Vision and Document ratings come from people voting between two anonymous answers; Text, Vision and Document are style-controlled, as on arena.ai. Agent is Arena's separate score for real agent sessions, on its own scale. Not rated on Search, where Grok 4.5 is. Data: Arena (arena.ai), CC BY 4.0.
Epoch AI
| Benchmark | Grok 4.6 | Grok 4.5 | Change | Setting | Run | Source |
|---|---|---|---|---|---|---|
| FrontierMath Tier 4 | 31.7% | 24.4% | +7.3 pts | xhigh effort (vs high effort) | Aug 14, 2026 | source |
| FrontierMath Tiers 1-3 | 66.0% | 57.2% | +8.8 pts | xhigh effort (vs high effort) | Aug 14, 2026 | source |
GPQA DiamondOther settings
| 94.0% | 93.4% | +0.6 pts | high effort | Aug 12, 2026 | source |
OTIS Mock AIME 2024-2025Other settings
| 99.2% | 97.8% | +1.4 pts | xhigh effort (vs high effort) | Aug 14, 2026 | source |
SimpleQA VerifiedOther settings
| 49.3% | 48.3% | +1.0 pts | high effort | Aug 27, 2026 | source |
Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.
On cloud platforms
All platform dates| Platform | Platform ID | State | Shutdown | Time left | Replacement | Source |
|---|---|---|---|---|---|---|
| Amazon Bedrock | xai.grok-4.6 | Active | not before Aug 18, 2027 | — | source |
Read daily from each platform's own pages. The shutdown date and countdown on this page use xAI's own date.
Price history
USD per 1M tokens, standard tierWe started recording this model's prices on Oct 5, 2026. The history grows with each daily check.
Show as a table
| From | Type | Price |
|---|---|---|
| Oct 5, 2026 | Input | $2.00 |
| Oct 5, 2026 | Output | $6.00 |
Prices
USD per 1M tokens, every type and band, by tier| Type | Band | Price $/1M | In effect |
|---|---|---|---|
| Standard | |||
| input | up to 200k prompt | $2.00 | |
| input | over 200k prompt | $4.00 | |
| cached input | up to 200k prompt | $0.50 | |
| cached input | over 200k prompt | $1.00 | |
| output | up to 200k prompt | $6.00 | |
| output | over 200k prompt | $12.00 | |
Changelog
Changes we detected on xAI's pagesNo changes recorded yet.
Email alerts
Get an email if grok-4.6 changes
We'll email you the same morning we spot a deprecation notice, a new or moved shutdown date, a price change, or the model leaving xAI's model list.
No password: one email to confirm, and you can unsubscribe any time. Privacy
Last checked · Sources: xAI pricing, xAI notices, xAI release notes