Grok 4.1 Fast
retiredxAI · Small
Low-cost, fast Grok variant with 2M context. Retired May 15, 2026; traffic redirected to Grok 4.3.
- Strengths
- Fast, low-cost variant with a 2M-token context.
- Best for
- High-volume, long-context tasks where speed and price lead.
- Limitations
- Retired May 2026; traffic redirected to Grok 4.3.
Input / 1M
$0.2
Output / 1M
$0.5
Cached input / 1M
$0.05
Context window
2M
Where it sits
61% below the small median
blended $/Mtok across 5 small models
Output costs 2.5× input
$0.2 in / $0.5 out per 1M
Cached input saves 75%
$0.05 vs $0.2 per 1M fresh
Held flat since launch (Nov 2025)
no blended price change recorded
Computed live from current prices and this model's history — not hand-written, so it stays accurate as prices move.
Price history
Only one price on record so far — the history chart appears once a price changes.
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 19 Nov 2025 | $0.2 | $0.5 | $0.05 | docs.x.ai |