Fast Grok model for responsive chat, reasoning, and tool-assisted work
Specification
most-agreed values
Context
131K
Max output
8K
Released
2025-04-11
Knowledge cutoff
2024-06
Retires
2026-05-01
Open weights
no
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.30
Output
$0.50
Cache read
$0.075
Quality
5 benchmarks · 1 source
Composite
62nd
percentile of 344 scored models
Rank
131 / 344
±0.06 sd
Evidence
5 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning76th1/4 bench
math58th4/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| MATH level 5 | 89.5 ±0.8 | default · 2 runs | Epoch AI | 2025-04-10 |
| GPQA diamond | 75.4 ±2.8 | default · 2 runs | Epoch AI | 2025-05-26 |
| OTIS Mock AIME 2024-2025 | 70.0 ±7.3 | default · 2 runs | Epoch AI | 2025-04-10 |
| FrontierMath-Tier-4-2025-07-01 | 0.0 ±0.0 | default | Epoch AI | 2025-07-01 |
| FrontierMath-v1 | 2.2 ±0.0 | default · 4 runs | Epoch AI | 2025-04-10 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 5 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| azure_ai | $0.25 | $1.27 | — | — | — | — | 2026-05-01 |
| helicone | $0.30 | $0.50 | $0.075 | — | 131K | 131K | — |
| oci · oci | $0.30 | $0.50 | — | — | 131K | 131K | — |
| poe | $0.30 | $0.50 | $0.075 | — | 131K | 8K | — |
| vercel_ai_gateway · vercel-ai-gateway | $0.30 | $0.50 | — | — | 131K | 131K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | azure_ai | Input | $0.25 |
| 2026-09-26 | azure_ai | Input | $0.25 |
| 2026-09-02 | azure_ai | Output | $1.27 |
| 2026-09-26 | azure_ai | Output | $1.27 |
More from xAI
most-hosted first