Compact GPT model for low-latency assistance and high-volume workloads
Specification
most-agreed values
Context
128K
Max output
66K
Released
2024-01-01
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, audio
Output
text
Price
US dollars per million tokens · most-agreed
Input
$1.292
Output
$4.998
Cache read
$0.323
Quality
3 benchmarks · 1 source
Composite
58th
percentile of 334 scored models
Rank
140 / 334
±0.05 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning62nd1/4 bench
math57th2/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| MATH level 5 | 83.5 ±1.0 | default | Epoch AI | 2025-02-06 |
| GPQA diamond | 65.7 ±3.4 | default | Epoch AI | 2025-02-07 |
| FrontierMath-v1 | 0.0 ±0.0 | default | Epoch AI | 2025-03-07 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nano-gpt | $1.292 | $4.998 | $0.323 | — | 128K | 66K | — |
More from Google
most-hosted first