Compact GPT model for low-latency assistance and high-volume workloads
Specification
most-agreed values
Context
2.1M
Max output
8K
Released
2025-02-05
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image, audio
Output
text
Price
US dollars per million tokens · most-agreed
Input
$1.989
Output
$7.956
Cache read
$0.4973
Quality
1 benchmark · 1 source
Composite
36th
percentile of 334 scored models
Rank
213 / 334
±0.11 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
—
one configuration only
coding29th1/3 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| Aider polyglot | 35.6 | default · aider whole | Aider | 2025-02-25 |
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 | $1.989 | $7.956 | $0.4973 | — | 2.1M | 8K | — |
More from Google
most-hosted first