Compact GPT model for low-latency assistance and high-volume workloads
Specification
most-agreed values
Context
1M
Max output
66K
Released
2025-03-25
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image, audio
Output
text
Price
US dollars per million tokens · most-agreed
Input
$2.50
Output
$10.00
Cache read
$0.25
Quality
1 benchmark · 1 source
Composite
93rd
percentile of 334 scored models
Rank
24 / 334
±0.11 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
—
one configuration only
coding93rd1/3 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| Aider polyglot | 72.9 | default · aider diff-fenced | Aider | 2025-04-12 |
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 | $2.50 | $10.00 | $0.25 | — | 1M | 66K | — |
More from Google
most-hosted first