Legacy model retained for compatibility with older integrations
Specification
most-agreed values
Context
128K
Max output
8K
Released
2024-08-14
Knowledge cutoff
2024-08
Retires
—
Open weights
no
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$4.50
Output
$14.00
Cache read
$2.50
Quality
1 benchmark · 1 source
Composite
38th
percentile of 344 scored models
Rank
215 / 344
±0.15 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
—
one configuration only
coding31st1/3 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| Aider polyglot | 36.2 | default · aider diff · 2 runs | Aider | 2025-02-15 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 2 hosts
More from OpenAI
most-hosted first