Loading...
Loading...
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
Input
$0.03
per 1M tokens
Output
$0.14
per 1M tokens
Blended
$0.06
per 1M tokens
Cheaper than 89% of models. Median price is $0.56/1M tokens.
Daily
$0.06
Monthly
$1.73
285
tokens/sec
Faster than 95% of models
0.38
seconds
Faster than 92% of models
7.40
seconds
Faster than 43% of models
Market Median
86 tok/s
232% faster
Median TTFT
1.07s
65% faster
Throughput/Dollar
4953
tok/s per $/1M
Speed Comparison
Context Window
131K
tokens
Larger than 33% of models
Max Output
131K
tokens
100% of context
7.2M
4.6K
24-48 GB
A6000 / M3 Ultra
Quality Index
24.5
200th of 507
Top 40%
Coding Index
18.5
211th of 417
Top 51%
Math Index
89.3
30th of 269
Top 12%
Price/1M
$0.06
70th cheapest
90% below median
Top 11%
Speed
285 tok/s
Top 5%
TTFT
0.38s
Context Window
131K
201st largest
Top 67%