Loading...
Loading...
Olmo 3.1 32B Think is a large-scale, 32-billion-parameter model designed for deep reasoning, complex multi-step logic, and advanced instruction following. Building on the Olmo 3 series, version 3.1 delivers refined reasoning behavior and stronger performance across demanding evaluations and nuanced conversational tasks. Developed by Ai2 under the Apache 2.0 license, Olmo 3.1 32B Think continues the Olmo initiative’s commitment to openness, providing full transparency across model weights, code, and training methodology.
Quality Index
13.9
290th of 442
Top 66%
Coding Index
9.8
266th of 352
Top 76%
Math Index
77.3
74th of 268
Top 28%
Price/1M
$0.00
1st cheapest
100% below median
Top 27%
Speed
92 tok/s
Top 30%
TTFT
0.60s
Context Window
66K
271st largest
Top 80%
Input
$0.00
per 1M tokens
Output
$0.00
per 1M tokens
Blended
$0.00
per 1M tokens
Cheaper than 73% of models. Median price is $0.31/1M tokens.
Daily
$0.00
Monthly
$0.00
92
tokens/sec
Faster than 70% of models
0.60
seconds
Faster than 40% of models
22.40
seconds
Faster than 11% of models
Market Median
46 tok/s
101% faster
Median TTFT
0.42s
43% slower
Speed Comparison
Context Window
66K
tokens
Larger than 20% of models
Max Output
66K
tokens
100% of context