Skip to main content
Back to Explore

Olmo 3.1 32B Think

Allen AI·Released 2025-12-12
Open Source66K ctx

About

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.

Pricing

Input

$0.15

per 1M tokens

Output

$0.50

per 1M tokens

Blended

$0.24

per 1M tokens

Cheaper than 67% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.24

Monthly

$7.13

vs. Similar Models

Pixtral LargeQ:0.0
$3.00+1163%
Ring-flash-2.0Q:+0.1
$0.25+4%
GPT-5 nano (minimal)Q:-0.1
$0.14-42%
OpenAI: GPT-4 TurboQ:-0.2
$15.00+6216%

Performance

98

tokens/sec

Faster than 52% of models

0.44

seconds

Faster than 93% of models

20.91

seconds

Faster than 24% of models

Market Median

94 tok/s

4% faster

Median TTFT

1.10s

60% faster

Throughput/Dollar

411

tok/s per $/1M

Speed Comparison

OpenAI: GPT-5 Mini
98 tok/s+0%
OpenAI: GPT-5
98 tok/s-0%
Grok 4 Fast (Non-reasoning)
98 tok/s+0%

Context Window

66K

tokens

Larger than 13% of models

Max Output

66K

tokens

100% of context

Benchmarks

MMLU-Pro
76.3%
GPQA Diamond
59.1%
HLE
6.0%
LiveCodeBench
69.5%
SciCode
29.3%
TerminalBench Hard
0.0%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
77.3%
IFBench
66.0%
Long Context Recall
0.0%
Tau2
0.0%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models