AllenAI: Olmo 3 32B Think

allenai/olmo-3-32b-think

JSONReasoningStreaming

Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...

Pricing

Input

$0.15 / 1M

Output

$0.5 / 1M

Specs

Context

65,536 tokens

Input

text

Output

text

Released: 2025-11

Supported parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p

Open weights · HuggingFace

3,612 downloads/mo

171 likes

apache-2.0 text-generation

arXiv:2512.13961

View on HuggingFace →

Use this model →