AllenAI: Olmo 3.1 32B Think

Allen AIID: allenai/olmo-3.1-32b-think

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 per 1M Tokens

Input (Prompt)$0.15
Output (Completion)$0.50
Cache ReadFree
Cache WriteFree
ImageN/A

Specifications

Context Length66K
Max Output Tokens66K
Input ModalitiesText
Output ModalitiesText
TokenizerOther
Instruct TypeN/A
Top Provider Context66K
Top Provider Max Output66K
ModeratedNo

Compare this model

See how AllenAI: Olmo 3.1 32B Think stacks up against other models.

vs AllenAI: Olmo 3.1 32B Instructvs AllenAI: Olmo 3 32B Thinkvs AllenAI: Olmo 2 32B Instruct

More from Allen AI

AllenAI: Olmo 3.1 32B Instruct
Input$0.20
Context66K
AllenAI: Olmo 3 32B Think
Input$0.15
Context66K
AllenAI: Olmo 2 32B Instruct
Input$0.05
Context128K

Last updated: March 23, 2026

First tracked: March 23, 2026