AllenAI: Olmo 3.1 32B Instruct

AllenAI: Olmo 3.1 32B Instruct

allenai · Released Jan 6, 2026
28
Our Score

Olmo 3.1 32B Instruct is a large-scale, 32-billion-parameter instruction-tuned language model engineered for high-performance conversational AI, multi-turn dialogue, and practical instruction following. As part of the Olmo 3.1 family, this variant emphasizes responsiveness to complex user directions and robust chat interactions while retaining strong capabilities on reasoning and coding benchmarks. Developed by Ai2 under the Apache 2.0 license, Olmo 3.1 32B Instruct reflects the Olmo initiative’s commitment to openness and transparency.

$0.20 / 1M Input Price
$0.60 / 1M Output Price
65,536 tokens Context Window
32B Parameters

Capabilities

Tool Use Function Calling

Architecture

ModalityText → Text
TokenizerOther
Parameters32B

Performance Indices

Source: Artificial Analysis

12.2 Intelligence Index
5.6 Coding Index
21.3 Agentic Index

Benchmark Scores

Evaluations

GPQA Diamond 53.9%
Graduate-level scientific reasoning
HLE 4.9%
Humanity's Last Exam
SciCode 16.7%
Scientific computing
IFBench 39.2%
Instruction following
τ²-Bench 21.3%
Conversational agent benchmark

Benchmark data from Artificial Analysis and Hugging Face

Model Information

OpenRouter ID allenai/olmo-3.1-32b-instruct
Providerallenai
Release Date January 6, 2026
Context Length65,536 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.20 $0.000200
Output $0.60 $0.000600

Live Performance

Live endpoint metrics — refreshed every 30 minutes.

418ms
Best Latency (TTFT)
14.5 tok/s
Best Throughput
0/1
Active Endpoints
Available via: DeepInfra