allenai Open weights Reasoning
Olmo 3 32B Think pricing & benchmarks
Released Nov 21, 2025 · served by 0 providers
Input / 1M tokens$0.150
Output / 1M tokens$0.500
Context window66K
Cached input—
1M in + 300K out$0.30
What Olmo 3 32B Think is
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...
- Model ID:
allenai/olmo-3-32b-think - Modality: text->text
- Tool calling: not supported · Structured output: supported
- Weights:
allenai/Olmo-3-32B-Thinkon Hugging Face
FAQ
How much does the Olmo 3 32B Think API cost?
$0.150 per 1M input tokens and $0.500 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.30.
Is Olmo 3 32B Think free?
No. It is a paid model starting at $0.150 per 1M input tokens, though some providers offer trial credits.
Can I self-host Olmo 3 32B Think?
Yes — weights are published as allenai/Olmo-3-32B-Think on Hugging Face, so you can run it on your own hardware.