Olmo 3.1 32B Instruct

Jan 2026
Olmo 3.1 32B Instruct
Compare in
on
—per task?
$0.20 / $0.60per 1M in / out?
—output speed?
66Kcontext

Rankingin non-thinking mode?

Strong at

C
Tool calling#186 of 242Reasoning#272 of 334Science#245 of 312Knowledge#222 of 318Instructions#161 of 245

Alternatives?

ModelScoreCostPer taskWhat changes
CheaperClaude Haiku 5.5max×6.7-33%$0.21Remove sampling parameters+5BetterGPT-6 Lunalow×3.3-33%$0.005Function calling only with none · Chat Completions+3OpenQwen3.8 27Bxhigh×5.2+219%$1.01max_tokens range · QwenCloud+4CheaperMiniMax M3.1 Flashthinking×6.6-13%$0.22Complete model response must be appendedCheaperGLM 5.3 FlashmaxOpen×6.4-21%$0.28Memory (4-bit): 19 GB → 193 GB+5

Run it yourself

estimate
Fits on✗ 8 GB (phone, laptop)✗ 16 GB✓ 24 GB GPU · compressed✓ 48 GB GPU · 8-bit✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use

Benchmarks

all categories
Chat & Knowledge
Humanity's Last Exam5#274
AA Omniscience Index-52.4#223
CritPt (physics)0#180
AA Intelligence Index 4.3.2≈6.5#287
AA Omniscience · Accuracy12.1#268
AA Omniscience · Hallucination Rate73.2#137
GPQA Diamond53.9#248
Coding
Terminal-Bench Hard (version unstated)0#213
Agents & Tool Use
τ²-bench · AA21.3#188
Writing & Language
IFBench (instructions)39.2#162

FAQ

How much does Olmo 3.1 32B Instruct cost?›

$0.20 per 1M input tokens and $0.60 per 1M output tokens (cheapest host: DeepInfra).

Is Olmo 3.1 32B Instruct free to use?›

There is no free API; the cheapest paid price is $0.20 per 1M input tokens. The weights are open, so you can run it yourself.

How good is Olmo 3.1 32B Instruct, and what is it best at?›

#272 of 334 in Chat & Knowledge, #210 of 239 in Coding, #186 of 242 in Agents & Tool Use, #134 of 195 in Writing & Language.

Is Olmo 3.1 32B Instruct better than Sarvam 30B?›

On AA Intelligence Index 4.3.2, Olmo 3.1 32B Instruct scores 6.5 vs 6.6 — about the same.

How can I use Olmo 3.1 32B Instruct?›

Through the API of DeepInfra.

What is the context window of Olmo 3.1 32B Instruct?›

66K tokens.

When was Olmo 3.1 32B Instruct released? Is there a newer version?›

Released 2026-01-13. It is the current version in its line.

Is Olmo 3.1 32B Instruct open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run Olmo 3.1 32B Instruct locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

Can Olmo 3.1 32B Instruct read images?›

No, it accepts text only.

What is Olmo 3.1 32B Instruct?›

Olmo 3.1 32B Instruct is an open-weights language model from Allen Institute for AI, released Jan 2026.

What are the best alternatives to Olmo 3.1 32B Instruct?›

Claude Haiku 5.5 (cheaper), GPT-6 Luna (better), Qwen3.8 27B (open weights).