Identity
- Status
- active
- Developer ID
allenai/Olmo-3-32B-Think- Released
- Not reported
- Version
- Olmo-3-32B-Think
- License
- apache-2.0
Ai2Olmo 3 32B Think
Olmo-3-32B-Think is an open-weight language model published by Ai2.
- Token context
- 66K tokens
- Inputs
- Text
- Outputs
- Text
- Released
- Not reported
Benchmark Market Position
Intelligence, Cost, and Efficiency
Rank #43 of 57
Claude Opus 5.5
GPT-5.5 Pro
Gemini 3.8 Flash- GPT-6.1 Sol
- GPT-6 Astra
Qwen3.8 Max
DeepSeek V4.1 Flash- Gemini 3.1 Pro
- GPT-5.6 Terra
Grok 4.7
ERNIE 5.1
Kimi K3
GLM 5.3- Qwen3.8 Flash
- Qwen3.7 Plus
- DeepSeek V4 Pro
- GLM 5.3 Flash
Mistral Large 4- Gemma 4 31B
- Qwen3.8 27B
- Qwen3.5 397B A17B
Hy3- Gemma 4 26B A4B
Inkling- Mistral Large 3
- GPT-6 Luna
NVIDIA Nemotron 3 Ultra 550B A55B BF16- Inkling Small
MiniMax M3- Kimi K2.7 Code
- GPT-5.4 Mini
- Gemini 3.5 Flash Lite
- Qwen3.5 35B A3B
- GPT-5.4 Nano
Muse Glimmer 30B
Solar Pro 4- DeepSeek R1
- Olmo 3 32B Think
Nova 2 Lite
Command A
Granite 4.2 30B- Granite 4.2 3B
- Granite 4.2 8B
- Llama 4 Maverick 17B 128E Instruct
- Llama 4 Scout 17B 16E Instruct
phi-4- NVIDIA Nemotron 3 Nano 30B A3B BF16
- NVIDIA Nemotron 3.5 Lightning 30B A3B
- GPT-4o
- GPT-4o Mini
- gpt-oss-120b
- gpt-oss-20b
Not ranked in current cohort
Not ranked in current cohort
The orange outline marks Olmo 3 32B Think. Each available panel preserves its real rank and value; missing benchmark or pricing inputs remain explicitly unranked.
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 OpenrouterAvailable | $0.15 | $0.50 | — | — | Aug 28, 2026 | Provider-reported |
Benchmarks
All benchmark results →| LMArena Text Arenatext-2026-10-15-a64ca3b12b6e | 1,299.42 | — | 5,831 | olmo-3-32b-think; 95% CI [1291.17882644, 1307.65677276]; votes 5831; rank 248unknown | Original sourcewinner eligible | Third-party benchmark |
At a Glance
Model Facts
Capacity
- Token context
- 66K tokens
- Maximum output
- 33K tokens
- Total parameters
- 32.2B
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- Yes
- Vision
- No
- Tool calling
- No
- Capabilities
- chat, generation, reasoning
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesallenai/Olmo-3-32B-Think, allenai/Olmo-3-32B-Think
Explicit Unknowns
- Release date
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
allenai/Olmo-3-32B-Think developer model repositoryAi2 · observed Aug 28, 2026OpenRouter allenai/olmo-3-32b-think model APIOpenRouter · observed Aug 28, 2026allenai/Olmo-3-32B-Think config.json at f2edda15216eAi2 · observed Aug 28, 2026allenai/Olmo-3-32B-Think README.md at f2edda15216eAi2 · observed Aug 28, 2026allenai/Olmo-3-32B-Think immutable Hub API metadataAi2 · observed Aug 28, 2026allenai/Olmo-3-32B-Think generation_config.json at f2edda15216eAi2 · observed Aug 28, 2026allenai/Olmo-3-32B-Think tokenizer_config.json at f2edda15216eAi2 · observed Aug 28, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
| vs | cross-developer peerstext | ||
| vs | Phi-4 ReasoningMicrosoft | cross-developer peerstext | |
| vs | family variantstext | ||
| vs | family variantstext | ||
| vs | family variantstext | ||
| vs | DeepSeek R1DeepSeek | cross-developer peerstext | |
| vs | Muse Glimmer 30BMeta | cross-developer peerstext | |
| vs | Phi-4 Mini ReasoningMicrosoft | cross-developer peerstext | |
| vs | Codestral 22B v0.1Mistral AI | cross-developer peerstext | |
| vs | Mistral Small 4 119B 2603Mistral AI | cross-developer peerstext | |
| vs | cross-developer peerstext | ||
| vs | gpt-oss-20bOpenAI | cross-developer peerstext |
Questions
Olmo 3 32B Think FAQs
What is Olmo 3 32B Think?+
Olmo-3-32B-Think is an open-weight language model published by Ai2. It is developed by Ai2 and its current sourced lifecycle status is active.
What inputs and outputs does Olmo 3 32B Think support?+
Olmo 3 32B Think's current record lists Text as input and Text as output.
How much context does Olmo 3 32B Think support?+
The current record lists a 66K-token context window and a maximum output of 33K tokens.
Is Olmo 3 32B Think available through an API?+
Olmo 3 32B Think is marked as API-available. The directly sourced provider records currently include Openrouter.
How large is Olmo 3 32B Think?+
The current record lists 32.2B total parameters and an unknown active parameter count. Its architecture is Olmo3ForCausalLM.
What capabilities and tasks does Olmo 3 32B Think support?+
Olmo 3 32B Think's recorded capabilities are chat, generation, and reasoning. Its supported tasks are text.
How much does Olmo 3 32B Think cost through an API?+
The lowest directly sourced prices currently attached to Olmo 3 32B Think are $0.15 per million input tokens through Openrouter and $0.50 per million output tokens through Openrouter. Prices are provider-specific and should be checked against each cited observation date.
Can Olmo 3 32B Think be self-hosted?+
Olmo 3 32B Think is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does Olmo 3 32B Think have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are allenai/Olmo-3-32B-Think.
Which models can Olmo 3 32B Think be compared with?+
The current compatible peer set includes Granite 4.2 30B, Phi-4 Reasoning, Olmo 3.1 32B Instruct, Olmo 3 7B Instruct, and Olmo 3 7B Think. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →