Identity
- Status
- active
- Developer ID
allenai/MolmoAct2-Pretrain- Released
- Not reported
- Version
- MolmoAct2-Pretrain
- License
- Unknown
MolmoAct2-Pretrain is an open-weight robotics policy model published by Ai2.
0 current hosted offerings
No exact current provider endpoint or published price has been verified for this model version.
At a Glance
allenai/MolmoAct2-PretrainThis 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.
Primary Evidence
Comparable Peers
| A | Pair | B | Context |
|---|---|---|---|
| vs | family variantsimage, robotics, text |
Questions
MolmoAct2-Pretrain is an open-weight robotics policy model published by Ai2. It is developed by Ai2 and its current sourced lifecycle status is active.
MolmoAct2 Pretrain's current record lists Model-specific input as input and Model-specific input as output.
The current record lists a 16K-token context window and does not report a maximum output length.
MolmoAct2 Pretrain's current primary-source record does not establish API availability. No provider endpoint is treated as available without direct provider evidence.
The current record lists 4.9B total parameters and an unknown active parameter count. Its architecture is MolmoAct2ForConditionalGeneration.
MolmoAct2 Pretrain's recorded capabilities are robot action generation. Its supported tasks are image, robotics, and text.
No directly sourced token price is currently attached to MolmoAct2 Pretrain. Missing prices remain unknown rather than being inferred from another model or provider.
MolmoAct2 Pretrain is an open-weight model. Self-hosting is supported, with no license recorded.
No predecessor is recorded. No successor is recorded. Recorded aliases are allenai/MolmoAct2-Pretrain.
The current compatible peer set includes MolmoAct2 Think. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →