Allenaitext+image+video->text

AllenAI: Molmo2 8B (free)

Molmo2-8B is an open vision-language model developed by the Allen Institute for AI (Ai2) as part of the Molmo2 family, supporting image, video, and multi-image understanding and grounding. It is based on Qwen3-8B and uses SigLIP 2 as its vision backbone, outperforming other open-weight, open-data models on short videos, counting, and captioning, while remaining competitive on long-video tasks.

Context Window

37K

Input Price

Free

Output Price

Free

Modality

text+image+video->text

Pricing Breakdown

Cost per million tokens for input and output

InputFree

OutputFree

Cost Example: Processing 10,000 input tokens and generating 1,000 output tokens would cost approximately $0.000000

Context Window Size

Maximum tokens the model can process in a single request

Context Window37K tokens

4% of 1M max

~28K

Words Equivalent

~18

Pages of Text

~369

Code Functions

Best Use Cases

What this model excels at

VisionImage-analysisMultimodalData-analysisAnalytics

Related Categories:

Data Analysis Image Generation

Test AllenAI: Molmo2 8B (free) Now

Compare this model with others using your own prompts

Ready to Test AllenAI: Molmo2 8B (free)?

Use our free AI Models Tester to compare AllenAI: Molmo2 8B (free) with other models side-by-side using your own prompts. See real results instantly.