Cosmos 3 Nano
Cosmos 3 Nano is NVIDIA's language model. A compact world foundation model using a Mixture-of-Transformer architecture that unifies vision-language understanding and video generation in a single model.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Cosmos 3 Super | Super | — | — | — | — |
| Cosmos 3 Super Image2Video | Super | — | — | — | — |
| Cosmos 3 Super Reasoner | Super | — | — | — | — |
| Cosmos 3 Super Text2Image Agentic | Super | — | — | — | — |
| Cosmos3 Super Image2Video 4Step | Super | — | — | — | — |
| Cosmos | — | — | — | — | — |
| Cosmos Reason1 7B | — | — | — | — | — |