NVIDIA
NVIDIA Nemotron Cascade 2 30B
Nemotron Cascade 2 30B A3B — NVIDIA reasoning-optimized language model for efficient inference across complex tasks.
nvidia-nemotron-cascade-2-30b-a3bCatalog preview. Paid requests for this model are not enabled yet.
List pricing
—USD. No uRouter markup. Live prices can change.
- Input
- $0.14 / 1,000,000 tokens
- Output
- $0.8 / 1,000,000 tokens
Model details
- Input
- text
- Output
- text
- Context window
- 256,000 tokens
- Maximum output
- 32,768 tokens
- Availability
- Unknown
- Updated
- 11/8/2026, 2:14:16 AM UTC
Capacity is reserved when your request is accepted.
Capabilities
chatstreamingtoolsreasoning
Supported parameters
max_tokenstemperaturetop_pfrequency_penaltypresence_penaltystoptoolstool_choiceresponse_formatseedstructured_outputsListed capabilities describe the model. uRouter execution support is verified separately.