NVIDIA
NVIDIA Nemotron 3 Ultra 550B
NVIDIA Nemotron 3 Ultra 550B-A55B — NVIDIA flagship reasoning model (550B total / 55B active MoE) tuned for agentic workloads, with a 1M-token context window.
nvidia-nemotron-3-ultra-550b-a55bPricing
~98%- Input
- $0.0125 / 1,000,000 tokens
- Output
- $0.0625 / 1,000,000 tokens
- Cache read
- $0.00375 / 1,000,000 tokens
- Cache write
- $0.0125 / 1,000,000 tokens
Discount history
Model details
- Input
- text
- Output
- text
- Context window
- 1,000,000 tokens
- Maximum output
- 16,384 tokens
- Availability
- $216Uncapped capacity
- Updated
- 11/8/2026, 4:00:11 AM UTC
Capacity is reserved when your request is accepted.
Capabilities
ChatStreamingTool callingReasoning
Supported parameters
max_tokenstemperaturetop_pfrequency_penaltypresence_penaltystoptoolstool_choiceresponse_formatseedstructured_outputs