NVIDIA · nemotron family
Nemotron model for efficient reasoning, coding, and specialized AI agents
Provider-specific prices and limits stay separate from canonical model facts.
| Provider | Provider model ID | Input | Output | Context | Output limit |
|---|---|---|---|---|---|
| NanoGPT | nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 | $0.05 / 1M | $0.25 / 1M | 128,000 | 16,384 |
| Kilo Gateway | nvidia/llama-3.3-nemotron-super-49b-v1.5 | $0.1 / 1M | $0.4 / 1M | 131,072 | 26,215 |
| Deep Infra | nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 | $0.4 / 1M | $0.4 / 1M | 131,072 | 131,072 |
Attachments
No
Reasoning
Yes
Tool calling
Yes
Structured output
Unknown
Temperature
Yes