← All models
N

NVIDIA: Llama 3.3 Nemotron Super 49B V1.5

nvidia/llama-3.3-nemotron-super-49b-v1.5

Tool useJSONReasoningStreaming

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and...

Pricing

Input

$0.1 / 1M

Output

$0.4 / 1M

Specs

Context

131,072 tokens

Input

text

Output

text

Knowledge cutoff: 2024-03-31

Released: 2025-10

Supported parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p

Open weights · HuggingFace

305,788 downloads/mo
233 likes
other text-generation
View on HuggingFace →