Back to all models
nvidia
nvidiaNVIDIA: Llama 3.3 Nemotron Super 49B V1.5
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...
nvidia/llama-3.3-nemotron-super-49b-v1.5
Context Size
131.072K
Input Price
15,000 pts/M
Output Price
60,000 pts/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p
Details
TokenizerLlama3
Max Completion16,384 tokens
Provider Context131.072K tokens
ModeratedNo
CreatedOct 10, 2025