How do you use Llama 3.3 Nemotron Super 49B V1.5?

Llama 3.3 Nemotron Super 49B V1.5 can be called through OpenRouter's OpenAI-compatible API using the model ID nvidia/llama-3.3-nemotron-super-49b-v1.5. This page includes a ready-to-run curl example and the supported parameter list.

Is Llama 3.3 Nemotron Super 49B V1.5 free?

Llama 3.3 Nemotron Super 49B V1.5 is a paid model in the OpenRouter catalog, with separate input and output token pricing shown on this page.

Llama 3.3 Nemotron Super 49B V1.5

All models

NVIDIANemotron

Llama 3.3 Nemotron Super 49B V1.5

131K context

$0.100/M input

$0.400/M output

Llama 3.3 Nemotron Super 49B V1.5 is an AI model from NVIDIA built for agent workflows, with support for text input and text output. 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...

What is Llama 3.3 Nemotron Super 49B V1.5?

Llama 3.3 Nemotron Super 49B V1.5 is an AI model from NVIDIA that Agent Mag tracks for pricing, context window, modalities, benchmarks, and API compatibility. Builders can use this page to compare Llama 3.3 Nemotron Super 49B V1.5 against other models for agent workflows and production deployments.

Model ID

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...

Modalities

Input

text

Output

text

Supported Parameters

frequency_penaltyinclude_reasoningmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p

More from NVIDIA

Nemotron 3 Super

262K ctx$0.090/M

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Nemotron 3 Super (free)

262K ctxFree

Nemotron 3 Nano 30B A3B (free)

256K ctxFree

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

Nemotron 3 Nano 30B A3B

262K ctx$0.050/M

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

Stay in the know

Llama 3.3 Nemotron Super 49B V1.5

What is Llama 3.3 Nemotron Super 49B V1.5?

More from NVIDIA

Related content