Llama 3.3 Nemotron Super 49B V1.5

ChatInput: TextReleased Oct 10, 2025

Built by NVIDIA · United States · nvidia.com

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...

How to use

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

Cap quality here and save

Hard questions go to this model, easy ones drop to something cheaper. Set a savings target (0–0.8) and the router tunes itself until realized savings converge on it.

{
  "model": "celon/auto",
  "celon": {
    "anchor": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
    "savings_target": 0.4
  }
}

Naming a model directly gets you that model — savings controls don't apply.

Context

131K

Max output

16K

Input $/1M

$0.40

Output $/1M

$0.40

Features

Tool callingJSON

Serving providers

DeepInfra

Providers

Price, latency, and uptime per provider serving this model. Celon routes each request to the fastest and cheapest of them. Click a row for regions and data policies.

Loading provider metrics…

Performance

Measured latency (lower is better) and throughput (higher is better) per provider.

Speed

Loading provider metrics…