LLM Reference
DeepInfra

Nemotron 3 Super-120B-A12B on DeepInfra

Nemotron 3 · NVIDIA AI

ServerlessOpen Weights

Last refreshed 2026-06-15. Next refresh: weekly.

Why use Nemotron 3 Super-120B-A12B on DeepInfra?

DeepInfra offers Nemotron 3 Super-120B-A12B with pay-as-you-go pricing at $0.10/1M input tokens. DeepInfra is a cloud inference platform offering cost-effective access to open-source AI models.

Compare Nemotron 3 Super-120B-A12B across 6 providers to find the best fit for your use case
Input / 1M
$0.10
Output / 1M
$0.50
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install openai
Auth
export DEEPINFRA_API_KEY=...
Call
import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
Model ID
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B

Request example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai"
)
response = client.chat.completions.create(
    model="nvidia/NVIDIA-Nemotron-3-Super-120B-A12B",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • Use provider model ID "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B", not the LLMReference slug "nemotron-3-super-120b-a12b".
  • DeepInfra uses "organization/model-name" format, e.g. "meta-llama/Meta-Llama-3-8B-Instruct" or "mistralai/Mistral-7B-Instruct-v0.3". See the DeepInfra model catalog for exact IDs.
  • The examples expect DEEPINFRA_API_KEY; rename it only if your application config maps the new variable.

Compare Nemotron 3 Super-120B-A12B Across Providers

ProviderInput (per 1M)Output (per 1M)
Cloudflare Workers AI——
DeepInfra$0.10$0.50
NVIDIA NIM$0.10$0.50
OpenRouter$0.09$0.45
Fireworks AI——
View all 6 providers →

Pricing

TypePrice (per 1M)
Input tokens$0.10
Output tokens$0.50

Capabilities

Structured Outputs

About Nemotron 3 Super-120B-A12B

NVIDIA Nemotron 3 Super-120B-A12B is a 120B total / 12B active hybrid Latent MoE model with interleaved Mamba-2 and MoE layers for agentic, reasoning, and conversational tasks. Fireworks lists the NVFP4 variant for on-demand deployment with 262k context.

Get Started