Using Nemotron 4 340B on DeepInfra

Implementation guide · Nemotron-4 · NVIDIA AI

ServerlessOpen Weights

DeepInfra exposes Nemotron 4 340B through model ID nemotron-4-340b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

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

Quick Start

  1. 1
    Create an account at DeepInfra and generate an API key.
  2. 2
    Use the DeepInfra SDK or REST API to call nemotron-4-340b — see the documentation for request format.
  3. 3
    You'll be billed $4.20/1M input, $4.20/1M output tokens. See full pricing.
API PortalDocumentationPricing

Code Examples

Install
pip install openai
API key
DEEPINFRA_API_KEY
Model ID
nemotron-4-340b

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.

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="nemotron-4-340b",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing on DeepInfra

TypePrice (per 1M)
Input tokens$4.20
Output tokens$4.20

Capabilities

Structured Outputs

About Nemotron 4 340B

Nemotron 4 340B is NVIDIA AI's Nemotron-4 model. It is deprecated (originally released 2025-02-27); use it only for reproducing earlier results or evaluating drift over time.

Full model details →

Model Specs

Released2025-02-27
Parameters340B
Context4k
ArchitectureDecoder Only

Also available on(1)

NVIDIA NIM
Compare all providers →

Provider

DeepInfra

San Francisco, California, United States