DeepInfra raises $107M Series B to scale the inference cloud — read the announcement

Nemotron Model Family

A family of open models, datasets, and training recipes engineered for high performance, efficiency, and customization. Nemotron models support synthetic data workflows and supervised fine-tuning—and are optimized for real-time inference, reasoning agents, and production AI systems.

Get an API Key

Check Token Pricing

Featured Model: nvidia/NVIDIA-Nemotron-3.5-Lightning

NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.

Price per 1M input tokens

$0.06

Price per 1M cached input tokens

$0.03

Price per 1M output tokens

$0.16

Release Date

09/28/2026

Context Size

262,144

# Assume openai>=1.0.0
import os

from openai import OpenAI

# Create an OpenAI client with your deepinfra token and endpoint
openai = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai",
)

chat_completion = openai.chat.completions.create(
    model="nvidia/NVIDIA-Nemotron-3.5-Lightning",
    messages=[{"role": "user", "content": "Hello"}],
)

print(chat_completion.choices[0].message.content)
print(chat_completion.usage.prompt_tokens, chat_completion.usage.completion_tokens)

# Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat?
# 11 25
copy

Featured Model: nvidia/NVIDIA-Nemotron-3.5-Super-VL

NVIDIA Nemotron 3.5 Super VL is an open multimodal model for agents that see, reason, and act. Its 120B-parameter Mixture-of-Experts design (12B active) understands text, images, documents, GUIs, and video, and adds reasoning and tool use on top.

Price per 1M input tokens

$0.10

Price per 1M cached input tokens

$0.08

Price per 1M output tokens

$0.40

Release Date

09/16/2026

Context Size

262,144

Quantization

fp4

# Assume openai>=1.0.0
import os

from openai import OpenAI

# Create an OpenAI client with your deepinfra token and endpoint
openai = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai",
)

chat_completion = openai.chat.completions.create(
    model="nvidia/NVIDIA-Nemotron-3.5-Super-VL",
    messages=[{"role": "user", "content": "Hello"}],
)

print(chat_completion.choices[0].message.content)
print(chat_completion.usage.prompt_tokens, chat_completion.usage.completion_tokens)

# Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat?
# 11 25
copy

Featured Model: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B

Nemotron 3 Ultra is built for, frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads while supporting up to 1M token context.

Price per 1M input tokens

$0.50

Price per 1M cached input tokens

$0.10

Price per 1M output tokens

$2.20

Release Date

09/25/2026

Context Size

262,144

Quantization

fp4

# Assume openai>=1.0.0
import os

from openai import OpenAI

# Create an OpenAI client with your deepinfra token and endpoint
openai = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai",
)

chat_completion = openai.chat.completions.create(
    model="nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B",
    messages=[{"role": "user", "content": "Hello"}],
)

print(chat_completion.choices[0].message.content)
print(chat_completion.usage.prompt_tokens, chat_completion.usage.completion_tokens)

# Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat?
# 11 25
copy

Featured Model: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B

NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.

Price per 1M input tokens

$0.085

Price per 1M output tokens

$0.40

Release Date

03/10/2026

Context Size

262,144

Quantization

bfloat16

# Assume openai>=1.0.0
import os

from openai import OpenAI

# Create an OpenAI client with your deepinfra token and endpoint
openai = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai",
)

chat_completion = openai.chat.completions.create(
    model="nvidia/NVIDIA-Nemotron-3-Super-120B-A12B",
    messages=[{"role": "user", "content": "Hello"}],
)

print(chat_completion.choices[0].message.content)
print(chat_completion.usage.prompt_tokens, chat_completion.usage.completion_tokens)

# Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat?
# 11 25
copy

Featured Model: nvidia/Nemotron-3-Embed-8B

Nemotron-3-Embed-8B is a multilingual text embedding model from NVIDIA, based on Ministral-3-8B, that maps text into 4096-dimensional dense vectors for retrieval and semantic similarity. Spanning 34 languages, it targets multilingual RAG and question-answering over large corpora and achieves state-of-the-art results on the RTEB leaderboard.

Release Date

07/16/2026

Context Size

32,768

Quantization

fp16

License Type

License

Featured Model: nvidia/Nemotron-3-Diarization

Nemotron 3 Diarization is an open-weight streaming Sortformer model, engineered for low-latency speaker diarization across up to 8 speakers, ordered by arrival time. It powers meeting transcription, call analytics, and voice-agent pipelines—resolving who spoke when with generic speaker labels and timestamps in a single streaming pass, offline or in real time.

Price per minute of audio input

$0.00060

Release Date

09/25/2026

License Type

License

Featured Model: nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b

Nemotron 3.5 ASR Streaming Multilingual is an open 0.6B-parameter prompt-conditioned cache-aware FastConformer-RNNT model, engineered for low-latency streaming transcription across 40+ languages. It powers real-time captioning, voice agents, and multilingual transcription pipelines—replacing separate per-language Whisper deployments with a single inference pass.

Price per minute of audio input

$0.00020

Release Date

06/3/2026

License Type

License

Available Nemotron Models

The Nemotron family spans Lightning, Super, Ultra, and specialized safety models, enabling you to balance accuracy, reasoning depth, latency, and cost for your specific workload.

Lightning for fast, low-cost inference
Super and Super-VL for multi-agent systems, advanced reasoning, and vision
Ultra for the hardest reasoning and agentic tasks
Content Safety for moderating prompts and responses

Model	Context	$ per 1M input tokens	$ per 1M output tokens	Actions
NVIDIA-Nemotron-3.5-Lightning	256k	$0.06 / $0.03 cached	$0.16	View more
NVIDIA-Nemotron-3.5-Super-VL	256k	$0.10 / $0.08 cached	$0.40	View more
Nemotron-Content-Safety-3.5	128k	$0.20	$0.20	View more
NVIDIA-Nemotron-3-Ultra-550B-A55B	256k	$0.50 / $0.10 cached	$2.20	View more
NVIDIA-Nemotron-3-Super-120B-A12B	256k	$0.085	$0.40	View more

Available Nemotron Speech Models

Nemotron speech models for streaming multilingual speech recognition and speaker diarization (who spoke when).

Model	$ per minute of audio input	Actions
Nemotron-3-Diarization	$0.00060	View more
Nemotron-3.5-ASR-Streaming-Multilingual-0.6b	$0.00020	View more

FAQ

How do I integrate Nemotron models into my application?

You can integrate Nemotron models seamlessly using DeepInfra’s OpenAI-compatible API. Just replace your existing base URL with DeepInfra’s endpoint and use your DeepInfra API key—no infrastructure setup required. DeepInfra also supports integration through libraries like openai, litellm, and other SDKs, making it easy to switch or scale your workloads instantly.