infery
← All models

NVIDIA models

20 models on Infery.ai.

Cosmos 3 Super

cosmos-3-super-text-to-image

Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from…

5 cr / image
Image output

Cosmos 3 Super Image to Video

cosmos-3-super-image-to-video

Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from…

6.25 cr / sec
Video output
Llama 3.1 Nemotron 70B Instruct HF

Llama 3.1 Nemotron 70B Instruct HF

llama-3.1-nemotron-70b-instruct

33K ctx

110 cr in / 1M110 cr out / 1M
ChatStreaming
Nemotron 3.5 Content Safety

Nemotron 3.5 Content Safety

nemotron-3.5-content-safety

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B.

131K ctx

25 cr in / 1M25 cr out / 1M
ChatStreamingVisionJSON
Nemotron 3.5 Lightning

Nemotron 3.5 Lightning

nemotron-3.5-lightning

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.

262K ctx

8.75 cr in / 1M25 cr out / 1M5 cr cached in / 1M
ChatStreamingJSON
Nemotron 3.5 Super VL

Nemotron 3.5 Super VL

nemotron-3.5-super-vl

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.

262K ctx

18.75 cr in / 1M62.5 cr out / 1M2.5 cr cached in / 1M
ChatStreamingVisionToolsJSON
Nemotron 3 Nano 30B A3B

Nemotron 3 Nano 30B A3B

nemotron-3-nano-30b-a3b

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build…

262K ctx

7.5 cr in / 1M30 cr out / 1M1.5 cr cached in / 1M
ChatStreamingToolsJSON

Nemotron 3 Nano Omni

nemotron-3-nano-omni-audio

Audio reasoning variant of NVIDIA's Nemotron 3 Nano Omni.

1250 cr in / 1M

Nemotron 3 Nano Omni

nemotron-3-nano-omni-vision

Vision reasoning variant of NVIDIA's Nemotron 3 Nano Omni.

750 cr in / 1M

Nemotron 3 Nano Omni

nemotron-3-nano-omni-video

Video reasoning variant of NVIDIA's Nemotron 3 Nano Omni.

750 cr in / 1M
Nemotron 3 Super

Nemotron 3 Super

nemotron-3-super-120b-a12b

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and…

262K ctx

37.5 cr in / 1M300 cr out / 1M18.75 cr cached in / 1M
ChatStreamingToolsJSON
Nemotron 3 Ultra

Nemotron 3 Ultra

nemotron-3-ultra-550b-a55b

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total…

262K ctx

75 cr in / 1M300 cr out / 1M15 cr cached in / 1M
ChatStreamingToolsJSON

Nemotron Asr Multilingual

nemotron-asr-multilingual-asr

Nemotron-ASR-Streaming is a multi lingual, streaming Automatic Speech Recognition (ASR) engineered to deliver high-quality multi lingual…

1 cr / min

NVIDIA Nemotron 3.5 Super Video

nemotron-3-5-super-video

Ask NVIDIA Nemotron 3.5 Super about a video clip: summarize what happens, find moments and reason across frames.

1250 cr in / 1M

NVIDIA Nemotron 3.5 Super Vision

nemotron-3-5-super-vision

Ask NVIDIA Nemotron 3.5 Super questions about an image: describe scenes, read text and charts, and reason over what it sees.

1250 cr in / 1M
NVIDIA Nemotron 3.5 Super VL

NVIDIA Nemotron 3.5 Super VL

nvidia-nemotron-3.5-super-vl

262K ctx

18.75 cr in / 1M62.5 cr out / 1M2.5 cr cached in / 1M
ChatStreaming
Nvidia Nemotron Nano 9B V2

Nvidia Nemotron Nano 9B V2

nvidia-nemotron-nano-9b-v2

131K ctx

7.5 cr in / 1M31.25 cr out / 1M
ChatStreaming

Sana

sana

0.125 cr / MP
Image output

Sana Sprint

sana-sprint

Sana Sprint is a text-to-image model capable of generating 4K images with exceptional speed.

0.313 cr / MP
Image output
Switchyard

Switchyard

switchyard

Switchyard is an open-source model router that switches between multiple models to optimize the cost of requests. This model is free to use.

ChatStreaming