Search

Search for a command to run...

All providers

NVIDIA models

All 7 NVIDIA models on OpenDunes, priced in Algerian Dinars.

Models7
Understands
TextAudio
Replies with
Text
Input price16,20 – 194,40 DA/ 1M tokens
Output price64,80 – 1 166,40 DA/ 1M tokens
Context up to1M
6 with json5 with reasoning5 with tools

7 models

NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B

nvidia/nemotron-3.5-asr-streaming-multilingual-0.6bTranscription

Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice...

AudioText
1 078,92 DA/M input·0 DA/M output
by NVIDIAAug 13, 2026JSON

NVIDIA: Nemotron 3.5 Lightning

nvidia/nemotron-3.5-lightningText

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

TextText
in25,92 DAout64,80 DAper 1M tokens
by NVIDIAAug 11, 2026262K contextReasoningToolsJSON

NVIDIA: Nemotron 3 Ultra

nvidia/nemotron-3-ultra-550b-a55bText

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

TextText
in162 DAout712,80 DAper 1M tokens
by NVIDIAJun 4, 2026262K contextReasoningToolsJSON

NVIDIA: Nemotron 3 Ultra (batch)

nvidia/nemotron-3-ultra-550b-a55b:batchText

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

TextText
in194,40 DAout1 166,40 DAper 1M tokens
by NVIDIAJun 4, 2026512K contextReasoningToolsJSON

NVIDIA: Parakeet TDT 0.6B v3

nvidia/parakeet-tdt-0.6b-v3Transcription

Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across...

AudioText
0,49 DA / hour
by NVIDIAMay 27, 2026

NVIDIA: Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12bText

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

TextText
in27,54 DAout129,60 DAper 1M tokens
by NVIDIAMar 11, 20261M contextReasoningToolsJSON

NVIDIA: Nemotron 3 Nano 30B A3B

nvidia/nemotron-3-nano-30b-a3bText

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

TextText
in16,20 DAout64,80 DAper 1M tokens
by NVIDIADec 14, 2025262K contextReasoningToolsJSON