Real-time or batch speaker identification and active-speaker tagging in broadcast, video communication, dubbing, localization, conferencing, and media analytics workflows.
Type
Multimodal
Reasoning
1/10
Speed
8/10
Multimodal
Audio input
Video input
Status
Current; downloadable NVIDIA NIM endpoint
View model
→
Real-time video relighting, virtual production, media effects, HDR-based lighting changes, and foreground/background compositing.
Type
Other
Reasoning
1/10
Speed
8/10
Multimodal
Image input
Video input
Status
Current and accessible through NVIDIA AI for Media and NVIDIA NIM documentation; version 1.1.0 is documented.
View model
→
Autonomous-driving research, trajectory prediction, interpretable motion planning, navigation-conditioned driving, visual question answering and safety-oriented model evaluation
Type
Reasoning
Reasoning
8/10
Speed
5/10
Multimodal
Image input
Video input
Status
Current; open weights available; also available through NVIDIA Alpamayo 1.5 NIM
View model
→
Multilingual offline speech transcription, speech translation, and NeMo-based ASR research or deployment
Type
Other
Reasoning
1/10
Speed
6/10
Audio input
Status
Active; open-weight checkpoint and NVIDIA deployment options available
View model
→
Fast English speech-to-text transcription, NeMo experimentation, domain fine-tuning, and Riva-based ASR deployment
Type
Other
Reasoning
1/10
Speed
9/10
Audio input
Fine-tuning
Streaming
Status
Available downloadable checkpoint; older NeMo ASR model
View model
→
Controllable video world generation, robotics sim-to-real augmentation, autonomous-vehicle simulation, and Physical AI synthetic-data generation
Type
Multimodal
Reasoning
1/10
Speed
3/10
Multimodal
Image input
Video input
Status
Available; legacy relative to Cosmos 3; original repository under limited maintenance
Input
No official token-based hosted price; NVIDIA lists a free NIM endpoint. Downloadable model is intended for self-hosted deployment.
Output
No official token-based hosted price; video-generation costs depend on deployment infrastructure and hardware.
View model
→
Edge physical AI, robotics, visual reasoning, world simulation, video generation, and action-policy prototyping
Type
Multimodal
Context
131K
Reasoning
7/10
Speed
9/10
Multimodal
Image input
Video input
Status
Current; open model; gated Hugging Face access
View model
→
Physical AI, robotics, autonomous-vehicle simulation, multimodal world generation, future-state prediction, action reasoning, and synthetic training data
Type
Multimodal
Reasoning
7/10
Speed
6/10
Multimodal
Image input
Audio input
Status
Current; downloadable open-weight model and available through an NVIDIA NIM endpoint
View model
→
High-quality Physical AI simulation, synthetic-data generation, robotics and autonomous-vehicle research, multimodal world modeling, and teacher-model distillation
Type
Multimodal
Context
262K
Reasoning
8/10
Speed
2/10
Multimodal
Image input
Audio input
Status
Current; open-weight model; commercially and non-commercially usable
View model
→
Physical-world video and image understanding, robotic perception, embodied-agent planning, spatial-temporal reasoning, and Physical AI research
Type
Reasoning
Context
256K
Reasoning
8/10
Speed
6/10
Multimodal
Image input
Video input
Status
Current; downloadable and hosted NIM endpoint
Input
Free downloadable endpoint; hosted pricing not specified in the reviewed NVIDIA sources
Output
Free downloadable endpoint; hosted pricing not specified in the reviewed NVIDIA sources
View model
→
Rapid global weather forecasting, ensemble simulation, climate-risk analysis, renewable-energy forecasting, and scientific weather-model research
Type
Other
Reasoning
0/10
Speed
9/10
Status
Current and downloadable; available through NVIDIA Earth-2 FourCastNet NIM and related deployment tooling
Input
Not publicly listed as a token-priced model; downloadable model and NIM access are subject to NVIDIA access and licensing terms
Output
Not publicly listed as a token-priced model; deployment and hosted inference pricing may depend on the selected NVIDIA service or infrastructure
View model
→
De novo molecular design, fragment-constrained generation, linker design, scaffold decoration, hit generation, and lead optimization
Type
Other
Context
512
Reasoning
2/10
Speed
7/10
Status
Current; downloadable model and available as an NVIDIA NIM
Input
No public per-token model price found; downloadable weights are available under the NVIDIA Open Model License. NIM access is subject to NVIDIA API or deployment terms.
Output
No public per-token model price found; NIM output pricing is not specified in the reviewed official documentation.
View model
→
Humanoid robot manipulation, cross-embodiment policy learning, robot demonstration fine-tuning, physical AI research, and action-sequence deployment
Type
Multimodal
Reasoning
4/10
Speed
6/10
Multimodal
Image input
Video input
Status
Current; general availability
View model
→
Quantum-computing calibration plot interpretation, QPU bring-up and retuning workflows, experiment diagnosis, parameter extraction, fit-quality assessment, and domain-specific calibration agents.
Type
Multimodal
Context
262K
Reasoning
7/10
Speed
6/10
Multimodal
Image input
Fine-tuning
Status
Current; available through NVIDIA Build, NVIDIA NIM, and downloadable checkpoints
View model
→
Generative lip dubbing, multilingual video localization, broadcasting, conferencing, and digital-human facial animation
Type
Multimodal
Reasoning
1/10
Speed
8/10
Multimodal
Image input
Audio input
Status
Current; downloadable model and NVIDIA LipSync NIM; private access may be required for some workflows
View model
→
Multimodal semantic search, visual document retrieval, question-answer retrieval, vector databases, and retrieval-augmented generation
Type
Embedding
Context
10K
Reasoning
2/10
Speed
8/10
Multimodal
Image input
Status
Current and downloadable
View model
→
Reranking text, document images, and image-text candidates in visual search, multimodal RAG, and question-answering retrieval pipelines
Type
Multimodal
Context
8K
Reasoning
2/10
Speed
7/10
Multimodal
Image input
Status
Current; downloadable and available through NVIDIA NIM and retrieval APIs
View model
→
Multilingual voice agents, accessibility, narration, audiobooks, dubbing, localization and interactive speech applications
Type
Other
Reasoning
1/10
Speed
8/10
Media output
Fine-tuning
Streaming
View model
→
Low-latency multilingual text translation, speech-translation pipelines, and self-hosted NVIDIA GPU deployments
Type
Other
Reasoning
1/10
Speed
8/10
Status
Current and downloadable; available through NVIDIA NIM and NVIDIA Riva
View model
→
Small-molecule generation, molecular embeddings, chemical-space exploration, lead optimization, and oracle-guided drug-design workflows
Status
Available through NVIDIA BioNeMo Framework and NVIDIA NIM; research and development model
View model
→
Detecting table cells, rows, columns, and merged-cell structure in document images for OCR alignment, table reconstruction, document ingestion, and retrieval systems
Type
Other
Reasoning
1/10
Speed
7/10
Image input
Status
Current; downloadable and available through NVIDIA NIM/Build
View model
→
Agentic reasoning, long-context analysis, coding, tool-calling workflows, retrieval-augmented generation, collaborative agents, and high-volume enterprise inference.
Type
Reasoning
Context
1M
Reasoning
9/10
Speed
8/10
Tool use
Fine-tuning
Streaming
Status
Current; open-weight; available through NVIDIA NIM, NVIDIA's hosted API trial endpoint, downloadable checkpoints, and self-hosted deployments.
View model
→
Frontier reasoning, complex coding, long-context analysis, enterprise RAG, tool-using agents, and multi-agent workflows
Type
Reasoning
Context
1M
Reasoning
10/10
Speed
7/10
Tool use
Fine-tuning
Streaming
Status
Current; open-weight model with BF16 and NVFP4 checkpoints
View model
→
Multilingual semantic search, dense retrieval, RAG, agentic retrieval, code search, and vector-based document matching
Type
Embedding
Context
33K
Fine-tuning
Status
Current; available through NVIDIA NIM and downloadable Hugging Face weights
View model
→
Multimodal document intelligence, OCR, long-video and audio understanding, cross-modal reasoning, voice agents, and self-hosted enterprise inference
Type
Multimodal
Context
262K
Reasoning
8/10
Speed
8/10
Multimodal
Image input
Audio input
Status
Current; generally available open-weight checkpoint with hosted NVIDIA NIM access
View model
→
Real-time full-duplex voice agents, interruptible conversational interfaces, speech-to-speech research, and NVIDIA GPU-based enterprise voice applications
Type
Multimodal
Reasoning
5/10
Speed
9/10
Multimodal
Audio input
Media output
Status
Early access; available for evaluation through NVIDIA NIM and qualified access programs
Input
Free endpoint for NVIDIA NIM trial access; no general production price published
Output
Free endpoint for NVIDIA NIM trial access; no general production price published
View model
→
High-volume agent execution, long-running AI agents, reasoning, coding assistance, RAG, chat, low-latency text generation, and domain customization
Type
Reasoning
Context
1M
Reasoning
8/10
Speed
9/10
Tool use
Fine-tuning
Streaming
Status
Current open-weight model; NIM container available for early-access evaluation
View model
→
Low-latency live speech-to-text, voice interfaces, live captions, and continuous audio streams
Type
Other
Reasoning
1/10
Speed
9/10
Multimodal
Audio input
Streaming
Status
Current and accessible through NVIDIA Speech NIM; streaming-only deployment
View model
→
Multilingual text-and-image moderation, LLM and VLM guardrails, response safety evaluation, and custom enterprise safety policies
Type
Other
Context
128K
Reasoning
5/10
Speed
8/10
Multimodal
Image input
Streaming
Status
Current; open-weight model and downloadable NVIDIA NIM; latest NGC container version bf16-v1.1 as of September 17, 2026
View model
→
Nemotron Graphic Elements
Detecting and localizing chart titles, axis labels, legends, mark labels, and value labels in document images
Type
Other
Reasoning
1/10
Speed
7/10
Image input
Status
Current and downloadable
View model
→
English OCR, document ingestion, layout-aware text extraction, multimodal retrieval, RAG preprocessing, and enterprise document intelligence
Type
Other
Reasoning
1/10
Speed
8/10
Image input
Status
Available; English-only OCR model; newer Nemotron OCR v2 is available for updated English and multilingual OCR deployments
View model
→
Multilingual OCR, scanned documents, forms, reports, charts, tables, image-based search, document ingestion, and retrieval-augmented generation preprocessing
Type
Other
Reasoning
1/10
Speed
9/10
Image input
Status
Current; downloadable model and available through NVIDIA NIM and NVIDIA-hosted services
View model
→
Document page-layout detection before OCR, table extraction, indexing, enterprise document processing, and multimodal RAG pipelines
Type
Other
Reasoning
1/10
Speed
7/10
Image input
Status
Current; downloadable and available through NVIDIA NIM
View model
→
Document OCR, layout analysis, table and chart extraction, retrieval pipelines, document indexing, and multimodal data curation
Type
Multimodal
Reasoning
2/10
Speed
7/10
Multimodal
Image input
View model
→
Quantum-computing calibration plot analysis, experiment interpretation, fit-quality assessment, parameter extraction, and technical research workflows
Type
Multimodal
Context
262K
Reasoning
7/10
Speed
6/10
Multimodal
Image input
Streaming
Status
Current; downloadable open-weight model
View model
→
NVIDIA Maxine Eye Contact
Gaze correction in video conferencing, telepresence, digital-human applications, and video-processing pipelines
Type
Other
Reasoning
1/10
Speed
8/10
Multimodal
Image input
Video input
Status
Current; downloadable NVIDIA NIM model
View model
→
English speech-to-text transcription, local ASR, offline processing, RAG audio extraction, and customized NeMo deployments
Type
Other
Reasoning
1/10
Speed
8/10
Audio input
Fine-tuning
Streaming
Status
Available open-weight checkpoint
View model
→
Local English speech transcription, offline ASR, long-form audio processing, and custom ASR fine-tuning
Type
Other
Reasoning
1/10
Speed
9/10
Audio input
Fine-tuning
Status
Current and accessible open-weight model
View model
→
Taiwanese Mandarin speech-to-text, Mandarin-English code-switching, live captions, voice interfaces, and NVIDIA GPU-hosted streaming or offline transcription.
Type
Other
Reasoning
1/10
Speed
8/10
Audio input
Streaming
Status
Listed in current NVIDIA Speech NIM documentation and model catalog; the associated NGC container is marked no longer supported.
View model
→
Mandarin-English automatic speech recognition, code-switched transcription, streaming transcription, and self-hosted enterprise speech-to-text
Type
Other
Reasoning
1/10
Speed
8/10
Audio input
Streaming
Status
Current and downloadable; available through NVIDIA NIM and Riva interfaces
Input
No public per-token price; downloadable model and NVIDIA service terms apply
Output
No public per-token price; downloadable model and NVIDIA service terms apply
View model
→
High-speed English speech transcription, captions, meeting transcription, audio search, and timestamped media workflows
Type
Other
Reasoning
1/10
Speed
10/10
Audio input
Fine-tuning
Streaming
Status
Current open-weight model; publicly available through Hugging Face and NVIDIA NeMo
View model
→
Multilingual sentence and document translation, localization, marketing content, and developer translation workflows
Type
Other
Context
8K
Reasoning
2/10
Speed
7/10
Status
Current and accessible through NVIDIA NIM and downloadable model weights
Input
Free hosted endpoint listed on Build.NVIDIA.com; no self-hosted per-token price specified
Output
Free hosted endpoint listed on Build.NVIDIA.com; no self-hosted per-token price specified
View model
→
Local or self-hosted multilingual sentence and document translation across English and 36 non-English languages
Type
Other
Context
8K
Reasoning
3/10
Speed
8/10
Status
Current and publicly downloadable; supported by NVIDIA NIM
View model
→
Camera-only multi-view 3D perception, autonomous-driving scene analysis, bird's-eye-view visualization, and object tracking
Multimodal
Image input
Video input
Status
Current NVIDIA NIM endpoint; free endpoint access requires an NVIDIA API key
View model
→
Real-time enhancement of speech captured with low-quality microphones in noisy or reverberant environments, including broadcast, conferencing, telecommunications, and media production.
Type
Other
Reasoning
1/10
Speed
9/10
Audio input
Streaming
Status
Current and available through NVIDIA NIM, hosted preview services, and NVIDIA audio software; downloadable deployment may require applicable NVIDIA licensing or subscription access.
View model
→
AI-generated video detection, media authentication, digital forensics, content moderation, and media-integrity monitoring
Type
Other
Reasoning
1/10
Speed
8/10
Video input
Streaming
Status
Current; downloadable NIM and managed trial endpoint, with self-hosted deployment requiring AI for Media Private Access
Input
Free managed trial endpoint; self-hosted and enterprise licensing terms may apply
View model
→
Professional video upscaling, broadcast enhancement, streaming pipelines, pre-encoding optimization, denoising, and deblurring
Type
Other
Reasoning
1/10
Speed
8/10
Multimodal
Video input
Media output
Status
Current; downloadable NVIDIA NIM
View model
→
