NVIDIA provides AI and accelerated computing APIs for building, customizing, and deploying multimodal generative AI models.

NVIDIA offers APIs for AI and accelerated computing, primarily through services like NeMo for building and deploying multimodal generative AI models. Key capabilities include model development, customization, and deployment across various domains. Notable strengths include integration with NVIDIA's hardware platforms (e.g., DGX, HGX) for high-performance computing. Typical use cases involve AI research, life sciences (via BioNeMo), and 3D simulation workflows (via Omniverse Cloud).

Time	Model	Speed	Latency
Nov 8, 12:52 PM	openai/gpt-oss-120b	149.96 t/s	18.38s
Nov 8, 12:45 PM	nvidia/llama-3.3-nemotron-super-49b-v1.5	79.68 t/s	0.28s
Nov 6, 01:20 PM	deepseek-ai/deepseek-v3.1	20.43 t/s	5.37s
Oct 31, 05:26 AM	qwen/qwen3-next-80b-a3b-instruct	158.38 t/s	0.50s
Oct 5, 02:42 AM	deepseek-ai/deepseek-v3.1	28.14 t/s	0.52s
Oct 5, 12:04 AM	deepseek-ai/deepseek-v3.1	29.94 t/s	0.38s
Oct 5, 12:01 AM	deepseek-ai/deepseek-r1	117.81 t/s	7.08s
Sep 28, 04:25 PM	qwen/qwen3-next-80b-a3b-instruct	79.54 t/s	0.67s
Sep 28, 10:27 AM	moonshotai/kimi-k2-instruct-0905	47.28 t/s	0.72s
Sep 20, 04:57 AM	google/gemma-2-27b-it	43.48 t/s	0.22s

integrate.api.nvidia.com

Supported Models

Recent Test Records

integrate.api.nvidia.com

About integrate.api.nvidia.com

Supported Models

Recent Test Records