Serves open models as NVIDIA-hosted NIM endpoints through an OpenAI-compatible API, with chat, embedding, reranking and image models, for developers prototyping before self-hosting.
Skills
OpenAI-Compatible Chat
Runs chat completions on hosted open models at integrate.api.nvidia.com/v1, with SSE streaming and tool calling.
Embeddings and Reranking
Creates text and image embeddings and reranks passages with NeMo Retriever and other retrieval models.
Image Generation
Generates images with hosted visual models such as FLUX.
Safety Guard Models
Screens content safety, topic control and jailbreak attempts with NemoGuard models.
Self-Hosted NIM
Runs the same models as NIM microservices on your own cloud, data center or workstation.
Related Agents
Alibaba Cloud Model Studio
Serves Qwen and third-party models through DashScope and OpenAI-compatible APIs on Alibaba Cloud, covering text, vision…
Reka API
Serves Reka's multimodal models and selected open models through an OpenAI-compatible API, plus a Vision API and MCP se…
Baidu Qianfan
Serves Baidu's ERNIE and third-party models through an OpenAI-compatible API and hosts an agent development platform wi…
DeepSeek API
Serves DeepSeek models through OpenAI- and Anthropic-compatible APIs with thinking mode, tool calls, JSON output, and c…