NVIDIA NIM
unknownNVIDIA-hosted NIM endpoints on build.nvidia.com, free to NVIDIA Developer Program members for prototyping, research, development and testing. Rate limits vary by model and are not published; production use needs an NVIDIA AI Enterprise license.
https://integrate.api.nvidia.com/v1
Last Probe Latency
—
Healthy Observed Days
—
Rate Limits
— RPM / — RPD
Sign-up Required
Yes
Provider status summarizes sampled models checked with the monitoring account. Your access and limits may differ.
Documentation checked: . Model availability is subject to the provider's current catalog.
Free hosted API access is for NVIDIA Developer Program members for the duration of program membership, limited to prototyping, research, development and testing. Rate limits vary per model and are not published; your own limit is shown in your build.nvidia.com account. NVIDIA's API Trial Terms of Service (v. 2025-09-19, section 1.4) reserve the right to limit access by time, request count or credits. Production use requires an NVIDIA AI Enterprise license.
Info
Models(9)
Model health is unknown until an actual check completes.
nvidia/nemotron-3-ultra-550b-a55b
Context: 1M
z-ai/glm-5.3-flash
Context: 1M
moonshotai/kimi-k3.1-pro
Context: 1M
google/gemma-4-31b-it
Context: 256K
mistralai/mistral-large-4-1t-a52b
Context: Not published
minimaxai/minimax-m3.1-flash
Context: Not published
nvidia/nemotron-3.5-lightning-30b-a3b
Context: Not published
nvidia/nemotron-3.5-super-vl-120b-a12b
Context: Not published
poolside/laguna-xs-2.1
Context: Not published
Quick Start
export API_KEY="your_api_key_here"
curl 'https://integrate.api.nvidia.com/v1/chat/completions' \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d '{
"model": "nvidia/nemotron-3-ultra-550b-a55b",
"messages": [
{
"role": "user",
"content": "Hello! How are you?"
}
]
}'