ModelHubby

← Directory

NVIDIA NIM (build.nvidia.com)

permanent free · inference_host · verification: partially_verified (60%, doc_fetch, 2026-07-17) · setup guide →

The record

Base URLs
https://integrate.api.nvidia.com/v1 openai-compatible
API key requiredyes
Credit cardno
Phone verificationyes
May train on promptsunknown
Quotafree_tier [rpm]
40 requests/minute (cheahjs); "Rate-limited (no daily token cap)" (mnfst); "~40 RPM" per model
Signup friction5 steps · ~15m to first key
Env varNVIDIA_API_KEY
NotesBase URL confirmed from official API reference (https://integrate.api.nvidia.com, POST /v1/chat/completions across the LLM catalog). 100+ hosted models. Tool-calling support varies by model and was not confirmed.

Models (4)

modelcapabilitiescontextfreelimits
deepseek-ai/deepseek-r1chat, reasoning128,000yes40 rpm
meta/llama-3.1-405b-instructchat128,000yes40 rpm
nvidia/llama-3.1-nemotron-ultra-253b-v1chat128,000yes40 rpm
qwen/qwen2.5-72b-instructchat128,000yes40 rpm

Provenance

source_nvidia_nim_docsofficial_docstrust: highchecked 2026-07-17
source_repo_cheahjscurated_repotrust: medium_highchecked 2026-07-17
source_repo_mnfstcurated_repotrust: medium_highchecked 2026-07-17