inference-providers

NVIDIA NIM API

first_party

DocsConsole

Getting credentials

api-key

api_key via header (header Authorization: Bearer)

Key prefix: nvapi-

Environment: NVIDIA_API_KEY

Generate nvapi- keys at build.nvidia.com (free with the NVIDIA Developer Program).

Credentials docs

Endpoints

IDURLProtocolAuth
v1-chat-completionshttps://integrate.api.nvidia.com/v1/chat/completionsopenai-chatany

API surfaces

textstreamingembeddings

Quirks

Models offered

ModelWire IDEndpointStatusReasoning
deepseek/deepseek-v4-prodeepseek-ai/deepseek-v4-prov1-chat-completionsretiredadaptive · default on · returns reasoning_content · round-trips reasoning_content
google/gemma-4google/gemma-4-31b-itv1-chat-completionsgaadaptive · default on · returns reasoning_content
meta/llama-3-3-70bmeta/llama-3.3-70b-instructv1-chat-completionsretirednone · default off · returns hidden
meta/muse-glimmer-30bmeta/muse-glimmer-30bv1-chat-completionsgaeffort · default on · returns reasoning_content
minimax/minimax-m3minimaxai/minimax-m3v1-chat-completionsretiredeffort · default on · mandatory · returns reasoning_content
moonshot/kimi-k2-6moonshotai/kimi-k2.6v1-chat-completionsgatoggle · default on · returns reasoning_content
moonshot/kimi-k3moonshotai/kimi-k3v1-chat-completionsgatoggle · default on · returns reasoning_content
nvidia/nemotron-3-5-lightningnvidia/nemotron-3.5-lightning-30b-a3bv1-chat-completionsgatoggle · default on · returns reasoning_content
nvidia/nemotron-3-supernvidia/nemotron-3-super-120b-a12bv1-chat-completionsgatoggle · default on · returns reasoning_content
nvidia/nemotron-3-ultranvidia/nemotron-3-ultra-550b-a55bv1-chat-completionsgatoggle · default on · returns reasoning_content
openai/gpt-oss-120bopenai/gpt-oss-120bv1-chat-completionsretiredtoggle · default on · returns reasoning_content
openai/gpt-oss-20bopenai/gpt-oss-20bv1-chat-completionsgatoggle · default on · returns reasoning_content
poolside/laguna-xs-2-1poolside/laguna-xs-2.1v1-chat-completionsgaadaptive · default on · returns hidden
stepfun/step-3-7-flashstepfun-ai/step-3.7-flashv1-chat-completionsretiredeffort · default on · mandatory · returns reasoning_content