Skip to main content

Nvidia

Inference platform

Nvidia is a Inference platform provider with 36 models across 36 catalog listings.

Models
36
Model families
11
Output coverage
Text
Latest release
2026-07-15
API base URL
https://integrate.api.nvidia.com/v1
SDK
@ai-sdk/openai-compatible
Environment variables
NVIDIA_API_KEY

Models

24 of 36 model offerings

Cache write
InklingThinking Machinesthinkingmachines/inklingCustom1M16KText, Image, AudioText--
Laguna XS 2.1Poolsidepoolside/laguna-xs-2.1Custom262K16KTextText--
GLM-5.2Zhipu AIz-ai/glm-5.2Openai chat1M131KTextText--
Nemotron 3 Ultra 550B A55BNVIDIAnvidia/nemotron-3-ultra-550b-a55bCustom1M66KTextText-
Nemotron 3.5 Content SafetyNVIDIAnemotron-3.5-content-safetyCustom128K8.2KImage, TextText----
Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIAnvidia/nemotron-3-nano-omni-30b-a3b-reasoningCustom256K66KText, Image, Video, AudioText--
Kimi K2.6Moonshot AImoonshotai/kimi-k2.6Custom262K262KText, Image, VideoText--
Nemotron 3 Content SafetyNVIDIAnvidia/nemotron-3-content-safetyCustom128K4.1KTextText--
Gemma 4 31B ITGooglegoogle/gemma-4-31b-itCustom256K16KText, Image, VideoText--
Llama Nemotron Rerank VL 1B v2NVIDIAnvidia/llama-nemotron-rerank-vl-1b-v2Custom128K4.1KText, ImageText--
Nemotron Cascade 2 30B A3BNVIDIAnemotron-cascade-2-30b-a3bCustom256K33KTextText----
Nemotron VoiceChatNVIDIAnvidia/nemotron-voicechatCustom128K8.2KText, AudioText--
Nemotron 3 Super 120B A12BNVIDIAnvidia/nemotron-3-super-120b-a12bCustom262K262KTextText--
Qwen3.5 122B-A10BAlibabaqwen/qwen3.5-122b-a10bOpenai chat262K66KText, Image, Video, AudioText--
Qwen3.5 397B-A17BAlibabaqwen/qwen3.5-397b-a17bOpenai chat262K8.2KText, ImageText--
Llama Nemotron Embed VL 1B v2NVIDIAnvidia/llama-nemotron-embed-vl-1b-v2Custom33K2KText, ImageText--
Nemotron Content Safety Reasoning 4BNVIDIAnvidia/nemotron-content-safety-reasoning-4bCustom128K4.1KTextText--
Nemotron 3 Nano 30B A3BNVIDIAnvidia/nemotron-3-nano-30b-a3bCustom131K131KTextText--
Llama 3.1 Nemotron Safety Guard 8B v3NVIDIAnvidia/llama-3.1-nemotron-safety-guard-8b-v3Custom128K4.1KTextText--
Nemotron Nano 12B v2 VLNVIDIAnvidia/nemotron-nano-12b-v2-vlCustom128K128KText, Image, VideoText--
Qwen3-Next 80B-A3B InstructAlibabaqwen/qwen3-next-80b-a3b-instructOpenai chat262K16KTextText--
Nemotron Nano 9B v2NVIDIAnemotron-nano-9b-v2Custom131K131KTextText----
gpt-oss-120bOpenAIopenai/gpt-oss-120bCustom128K8.2KTextText--
gpt-oss-20bOpenAIopenai/gpt-oss-20bCustom131K33KTextText--

Page 1 of 2

Other providers