Skip to the content
Rhumb
Menu

NVIDIA API Catalog

nvidia, the name to use in providers=

Models offered
45
Billing currency
USD
Runs
hosted
Fees
none
Try it in the sandbox

Models

ModelModel id hereStatusInput per 1MOutput per 1M
Cosmos Reason2 8Bnvidia/cosmos-reason2-8bdeprecatedunknownunknown
cosmos-transfer2.5-2bnvidia/cosmos-transfer2_5-2bgaunknownunknown
DeepSeek-V4.1-Flashdeepseek-ai/deepseek-v4.1-flashgaunknownunknown
DiffusionGemma 26B A4B ITgoogle/diffusiongemma-26b-a4b-itgaunknownunknown
FLUX.1-devblack-forest-labs/flux.1-devgaunknownunknown
FLUX.1-Kontext-devblack-forest-labs/flux_1-kontext-devgaunknownunknown
FLUX.1-schnellblack-forest-labs/flux_1-schnellgaunknownunknown
FLUX.2 Klein 4Bblack-forest-labs/flux_2-klein-4bgaunknownunknown
Gemma 3 12B ITgoogle/gemma-3-12b-itdeprecatedunknownunknown
Gemma 3 4B ITgoogle/gemma-3-4b-itdeprecatedunknownunknown
Gemma-4-31B-ITgoogle/gemma-4-31b-itgaunknownunknown
GLM-5.3z-ai/glm-5.3deprecatedunknownunknown
GLM-5.3-FlashXz-ai/glm-5.3-flashgaunknownunknown
GPT OSS 20Bopenai/gpt-oss-20bgaunknownunknown
Kimi K2.6moonshotai/kimi-k2.6deprecatedunknownunknown
Kimi K3moonshotai/kimi-k3deprecatedunknownunknown
Llama 3.1 Nemotron 70B Instructnvidia/llama-3.1-nemotron-70b-instructdeprecatedunknownunknown
Llama 3.1 Nemotron Ultra 253Bnvidia/llama-3.1-nemotron-ultra-253b-v1deprecatedunknownunknown
Llama 3.2 11b Vision Instructmeta/llama-3.2-11b-vision-instructgaunknownunknown
Llama Guard 4 12Bmeta/llama-guard-4-12bgaunknownunknown
llama-3.1-nemotron-safety-guard-8b-v3nvidia/llama-3.1-nemotron-safety-guard-8b-v3gaunknownunknown
Llama-3.2-90B-Vision-Instructmeta/llama-3.2-90b-vision-instructgaunknownunknown
llama-nemotron-embed-vl-1b-v2nvidia/llama-nemotron-embed-vl-1b-v2gaunknownunknown
llama-nemotron-rerank-vl-1b-v2nvidia/llama-nemotron-rerank-vl-1b-v2gaunknownunknown
Magistral Small 2506mistralai/magistral-small-2506deprecatedunknownunknown
magpie-tts-zeroshotnvidia/magpie-tts-zeroshotgaunknownunknown
MiniMax-M3.1-Flashminimaxai/minimax-m3.1-flashgaunknownunknown
Mistral Medium 3mistralai/mistral-medium-3-instructdeprecatedunknownunknown
Mistral-7B-Instruct-v0.3mistralai/mistral-7b-instruct-v0.3deprecatedunknownunknown
Muse Glimmer 30Bmeta/muse-glimmer-30bgaunknownunknown
Nemotron 3 Nano Omninvidia/nemotron-3-nano-omni-30b-a3b-reasoninggaunknownunknown
Nemotron 3 Ultra 550B A55Bnvidia/nemotron-3-ultra-550b-a55bgaunknownunknown
Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safetygaunknownunknown
Nemotron 3.5 Lightning 30B A3Bnvidia/nemotron-3.5-lightning-30b-a3bgaunknownunknown
Nemotron 3.5 Super VL 120B A12Bnvidia/nemotron-3.5-super-vl-120b-a12bgaunknownunknown
nemotron-voicechatnvidia/nemotron-voicechatgaunknownunknown
paligemmagoogle/google-paligemmagaunknownunknown
Qwen Imageqwen/qwen-imagegaunknownunknown
Qwen Image Editqwen/qwen-image-editgaunknownunknown
rerank-qa-mistral-4bnvidia/rerank-qa-mistral-4bdeprecatedunknownunknown
riva-translate-4b-instruct-v1_1nvidia/riva-translate-4b-instruct-v1.1deprecatedunknownunknown
Step 5 Previewstepfun-ai/step-5-previewgaunknownunknown
usdcodenvidia/usdcodedeprecatedunknownunknown
usdvalidatenvidia/usdvalidatedeprecatedunknownunknown
Whisper Large v3openai/whisper-large-v3gaunknownunknown

Built from catalog version 2026-11-04.13 of . Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).