AI Rate Card

NVIDIA API pricing: all models and providers

Every NVIDIA model on sale with its lowest price among all providers (35 in all). Prices per 1M tokens unless a cell names another unit; open a model for every offer.

Read also: Llama API pricing: Llama 4 Maverick, Scout and Llama 3.3 70B at every provider

NVIDIA's own API: its provider page

ModelTypeInput fromOutput fromContextProviders
Nemotron 3 Ultra 550B A55BText models$0.10$1.701M22
Nemotron 3 Super 120B A12BText models$0.015$0.321M20
Nemotron 3.5 Lightning 30B A3BText models$0.025$0.121M17
NVIDIA Nemotron 3.5 Super VLText models$0.06$0.351M17
Nemotron 3 Nano 30B A3BText models$0.04$0.161M15
Nemotron 3 Nano Omni 30B A3B ReasoningText models$0.06$0.24300K12
Nemotron 3.5 Content SafetyModeration$0.05$0.15131K10
Nemotron Nano 9B v2Text models$0.04$0.16131K6
Nemotron Nano 12B v2 VLText models$0.20$0.60131K5
Llama 3.1 Nemotron 70B InstructText models$0.60$0.60131K4
Llama 3.3 Nemotron Super 49B v1.5Text models$0.11$0.40131K3
Nemotron 3.5 Super VL 120B A12BText models$0.11$0.50—3
Llama 3.1 Nemotron Ultra 253BText models$0.50$0.50—2
Llama Nemotron Embed VL 1B v2Embeddings$0.01—33K2
nemotron-3-120b-a12bText models$0.50$1.50256K2
nemotron-3.5-bolt-e4bText models$2.11$10.55—2
nemotron-3.5-embed-1bEmbeddings$0.015—33K2
nemotron-3.5-embed-8bEmbeddings$0.035—33K2
Nemotron 3 Embed 1BEmbeddings$0.01—33K2
nemotron-3-nanoText models$0.06$0.24—2
nemotron-4-340b-instructText models$4.20$4.204K2
nvidia.nemotron-nano-12b-v2@usText models$0.20$0.60131K2
ai-synthetic-video-detectorVideoFreeFree—1
Cosmos Reason2 8BText modelsFreeFree131K1
deepinfra-nvidia-nemotron-3-nano-30b-a3b2Text models$0.066$0.26—1
ising-calibration-1.5-31bText modelsFreeFree—1
llama-3.1-nemotron-51b-instructText modelsFreeFree—1
Llama 3.1 Nemotron Safety Guard 8B v3ModerationFreeFree128K1
Llama Nemotron Rerank VL 1B v2Reranking$0.01—10K1
Nemotron-120B-A12BText models——203K1
Nemotron 3.5 Lightning 30BText models$0.05$0.15—1
Nemotron 3.5 Lightning 30B Free cached input until Oct 31, 2026, 11:59 PM UTCText models———1
Nemotron-3.5-Rerank-8B-BF16Reranking$0.05—33K1
NVIDIA-Nemotron-3.5-Transcribe-30B-A4BSpeech to text$0.002 / minute——1
Nemotron-3-Diarization-previewText models$0.0006 / minute——1
Nemotron-3-Embed-8BEmbeddings$0.035—33K1
Nemotron 3.5 ASR Streaming Multilingual 0.6BSpeech to text$0.0001998 / minute——1
Nemotron 3.5 Super 120B A12BText models$0.20$0.50—1
nemotron-4-340b-rewardText modelsFreeFree—1
nemotron-nano-12b-v2Text models$0.21$0.63—1
nemotron-nano-3-30b-a3bText modelsFreeFree—1
Nemotron Nano 3 OmniText models$0.50$0.90—1
nemotron-nano-v2-12bText models$0.24$0.71128K1
nemotron-parseText modelsFreeFree—1
nemotron-parse-2.0Text modelsFreeFree—1
Nemotron-SEA-LION-v4.8-120B-A12BText models$0.50$2.00—1
neva-22bText modelsFreeFree—1
nv-embedqa-mistral-7b-v2EmbeddingsFreeFree—1
nvclipText modelsFreeFree—1
Parakeet TDT 0.6B v3Speech to text$0.0014 / minute——1
riva-translate-4b-instructText modelsFreeFree—1
riva-translate-4b-instruct-v2Text modelsFreeFree—1
vilaText modelsFreeFree—1

Prices in USD per 1M tokens. * price not verified.