NVIDIA

Models
61
Hosted by a direct provider
56

Provider counts exclude gateways.

ModelCompareTypeReleasedContextProvidersInput $/1MOutput $/1M
Nemotron 3.5 Super VL 120B A12BChat2026-10-151.05M10 +6$0.10–$0.30$0.40–$1.25
SwitchyardChat2026-09-211M0 +1
Nemotron 3.5 ASR Streaming Multilingual 0.6BTranscription2026-08-130 +1n/a
Nemotron 3.5 Lightning 30B A3BChat2026-08-11262K9 +9$0.025–$0.080$0.12–$0.24
Nemotron 3 Nano Omni 30B TEEunverifiedChat2026-07-23131K1$0.0245$0.0978
Nemotron 3 Embed 1BEmbedding2026-07-1632.8K0 +1Free tier
Nemotron 3.5 Content SafetyChat2026-06-04128K3 +5$0.05–$0.20$0.15–$0.20
Nemotron 3 Ultra 550B A55BChat2026-06-041M10 +14$0.50–$1.00$2.15–$3.13
Nemotron 3 UltraunverifiedChat2026-06-01262K1 +1$0.90$1.70
Parakeet TDT 0.6B v3Transcription2026-05-270 +1n/a
nemotron-3-nano-omniChat2026-05-20300K1 +1$0.06$0.24
Nemotron 3 Nano OmniChat2026-04-28256K5 +4$0.10–$0.50$0.25–$1.83
Active Speaker DetectionChat2026-04-161Free tier
nemotron-3-content-safetyChat2026-04-16128K1Free tier
synthetic-video-detectorChat2026-04-161Free tier
llama-nemotron-rerank-vl-1b-v2Rerank2026-03-31128K1 +1Free tiern/a
nemotron-voicechatRealtime2026-03-16128K1Free tier
Nemotron 3 Super 120BChat2026-03-11262K13 +10$0.08–$0.50$0.40–$2.50
gliner-piiChat2026-03-03128K1Free tier
cosmos-transfer2.5-2bVideo generation2026-02-261Free tiern/a
llama-nemotron-embed-vl-1b-v2Embedding2026-02-1032.8K1 +1Free tier
nemotron-content-safety-reasoning-4bChat2026-01-22128K1Free tier
usdcodeChat2026-01-01128K1Free tier
riva-translate-4b-instruct-v1_1Chat2025-12-12128K1Free tier
Cosmos Reason2 8BChat2025-12-01131K1Free tier
streampetrChat2025-11-13128K1Free tier
nemotron-nano-v2-12bunverifiedChat2025-10-31128K0 +1via Cortecs $0.24via Cortecs $0.707
llama-3.1-nemotron-safety-guard-8b-v3Chat2025-10-28128K1Free tier
Nemotron Nano 12B v2 VLChat2025-10-28131K3 +1$0.20$0.60
Llama Nemotron Embed 1B v2Embedding2025-10-168.2K1
NVIDIA-Nemotron-Nano-12B-v2Chat2025-08-18131K3$0.07–$0.20$0.20
nvidia-nemotron-nano-9b-v2Chat2025-08-18131K5 +2$0.04–$0.20$0.16–$0.23
Llama 3.3 Nemotron Super 49B v1.5Chat2025-07-25131K2Free tier
llama-3_2-nemoretriever-300m-embed-v1Embedding2025-07-2432.8K1Free tier
cosmos-transfer1-7bVideo generation2025-06-131Free tiern/a
mistral-nemotronChat2025-06-11128K1Free tier
magpie-tts-zeroshotSpeech synthesis2025-05-221Free tiern/a
Llama 3.1 Nemotron 70B InstructChat2025-04-15128K2 +2$0.60$0.60
Llama 3.1 Nemotron Nano VL 8B v1Chat2025-04-1032.8K1Free tier
Llama 3.1 Nemotron Ultra 253BChat2025-04-07128K3$0.60$1.80
Llama 3.3 Nemotron Super 49B v1Chat2025-04-07131K2 +1$0.10$0.40
bevformerChat2025-03-18128K1Free tier
cosmos-predict1-5bVideo generation2025-03-181Free tiern/a
Llama 3.1 Nemotron Nano 8B v1Chat2025-03-18131K1Free tier
sparsedriveChat2025-03-18128K1Free tier
nv-embedcode-7b-v1Embedding2025-03-1732.8K1Free tier
nemotron-3-nano-30b-a3bChat2024-12262K10 +9$0.050–$0.075$0.20–$0.30
studiovoiceChat2024-10-03128K1Free tier
nvidia--llama-3.2-nv-embedqa-1bEmbedding2024-09-258.2K1$0.07
nemotron-mini-4b-instructChat2024-08-21128K1Free tier
usdvalidateChat2024-07-241Free tier
nv-embed-v1Embedding2024-06-0732.8K1Free tier
rerank-qa-mistral-4bRerank2024-03-17128K1Free tiern/a
cosmos3-super-reasonerChat—262K1$0.10$0.30
gemma-4-31b-itChat—262K1$0.14$0.40
llama-3-1-nemotron-70b-instruct-hfChat—32.8K1
llama-3-2-nv-rerankqa-1b-v2Rerank—1Free tiern/a
nemotron-content-safety-3-5Chat—131K1$0.20$0.20
nemotron-lightning-3p5-30b-a3bunverifiedChat—262K1$0.05$0.20
nemotron-nano-v2-12b-vlunverifiedChat—131K1$0.10$0.10
nv-rerankqa-mistral-4b-v3Rerank—1Free tiern/a

Providers: direct count, then “+n” gateways. Prices are the range across comparable direct providers (gateways, subscription plans, deprecated endpoints and anything that is not a paid per-token price excluded); models only on gateways show the cheapest gateway list price. Non-token models show their native unit.