Skip to content
Sovyron

Nvidia

57 modelsProvider docs

As of Oct 4, 2026, Nvidia lists 57 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash, GLM-5.3-Flash, GLM-5.3, Nemotron 3.5 Lightning 30B A3B and Muse Glimmer 30B — deepseek-flash, glm-flash, glm, nemotron, muse and kimi-k3 families. Its metered rates span $0.35–$1 per 1M tokens on a 3:1 input:output blend, and every price in the table is Nvidia's own, normalized to USD — open a model to compare it with the cheapest offer across all providers. Offer mix: 55 free-tier offers.

Supported models and pricing

57 of 57 models
Nvidia model prices in USD per 1M tokens, updated Oct 4, 2026
Model1M input1M output1M cache readContextReleasedTags
DeepSeek V4.1 Flashfreefree—1.0MSep 10, 2026free
GLM-5.3-Flashfreefree—1.0MAug 26, 2026free
GLM-5.3freefree—1.0MAug 14, 2026free
Nemotron 3.5 Lightning 30B A3Bfreefree—262kAug 11, 2026free
Muse Glimmer 30Bfreefree—131kAug 10, 2026free
Kimi K3freefree—1.0MJul 16, 2026free
Laguna XS 2.1freefree—262kJul 2, 2026free
DiffusionGemma 26B A4B ITfreefree—250kJun 9, 2026free
Nemotron 3 Ultra 550B A55B$0.5$2.5$0.151.0MJun 4, 2026
Nemotron 3.5 Content Safetyfreefree—128kJun 4, 2026free
Nemotron 3 Nano Omnifreefree—256kApr 28, 2026free
Active Speaker Detectionfreefree——Apr 16, 2026free
synthetic-video-detectorfreefree——Apr 16, 2026free
Gemma 4 31B ITfreefree—256kApr 2, 2026free
llama-nemotron-rerank-vl-1b-v2freefree—128kMar 31, 2026free
nemotron-voicechatfreefree—128kMar 16, 2026free
Nemotron 3 Super$0.2$0.8—262kMar 11, 2026
cosmos-transfer2.5-2bfreefree——Feb 26, 2026free
llama-nemotron-embed-vl-1b-v2freefree—33kFeb 10, 2026free
FLUX.2 Klein 4Bfreefree—41kJan 14, 2026free
usdcodefreefree—128kJan 1, 2026free
riva-translate-4b-instruct-v1_1freefree—128kDec 12, 2025free
Cosmos Reason2 8Bfreefree—131kDec 1, 2025free
streampetrfreefree—128kNov 13, 2025free
llama-3.1-nemotron-safety-guard-8b-v3freefree—128kOct 28, 2025free
Magistral Small 2506freefree—33kSep 25, 2025free
Mistral Medium 3freefree—131kSep 25, 2025free
Qwen Image Editfreefree——Aug 19, 2025free
FLUX.1-Kontext-devfreefree—41kAug 12, 2025free
Qwen Imagefreefree——Aug 7, 2025free
GPT OSS 20Bfreefree—131kAug 5, 2025free
llama-3_2-nemoretriever-300m-embed-v1freefree—33kJul 24, 2025free
cosmos-transfer1-7bfreefree——Jun 13, 2025free
magpie-tts-zeroshotfreefree——May 22, 2025free
Llama 3.1 Nemotron 70B Instructfreefree—128kApr 15, 2025free
Llama 3.1 Nemotron Ultra 253Bfreefree—128kApr 7, 2025free
Llama Guard 4 12Bfreefree—128kApr 5, 2025free
Mistral 7B Instruct v0.3freefree—66kApr 1, 2025free
bevformerfreefree—128kMar 18, 2025free
cosmos-predict1-5bfreefree——Mar 18, 2025free
sparsedrivefreefree—128kMar 18, 2025free
nv-embedcode-7b-v1freefree—33kMar 17, 2025free
Gemma 3 12B ITfreefree—131kMar 12, 2025free
Gemma 3 4B ITfreefree—131kMar 12, 2025free
studiovoicefreefree—128kOct 3, 2024free
Llama 3.2 90B Vision Instructfreefree—128kSep 25, 2024free
Llama 3.2 11B Vision Instructfreefree—128kSep 18, 2024free
esm2-650mfreefree—128kAug 29, 2024free
FLUX.1-devfreefree—4kAug 1, 2024free
FLUX.1-schnellfreefree—77Aug 1, 2024free
usdvalidatefreefree——Jul 24, 2024free
nv-embed-v1freefree—33kJun 7, 2024free
paligemmafreefree—128kMay 14, 2024free
rerank-qa-mistral-4bfreefree—128kMar 17, 2024free
esmfoldfreefree—128kMar 15, 2024free
BGE M3freefree—8kJan 30, 2024free
Whisper Large v3freefree——Sep 1, 2023free