Models
Price comparison

NVIDIA Nemotron 3 Nano 30B A3B FP8

NVIDIA Nemotron 3 Nano 30B A3B FP8 by NVIDIA: 8 offers. From €0.027 per 1M input tokens, with EU processing from €0.054.

Calculate costs for this modelCompare offersView price history

Profile

Profile
DeveloperNVIDIA
TypeLanguage models
OriginUS
Input typestext
Context (tokens)256,000
Max. output (tokens)1,000,000
Reasoningmit
Parameters (bn)31.58
Open weights✓ yes
LicenceNVIDIA Nemotron Open Model License
VRAM at 4-bit (GB)22 (RTX PRO 4000)
Released–

Offers with processing in the EU (3)

ProviderCountryVariantInputOutputSourceAs of
Nebius Token FactoryNLstandard€0.054€0.21tokenfactory.nebius.com14 Oct 2026
cortecsATstandard€0.054€0.21api.cortecs.ai14 Oct 2026
HostYourAINLstandard€0.15€0.40hostyourai.com14 Oct 2026

€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.

Offers outside the EU (5)

ProviderCountryVariantInputOutputSourceAs of
AWS BedrockUSflex€0.027€0.11pricing.us-east-1.amazonaws.com14 Oct 2026
CrusoeUSstandard€0.045€0.18www.crusoe.ai13 Oct 2026
Novita AIUSstandard€0.045€0.18novita.ai13 Oct 2026
AWS BedrockUSstandard€0.054€0.21pricing.us-east-1.amazonaws.com14 Oct 2026
AWS BedrockUSpriority€0.098€0.38pricing.us-east-1.amazonaws.com14 Oct 2026

€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.

AI Act

Whether the developer has signed the Code of Practice for general-purpose AI models: unknown. What this means is explained under “EU and AI Act”. EU processing and AI Act

Benchmarks

Benchmarks
GPQA Diamond (Artificial Analysis)75.7
Humanity's Last Exam (Artificial Analysis)11.4
Vectara HHEM-2.39.6
Vectara HHEM-2.3 – antwortrate99.6
Vectara HHEM-2.3 – halluzination9.6

Report an error on this page