Nemotron 3.5 Lightning

Released
2026-08-11
Last refreshed
2026-11-18
Status
Researched 46d ago
Open weightsCommercial use: permittedRAGAgentsLong contextJSON / Tool use
NVIDIA AI releases · 27 in the last 12 months · this family litChangelog →
Specifications
Released
2026-08-11
Context
1M
Parameters
30B (3B activated)
Architecture
MoE + SSM Hybrid
Specialization
general
Openness
Open weights
License
OpenMDW 1.1Permitted
Weights
Available
Code
Unknown
Training
Multi-stage
Created by

Accelerated AI for enterprise solutions

Santa Clara, California, United States
Founded 2015
Website
Pricing
Output / 1M
$0.160
Input / 1M
$0.060

Cheapest of 3 routes · FlexAI · cache read $0.009

About

NVIDIA Nemotron 3.5 Lightning (HF nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B) is an open-weight hybrid Mamba-Transformer mixture-of-experts text model with 30B total and 3B active parameters (NemotronHForCausalLM), released 11 August 2026. NVIDIA lists context up to 1M tokens (256K used for single-H100 deployment). Weights ship in BF16, NVFP4 and speculative-decoding (DSpark/DFlash) variants plus a base checkpoint under OpenMDW 1.1. It is offered on build.nvidia.com and OpenRouter (free tier).

Providers(3)

Compare all 3

Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
FlexAI$0.060$0.160read $0.009
Serverless
OpenRouter$0.060$0.160read $0.030
Serverless
Vercel AI Gateway$0.050$0.200read $0.010
Serverless

Capabilities

ReasoningJSON / Tool use

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4NVIDIA-Nemotron-3.5-Lightning-30B-A3Bnvidia/nemotron-3.5-lightning