Skip to content
OpenSmartRoute
Model catalogue
NVIDIA

NVIDIA

Nemotron 3.5 Lightning

nvidia/nemotron-3.5-lightning

Specification

Published by the vendor; the platform bills at the target's declared price.

NVIDIA

Nemotron 3.5 Lightning

reasoning open weights tools

NVIDIA nvidia/nemotron-3.5-lightning

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

Input $/1M
$0.08
Output $/1M
$0.20
Context
262K
Max output
131K
Released
Aug 11, 2026
Modalities
text
Intelligence index-
Coding index27
Agentic index-

Cached input reads $0.04 per 1M · weights on Hugging Face as nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet
Add a target with metadata.model set to this id.
targets.yamlyaml
# targets.yaml - declare a target that runs Nemotron 3.5 Lightning
targets:
  - id: nemotron-3-5-lightning
    kind: llm
    name: Nemotron 3.5 Lightning
    metadata:
      model: nvidia/nemotron-3.5-lightning          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 262144
    cost:
      usd_per_1k_tokens: 0.000140