ModelPriceWatch.com
Last scan 2026-10-02 Models tracked 273 Providers 35 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

NVIDIA Nemotron 3.5 Lightning

by DeepInfra · 30B (3B active) parameters

Current open weights open weights cheap tier
Email me when NVIDIA Nemotron 3.5 Lightning gets cheaper
Availability: The 256K context here is DeepInfra's, and it is what you get on this endpoint. NVIDIA's own model page and other catalogues advertise 1M tokens for the open weights, so the same model served elsewhere or self-hosted may accept a longer prompt than this row's price buys.

Today's price · per 1M tokens

Input

$0.080

per 1M tokens

Output

$0.200

per 1M tokens

Blended

$0.110

blended $/1M — 3:1 weighted input:output

Cached input

$0.040

50% of input — prompt caching

Source: official DeepInfra pricing · read MODELPRICEWATCH.COM · 2026-10-02

Price receipt

We read DeepInfra's own pricing page on and found NVIDIA-Nemotron-3.5-Lightning listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is 1829065880.

Overview

NVIDIA Nemotron 3.5 Lightning served on DeepInfra at $0.08/$0.20 per 1M tokens, with cached input at $0.04. The cheapest of the three hosts serving it (CoreWeave and Venice both list $0.10/$0.25). NVIDIA publishes no per-token price of its own for this model, so a host rate is the only price it has.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

RunPod →
Rent GPUs by the second and serve any open-weight model yourself.
Novita AI →
Serverless open-model inference billed per token — no GPU ops.
Vast.ai →
GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

struck through = not supported
Input 1/4
Text ✓ Image Audio Video
Output
Text ✓
Features 3/9
Prompt caching ✓ Reasoning Coding Fast inference Long context ✓ Open weights ✓ Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Percentile vs all tracked models 29.1th2 independent measurements
Percentile per $/Mtok 264.5
GPQA Diamond vendor
75.57%
SWE-Bench Verified vendor
52.8%
Terminal-Bench 2.1 vendor
23.46%
BrowseComp vendor
36.81%
Humanity's Last Exam vendor
10.47%

Every per-benchmark score we hold for this model is reported by its own vendor, so none is counted toward an accuracy average or any ranking. The percentile above is its standing across the independent composites below.

Independent composite scores
  • AA Intelligence Index: 12.9 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA-Omniscience Index: -17.7 (−100–100)
How it stacks up
  • Ranks #125 of 189 comparably-measured models by percentile score, across 2 independent measurements
  • Ranks #7 of 189 comparably-tested models by normalized performance per dollar

302.1 tokens/sec output

Source: Artificial Analysis, NVIDIA NIM API docs model card (HLE text-only, no tools, NVFP4 variant), NVIDIA NIM API docs model card (NVFP4 variant) · updated · See full rankings →

Specifications

Provider
DeepInfra
Context window
256K tokens
Modality
text
Parameters
30B (3B active)
Open source
Yes — open weights available
Released
Status
Current
Last updated
Tags
open-weightscachingcheap

Availability verified: — listed on DeepInfra's own page

Try on DeepInfra Official pricing page