NVIDIA-Nemotron-3.5-Lightning

NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.

Context
262K
Input price
$0.06/1M tokens
Output price
$0.16/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDnvidia/NVIDIA-Nemotron-3.5-Lightning
Provider DeepInfra
Creator NVIDIA
Family—
License—
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters—
Architecture—
Context window262K tokens
Max input—
Max output—
Reasoning tokensYes
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.deepinfra.com/v1/openai/v1/chat/completions

Pricing

Input
$0.06
Output
$0.16
Cache write
—
Cache read
$0.03
Batch in
—
Batch out
—

API

GET/v1/models/deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning

NVIDIA-Nemotron-3.5-Lightning

nvidia/NVIDIA-Nemotron-3.5-Lightning

NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.

Changes · 4 entries
nvidia/NVIDIA-Nemotron-3.5-Lightningcreateca7a400Nov 2, 2026, 03:02 AM
nvidia/NVIDIA-Nemotron-3.5-Lightningupdate1a66bb0Sep 29, 2026, 06:40 AM
pricinginput$0.08→$0.06output$0.2→$0.16cached input$0.04→$0.03
nvidia/NVIDIA-Nemotron-3.5-Lightningupdatebe35184Aug 17, 2026, 04:02 AM
context_window28672→262144
pricinginput$0.05→$0.08cached input$0.04
reasoning_tokensyes
nvidia/NVIDIA-Nemotron-3.5-Lightningcreate3cddff5Aug 13, 2026, 02:54 AM