Where is the Nemotron 3.5 Lightning documentation?

The Nemotron 3.5 Lightning documentation on OpenRouter includes the What Is Nemotron 3.5 Lightning blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does Nemotron 3.5 Lightning cost?

Nemotron 3.5 Lightning costs $0.025/M input tokens and $0.12/M output tokens, with separate rates for Cache Read at $0.0125/M tokens.

What is the context length of Nemotron 3.5 Lightning?

Nemotron 3.5 Lightning has a 262,144 token context window. It supports up to 65,536 completion tokens.

Does Nemotron 3.5 Lightning support tool calling and structured outputs?

Yes. Nemotron 3.5 Lightning accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Which providers serve Nemotron 3.5 Lightning?

Nemotron 3.5 Lightning is served by 4 providers on OpenRouter: Darkbloom, Fireworks, DeepInfra, and CoreWeave. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Nemotron 3.5 Lightning released?

Nemotron 3.5 Lightning was released on August 11, 2026.

For the free endpoint, please do not upload any confidential information or personal data (such as voices or faces of people). Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about NVIDIA's data processing practices, see Privacy Policy. By using this free endpoint, you consent to NVIDIA's collection, recording, and use of such information and the NVIDIA API Trial Terms of Service

NVIDIA: Nemotron 3.5 Lightning (nitro)

nvidia/nemotron-3.5-lightning:nitro

Model weights

Compare

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 benefit from domain-specific customization.

Modalities

In / out price

$0.025 / $0.12per 1M

Context

262K

Released

Aug 11, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput

Input /M	Output /M	Cache read /M	Latency	Throughput	Uptime
$0.05	$0.20	$0.01	0.24s	457 tok/s	100.00%
$0.06	$0.16	$0.03	0.26s	210 tok/s	99.82%
$0.025	$0.12	$0.0125	1.23s	109 tok/s	99.40%
$0.07	$0.20	$0.04	0.53s	94 tok/s	100.00%

Input $0.05Output $0.20
457 tok/s100.00% uptime
Input $0.06Output $0.16
210 tok/s99.82% uptime
Input $0.025Output $0.12
109 tok/s99.40% uptime
Input $0.07Output $0.20
94 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.05397/M tokens

Output

$0.1847/M tokens

Nemotron 3.5 Lightning — Price history

Price history

No effective price data for this selection

$0.0186	$0.120	49.6%	4.4%
$0.0250	$0.200	61.9%	12.6%
$0.0478	$0.159	40.2%	11.7%
$0.0593	$0.200	35.5%	71.3%

Effective in $0.0186Effective out $0.120
Token share
4.4%
Effective in $0.0250Effective out $0.200
Token share
12.6%
Effective in $0.0478Effective out $0.159
Token share
11.7%
Effective in $0.0593Effective out $0.200
Token share
71.3%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

457tok/s

P50, best across providers

Latency

0.24s

P50, best provider

Latency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchCoreWeave75.7%70.0%Io Net76.7%66.3%DeepInfra72.8%66.0%auto-routing71.7%66.5%Darkbloom66.3%65.6%

+1 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.92%

Availability over the last 3 days

Last 72 hours

Availability 99.92%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.92%

Without Routing

99.61%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for NVIDIA: Nemotron 3.5 Lightning (Artificial Analysis)
Source	Benchmark	Score
Artificial Analysis	Nemotron 3.5 Lightning Intelligence Index	5.5
Artificial Analysis	Nemotron 3.5 Lightning Coding Index	26.8
Artificial Analysis	Nemotron 3.5 Lightning Agentic Index	3.5
Artificial Analysis	Nemotron 3.5 Lightning GPQA Diamond	74.3%
Artificial Analysis	Nemotron 3.5 Lightning HLE	10.6%
Artificial Analysis	Nemotron 3.5 Lightning AA-LCR	60.3%
Artificial Analysis	Nemotron 3.5 Lightning τ-Bench Banking	8.9%
Artificial Analysis	Nemotron 3.5 Lightning GDPval-AA	7.3%
Artificial Analysis	Nemotron 3.5 Lightning CritPt	0.0%
Artificial Analysis	Nemotron 3.5 Lightning SciCode	32.1%
Artificial Analysis	Nemotron 3.5 Lightning Terminal-Bench 4.0	0.5%
Artificial Analysis	Nemotron 3.5 Lightning Terminal-Bench 2.1	24.3%
Artificial Analysis	Nemotron 3.5 Lightning AA-Omniscience Accuracy	14.7%
Artificial Analysis	Nemotron 3.5 Lightning AA-Omniscience Non-Hallucination Rate	64.3%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

7.51Btokens

Sentient

new

2.91Btokens

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

1.45Btokens

threat.gg

new

1.33Btokens

There are many coding agents, but this one is yours.

1.16Btokens

Rest of OpenRouter

1.29B

Top 5 Apps

252M

Not currently available through EU in-region routing. In-region routing docs

More models from Nvidia

Nemotron 3.5 Transcribe

Nemotron 3.5 Transcribe is an open-weight speech recognition model from NVIDIA, a 30B mixture-of-experts with about 4B active parameters. It transcribes recordings of up to one hour in 40 languages, with speaker attribution, speech translation, and prompt-guided vocabulary and style.

Transcription$0.000017/second

Nemotron 3.5 Embed 1B (free)

Nemotron 3.5 Embed 1B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be text, an image, or both. It returns 2048-dim vectors that can be truncated, and shares the text embedding space of Nemotron 3 Embed 1B.

EmbeddingsFree

Nemotron 3.5 Embed 8B (free)

Nemotron 3.5 Embed 8B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be text, an image, or both. It returns 4096-dim vectors that can be truncated, and shares the text embedding space of Nemotron 3 Embed 8B.

EmbeddingsFree

Nemotron 3.5 Rerank 8B (free)

RerankFree

Nemotron 3.5 Super VL

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video as input and returns text, and is built for long-running agents that combine visual understanding with reasoning and tool use.

It uses a hybrid Mamba-Transformer architecture with multi-token prediction and supports a 1M-token context. Typical uses include document intelligence, web research, coding validation, customer service, and video understanding. Reasoning is on by default and can be turned off or given a token budget.

Text1.0M context$0.06 / $0.35

Nemotron 3.5 Super VL (free)

Text1M contextFree

Switchyard

Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most popular low and high cost models. You can pass in two choices in the models parameter as well as specify any of the routing algorithms Switchyard offers. Details in the Switchyard docs. OpenRouter then applies its normal provider routing, fallbacks and billing for the chosen model.

Text1M context

Nemotron 3.5 ASR Streaming Multilingual 0.6B

Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice agents, and multilingual transcription pipelines.

Transcription$0.000003/second

Nemotron 3.5 Lightning

Text262K context$0.025 / $0.12

Nemotron 3.5 Lightning (free)

Text1M contextFree

Nemotron 3 Embed 1B (free)

NVIDIA Nemotron 3 Embed 1B is an open text embedding model from NVIDIA, optimized for high-throughput, low-latency retrieval. It is suited for enterprise search, RAG, code retrieval, and agentic retrieval workflows, retaining more than 95% of the 8B model’s accuracy in a smaller deployment footprint.

EmbeddingsFree

Llama Nemotron Rerank VL 1B V2 (free)

Llama Nemotron Rerank VL 1B V2 is a 1.7B multimodal reranking model from NVIDIA. It evaluates the relevance of document images and text against user queries, designed for vision RAG pipelines handling charts, tables, infographics, and mixed-media documents. Functions as a cross-encoder that accepts text queries paired with image, text, or combined document inputs, delivering approximately 6-7% recall improvements over embedding-only baselines on visual document retrieval benchmarks.

RerankFree

Nemotron 3.5 Content Safety

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting text and image input and returning text output: a safe/unsafe classification for the user prompt and the response, safety category labels, and an optional reasoning trace. It covers 12 languages with a context window of up to 128K tokens.

It is suited for prompt and response moderation, content classification, safety pipelines, and enterprise AI guardrails with policy enforcement, and includes a togglable reasoning mode. It is part of the NVIDIA Nemotron family of open models for agentic AI.

Text131K context$0.20 / $0.20

Nemotron 3 Ultra

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.

It is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.

Text262K context$0.50 / $2.20

Nemotron 3 Ultra (free)

Text1M contextFree

Parakeet TDT 0.6B v3

Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across all official EU languages and achieves a 6.34% average word error rate on the HuggingFace Open ASR Leaderboard. Returns transcribed text with punctuation and segment timestamps.

Transcription$0.000017/second

Nemotron 3 Nano Omni (free)

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and audio inputs and produces text output, enabling agents to perceive and reason across modalities in a single inference loop.

Built on a hybrid MoE Transformer-Mamba architecture with Conv3D video layers and Efficient Video Sampling (EVS), it delivers approximately 2× higher throughput and 2.5× lower compute for video reasoning versus separate vision + speech pipelines. It supports up to 300K context length and a 16,384 reasoning budget, with extended thinking enabled via reasoning.enabled on OpenRouter.

Text256K contextFree

Nemotron 3 Super

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models.

The model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified.

Fully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.

Text262K context$0.075 / $0.40

Llama Nemotron Embed VL 1B V2 (free)

The Llama Nemotron Embed VL 1B V2 embedding model is optimized for multimodal question-answering retrieval. The model can embed 'documents' in the form of image, text, or image and text combined. Documents can be retrieved given a user query in text form. The model supports images containing text, tables, charts, and infographics.

EmbeddingsFree

Nemotron 3 Nano 30B A3B

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.

The model is fully open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.

Text262K context$0.06 / $0.24

NVIDIA: Nemotron 3.5 Lightning (nitro)

Providers