How much does NVIDIA: Nemotron 3.5 Lightning cost?

NVIDIA: Nemotron 3.5 Lightning costs $0.06 per 1M input tokens and $0.16 per 1M output tokens. Prompt caching is priced with cache reads at $0.03/1M tokens.

What is the context length of NVIDIA: Nemotron 3.5 Lightning?

NVIDIA: Nemotron 3.5 Lightning has a 262,144 token context window.

Does NVIDIA: Nemotron 3.5 Lightning support tool calling and structured outputs?

Yes. NVIDIA: Nemotron 3.5 Lightning supports tool calling and structured outputs.

What inputs and outputs does NVIDIA: Nemotron 3.5 Lightning support?

NVIDIA: Nemotron 3.5 Lightning accepts text as input and returns text.

What other models does NVIDIA have?

NVIDIA: Nemotron 3 Nano 30B (Free), NVIDIA: Nemotron 3 Super 120B A12B, NVIDIA: Nemotron 3 Super 120B (Free) and 3 more are other models from NVIDIA.

When was NVIDIA: Nemotron 3.5 Lightning released?

NVIDIA: Nemotron 3.5 Lightning was released on Aug 3, 2026.

Nemotron 3.5 Lightning

NVIDIAReleased Aug 3, 2026nvidia/nemotron-3.5-lightning

Cost Compare

NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks, with up to 4x higher throughput on a 1M-token context.

Context

262K

Max output

33K

Input /1M

$0.06

Output /1M

$0.16

Blended /1M

$0.08

AcceptsTextProducesTextTokenizer Other

Providers

FastRouter routes your requests to this provider. You can also bring your own key.

ProviderInput /1MOutput /1MContextMax outputLatencyThroughput

DeepInfra

deepinfra

Input /1M$0.06

Output /1M$0.16

Context262K

Max output33K

Latency—

Throughput—

Supported parameters

Request parameters you can send with this model.

Core (Sampling & basic generation)

max_tokens: Maximum tokens to generate.
seed: Seed for deterministic sampling.
stop: Sequences where generation stops.
temperature: Controls randomness of output.
top_k: Limits sampling to top K tokens.
top_p: Nucleus sampling threshold.

Penalties (Token Penalties)

frequency_penalty: Penalizes frequent tokens.
presence_penalty: Penalizes tokens already present.
repetition_penalty: Penalizes repeated tokens.

Reasoning (Reasoning Controls)

include_reasoning: Include reasoning trace in the response.
reasoning: Provider-specific reasoning configuration.

Tool Use (Function Calls & Tools)

tool_choice: How the model should use tools.
tools: Tool/function definitions available to the model.

Output & Format (Response Formatting)

logprobs: Return log probabilities of output tokens.
response_format: Structured output format configuration.

Performance

Median throughput and time to first token per provider over the last week.

Throughput

Latency

Make your first API call

OpenAI-compatible. Point your SDK at FastRouter, or call the API directly.

Full API docs

Replace <FASTROUTER_API_KEY> with your key · Get your key →Install

OpenAI SDKHTTP

from openai import OpenAI

client = OpenAI(

base_url="https://api.fastrouter.ai/api/v1", # FastRouter base URL

api_key= "<FASTROUTER_API_KEY>", # Replace with your FastRouter API key

)

completion = client.chat.completions.create(

model="nvidia/nemotron-3.5-lightning", # Replace with your model ID

messages=[

{ "role": "user", "content": "What is the meaning of life?" }

]

)

print(completion.choices[0].message.content)

Frequently asked questions

More models from NVIDIA

Nemotron 3 Nano 30B (Free)nvidia/nemotron-3-nano-30b:free

NVIDIA Nemotron 3 Nano 30B is a hybrid Mamba-2/MoE/Attention model with 3.5B active parameters, trained from scratch as a unified model for both reasoning and non-reasoning tasks. Reasoning traces can be toggled via a chat template flag, and the model supports tool use within a 1M-token context window, making it well suited for specialized agentic applications.

Nemotron 3 Super 120B A12Bnvidia/nemotron-3-super

NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts model engineered for compute efficiency and accuracy in multi-agent and specialized agentic systems, with strong reasoning, tool use and instruction following.

Nemotron 3 Super 120B (Free)nvidia/nemotron-3-super:free

NVIDIA Nemotron 3 Super is a 120B-parameter open mixture-of-experts model that activates just 12B parameters per token, delivering high compute efficiency and strong reasoning, agentic, and conversational capabilities for complex multi-agent applications. It supports tool use, thinking/reasoning traces, and a large 262K-token context window, and is optimized for collaborative agents and high-volume workloads such as IT ticket automation.

Nemotron 3 Ultra 550B A55Bnvidia/nemotron-3-ultra-550b-a55b

Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows, with up to 5x faster inference and up to 30% lower cost for agentic workloads.

Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl

NVIDIA Nemotron 3.5 Super VL is an open multimodal 120B-parameter Mixture-of-Experts model (12B active) for agents that see, reason, and act. It understands text, images, documents, GUIs, and video, and adds reasoning and tool use.

Nemotron Content Safety 3.5nvidia/nemotron-content-safety-3.5

Nemotron Content Safety 3.5 is a compact multimodal safety classifier handling text, images and custom policies, with a safe/unsafe verdict plus reasoning trace.

Model scores sourced from ArtificialAnalysis