impulse

Nemotron 3.5 Lightning

Open weights

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.

API id Nemotron-3_5-LightningReleased 11 Aug 2026 (Aug 2026)
Input / 1M
$0.06
at Nebius AI Studio
Output / 1M
$0.24
at Nebius AI Studio
Context window
1M
tokens
Max output
1M
tokens per reply
Hosts
1
1 listings
Released
Aug 2026
11 Aug 2026

Pricing

List prices at Nebius AI Studio, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.06$0.24
Cached input
50% off input
$0.03

What it costs a month

At Nebius AI Studio list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$33.30
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$30.24
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$61.20
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$202
Use your own numbers

Where to run it

1 host serve Nemotron 3.5 Lightning. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Nemotron-3_5-Lightning
$0.06 / $0.24

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: NVIDIA Open Model License
Runs in about 75.8 GB of GPU memory
Runtimes: TGI, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Nebius AI Studio.

Smaller NVIDIA models

No cheaper NVIDIA model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • MiniMax M3.1 Flash
    MiniMax · on Refuseless
    $0.05 / $0.25
    Has every key capability
    5% less
  • Qwen3.5 9B
    Alibaba Qwen · on EmpirioLabs AI
    $0.09 / $0.13
    Has every key capability
    5% less
  • GLM 5.3 Flash
    Zhipu AI · on CLF AI Gateway
    $0.06 / $0.20
    Has every key capability
    10% less
  • Ling 3.0 Flash
    Independent · on DeepInfra
    $0.06 / $0.18
    Has every key capability
    14% less

Call it

Using Nebius AI Studio's API.

Python
from litellm import completion

response = completion(
    model="nebius/Nemotron-3_5-Lightning",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Nemotron 3.5 Lightning cost?

On Nebius AI Studio, Nemotron 3.5 Lightning costs $0.06 per million input tokens and $0.24 per million output tokens. Cached input costs $0.03 per million tokens.

Which APIs offer Nemotron 3.5 Lightning?

Nemotron 3.5 Lightning runs on 1 API: Nebius AI Studio.

What is Nemotron 3.5 Lightning's context window?

1M tokens, with up to 1M tokens in one reply.

Is Nemotron 3.5 Lightning being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Nemotron 3.5 Lightning?

Models that cost less and keep most of what it can do: MiniMax M3.1 Flash on Refuseless (5% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Nemotron 3.5 Lightning released?

NVIDIA released it on 11 Aug 2026.

What is Nemotron 3.5 Lightning's API model id?

Use Nemotron-3_5-Lightning with Nebius AI Studio.

Sources

Raw catalog entry for Nemotron-3_5-Lightning on Nebius AI Studio
{
  "max_input_tokens": 1048576,
  "max_output_tokens": 1048576,
  "input_cost_per_token": 6e-8,
  "output_cost_per_token": 2.4e-7,
  "litellm_provider": "nebius",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_reasoning": true,
  "source": "https://tokenfactory.nebius.com/api/public/models_info",
  "cache_read_input_token_cost": 3e-8
}