Home/Models
Models/Nvidia

Nemotron 3.5 Lightning 30B A3B

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.

nvidia/nemotron-3.5-lightning
Organization
Nvidia
Family
nemotron
Providers
15
Context
262,144
Output limit
262,144
Knowledge
2025-09
Release
2026-08-11
Updated
—
Weights
Open
Input
text
Output
text
Capabilities
—

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

26 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
AIHubMix
nemotron-3.5-lightning-free
262,144262,144— / ————
View
CoreWeave
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B
262,144262,144— / ————
View
Fireworks AI
accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b
262,144262,144— / ————
View
Kilo Gateway
nvidia/nemotron-3.5-lightning
262,144235,929— / ————
View
Kilo Gateway
nvidia/nemotron-3.5-lightning:free
1,000,00065,536— / ————
View
Merge Gateway
nvidia/nemotron-3.5-lightning-30b-a3b
1,000,000262,144— / ————
View
NanoGPT
nvidia/nemotron-3.5-lightning
1,000,00065,536— / ————
View
NanoGPT
nvidia/nemotron-3.5-lightning:thinking
1,000,00065,536— / ————
View
NanoGPT
TEE/nemotron-3.5-lightning
262,14465,536— / ————
View
Nebius Token Factory
nvidia/Nemotron-3_5-Lightning
1,048,5761,048,576— / ————
View
Nvidia
nvidia/nemotron-3.5-lightning-30b-a3b
262,144262,144— / ————
View
OpenCode
nemotron-3.5-lightning-free
262,144262,144— / ————
View
CoreWeavevia OpenRouter
nvidia/nemotron-3.5-lightning
bf16		262,144235,929$0.07 / $0.20YesYesYes
View
Darkbloomvia OpenRouter
nvidia/nemotron-3.5-lightning
int4		262,14432,768$0.025 / $0.12YesYesYes
View
DeepInfravia OpenRouter
nvidia/nemotron-3.5-lightning
bf16		262,14432,768$0.06 / $0.16YesYesYes
View
Io Netvia OpenRouter
nvidia/nemotron-3.5-lightning
unknown		262,144131,072$0.0469 / $0.134YesYesYes
View
Nvidiavia OpenRouter
nvidia/nemotron-3.5-lightning:free
nvfp4		1,000,00065,536$0.00 / $0.00YesYesNo
View
Phalavia OpenRouter
nvidia/nemotron-3.5-lightning
unknown		262,144235,929$0.07 / $0.20YesYesYes
View
Wafervia OpenRouter
nvidia/nemotron-3.5-lightning
unknown		262,144235,929$0.045 / $0.13YesYesYes
View
Pioneer
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
65,5364,096— / ————
View
Requesty
nemotron-3.5-lightning-30b-a3b
1,048,57665,536— / ————
View
RunInfra
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
262,14432,768— / ————
View
Thinking Machines
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16:peft:262144
262,144262,144— / ————
View
Thinking Machines
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
65,53665,536— / ————
View
Vercel AI Gateway
nvidia/nemotron-3.5-lightning
262,144131,072— / ————
View
Vercel AI Gateway
nvidia/nemotron-3.5-lightning-free
1,000,00065,000— / ————
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$0.00Per 1M input tokens
Output from$0.00Per 1M output tokens
Available offers26Across 15 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 7 lowest-priced configurations
InputOutput
Nvidianvidia/nvfp4
$0.00$0.00
Darkbloomdarkbloom/int4
$0.025$0.12
Waferwafer
$0.045$0.13
Io Netio-net
$0.0469$0.134
DeepInfradeepinfra/bf16
$0.06$0.16
CoreWeavecoreweave/bf16
$0.07$0.20
Phalaphala
$0.07$0.20
nvidia/nemotron-3.5-lightningObserved
Input
$0.07
Output
$0.20
Cache read
$0.04
nvidia/nemotron-3.5-lightning:freeObserved
Input
$0.00
Output
$0.00
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
CoreWeavecoreweave/bf16$0.07$0.20$0.04—
Darkbloomdarkbloom/int4$0.025$0.12$0.0125—
DeepInfradeepinfra/bf16$0.06$0.16$0.03—
Io Netio-net$0.0469$0.134$0.02345—
Phalaphala$0.07$0.20$0.04—
Waferwafer$0.045$0.13$0.027—
Nvidianvidia/nvfp4$0.00$0.00——

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
CoreWeavecoreweave/bf16
391–1,117.45 ms
Darkbloomdarkbloom/int4
711–7,519.26 ms
DeepInfradeepinfra/bf16
597–3,977.24 ms
Io Netio-net
625–3,996.5 ms
Phalaphala
506–4,648.4 ms
Waferwafer
678–3,287.02 ms
All latency percentiles 7 endpoints
EndpointP50P75P90P99
CoreWeavecoreweave/bf16391 ms443 ms542.9 ms1,117.45 ms
Darkbloomdarkbloom/int4711 ms1,483.5 ms2,519 ms7,519.26 ms
DeepInfradeepinfra/bf16597 ms1,300.5 ms1,872 ms3,977.24 ms
Io Netio-net625 ms1,193.5 ms1,948.4 ms3,996.5 ms
Phalaphala506 ms2,503 ms3,809 ms4,648.4 ms
Waferwafer678 ms737.5 ms902.4 ms3,287.02 ms
Nvidianvidia/nvfp4502.5 ms1,304.25 ms4,357.9 ms23,311 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
CoreWeavecoreweave/bf16
137–391.09 t/s
Darkbloomdarkbloom/int4
47–147 t/s
DeepInfradeepinfra/bf16
121–264.8 t/s
Io Netio-net
23–164.24 t/s
Phalaphala
75–221.67 t/s
Waferwafer
144–207.65 t/s
All throughput percentiles 7 endpoints
EndpointP50P75P90P99
CoreWeavecoreweave/bf16137 t/s172 t/s210 t/s391.09 t/s
Darkbloomdarkbloom/int447 t/s78 t/s117.6 t/s147 t/s
DeepInfradeepinfra/bf16121 t/s158 t/s195 t/s264.8 t/s
Io Netio-net23 t/s24 t/s25 t/s164.24 t/s
Phalaphala75 t/s93 t/s132.3 t/s221.67 t/s
Waferwafer144 t/s159 t/s172 t/s207.65 t/s
Nvidianvidia/nvfp435 t/s43 t/s69 t/s131.09 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 7 endpoints
Endpoint5 minutes30 minutes24 hours
CoreWeavecoreweave/bf16
Darkbloomdarkbloom/int4
DeepInfradeepinfra/bf16
Io Netio-net
Phalaphala
Waferwafer
Nvidianvidia/nvfp4

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations
nvidia/nemotron-3.5-lightningObserved
Benchmark profileArtificial Analysis · shared source scale from 0 to 30
Coding26.8
Agentic3.5
Intelligence12.9
nvidia/nemotron-3.5-lightning:freeObserved
Benchmark profileArtificial Analysis · shared source scale from 0 to 30
Coding26.8
Agentic3.5
Intelligence12.9

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
gpqa diamondNVIDIA: Nemotron 3.5 Lightning
70.081%
tau bench verified airlineNVIDIA: Nemotron 3.5 Lightning
65.273%
EvaluationConfigurationSourceResultsDetails
gpqa diamondNVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning-20260807OpenRouter70.081%
Details
tau bench verified airlineNVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning-20260807OpenRouter65.273%
Details
Composite indicesNemotron 3.5 Lightningnvidia/nemotron-3.5-lightning-20260807Artificial AnalysisIntelligence 12.9 · Coding 26.8 · Agentic 3.5
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Oct 18, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Hermes Agentnvidia/nemotron-3.5-lightning-202608072–9 turns
$0.001708
Details

Source: OpenRouter, as of Oct 20, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
nvidia/nemotron-3.5-lightningObserved
Context
262,144
Maximum output
235,929
Tokenizer
Other
Input
text
Output
text
Moderation
No
Added to OpenRouter
2026-08-11
Base URLhttps://openrouter.ai/api/v1
Model IDnvidia/nemotron-3.5-lightning
Version IDnvidia/nemotron-3.5-lightning-20260807
Weights IDnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

Reasoning

Required
No
Enabled by default
Not reported
Default effort
—
Supported efforts
—

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p
nvidia/nemotron-3.5-lightning:freeObserved
Context
1,000,000
Maximum output
65,536
Tokenizer
Other
Input
text
Output
text
Moderation
No
Added to OpenRouter
2026-08-11
Base URLhttps://openrouter.ai/api/v1
Model IDnvidia/nemotron-3.5-lightning:free
Version IDnvidia/nemotron-3.5-lightning-20260807
Weights IDnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

Reasoning

Required
No
Enabled by default
Not reported
Default effort
—
Supported efforts
—

Supported parameters

  • include_reasoning
  • max_tokens
  • reasoning
  • seed
  • temperature
  • tool_choice
  • tools
  • top_p

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Nemotron 3.5 Lightning 30B A3B cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Nemotron 3.5 Lightning 30B A3B?

There are 26 cataloged offers across 15 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 262,144 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Not reported. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 3 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

  • · 9611c015e976
  • · 2e1bf2ae8bd0
  • · 9f939d112577