Get started

Nemotron 3.5 Lightning

Sold by 5 sellers, timed at 260 tok/s, and scored 5.5 on the Intelligence Index.

retrieved sha256 · 0bb53a77713f

Models/NVIDIA/Nemotron 3.5 LightningUSD per 1M tokens · as OpenRouter routes it
nvidia/nemotron-3.5-lightningNVIDIA · base listing · Other tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.07per 1M tokens
Output$0.20per 1M tokens
Cached input$0.04per 1M tokens
Context1.05M1,048,576 tokens
What Vitna read · the provider's own pricing page, kept as a dated recordin / out per 1M tokens
DeepInfraopen weights$0.06 / $0.16confirmed 22 Nov 2026

The same weights, served by one provider at its own list price, read from deepinfra.com. OpenRouter's rate is its routed rate across whichever sellers it uses, and the two need not agree.

What the list says · the fields OpenRouter publishes for this id11 fields
AuthorNVIDIA
Listed
Canonical idnvidia/nemotron-3.5-lightning-20260807
Context1,048,576 tokens
Max output235,929 tokens
Modalitiestext → text
TokenizerOther
Reasoningoptional
Moderationnot moderated by OpenRouter
Other listingfree variant
What the weights say · read from the model's own repository on Hugging Faceretrieved from huggingface.co ↗
Parameters31.6B · 31,577,937,344 declared
Model classNemotronHForCausalLM
Downloadnot gated
Published

What sellers charge

5 sellers · 3.5x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $0.02 at Darkbloom to $0.07 at ModelRun. 3 sellers undercut the $0.07 listed; 0 are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.

Measured speed

10,681 requests · 5 endpoints · 30-minute window
Throughput260 tok/sMedian output rate, weighted across the 5 endpoints serving it by the requests each answered.the speed board
First token275msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread78 to 336The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.the board, fastest first

OpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.

Every endpoint

5 priced · 5 timed · cheapest first
  1. Darkbloomdarkbloom/int4$0.02$0.096$0.01int466k78 tok/s47.1737ms139 req100%
  2. Fireworksfireworks$0.05$0.20$0.01not declared236k252 tok/s128310ms6,410 req100%
  3. DeepInfradeepinfra/bf16$0.06$0.16$0.03bf1633k215 tok/s127243ms1,227 req100%
  4. CoreWeavecoreweave/bf16 · listed$0.07$0.20$0.04bf16236k216 tok/s134377ms764 req100%
  5. ModelRunmodelrun/fp4 · listed$0.07$0.20$0.04fp4944k336 tok/s190122ms2,141 req100%

Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 4 of the 5 timed routes are slower than it, and the middle route runs at 216 tok/s. The widest median-to-p90 gap is Fireworks's, 1.97x.

Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . 5 of the 6 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Fireworks at 84.95% on 18 Nov 2026, CoreWeave at 93.25% on 16 Nov 2026, Io Net at 97.93% on 23 Oct 2026, Darkbloom at 98.73% on 10 Nov 2026, and 1 more. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.

Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .

What each seller accepts

19 parameters · 5 sellers
  1. frequency_penaltyevery seller
  2. include_reasoningevery seller
  3. max_tokensevery seller
  4. presence_penaltyevery seller
  5. reasoningevery seller
  6. repetition_penaltyevery seller
  7. response_formatevery seller
  8. stopevery seller
  9. structured_outputsevery seller
  10. temperatureevery seller
  11. tool_choiceevery seller
  12. toolsevery seller
  13. top_pevery seller
  14. top_k4 of 5not ModelRun
  15. logprobs3 of 5not DeepInfra and ModelRun
  16. seed3 of 5not Fireworks and ModelRun
  17. top_logprobs3 of 5not DeepInfra and ModelRun
  18. logit_bias2 of 5not CoreWeave, Darkbloom, and ModelRun
  19. min_p1 of 5only DeepInfra

13 of these 19 are accepted by every one of the 5 sellers that publish a list; the other 6 are declared by some sellers and not others, so what a request sending one of them gets depends on which seller serves it. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.

Price position

342 priced models

Blended $0.103 per million tokens, 3 in to 1 out: cheaper than 311 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.

Measured quality

145 models with an index · 132 on a design arena board

Each mark is one board this model stands on, placed at the share of that board it scores above, and led to its number in the list under the rule. The columns and the ledger below carry the figures.

Intelligence Index5.5Position 52 of 58, above 10% of the models scored.the intelligence leaderboard
Coding Index26.8Position 87 of 118, above 26% of the models scored.the coding leaderboard
Agentic Index3.5Position 68 of 94, above 28% of the models scored.the agentic leaderboard

Not ranked in any Design Arena category.

Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals

Epoch AI has not placed Nemotron 3.5 Lightning on its Capabilities Index, or places it under a name the pairing does not reach. Epoch places a model once four of its benchmarks carry a result.

Benchmark results

none of 6 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for Nemotron 3.5 Lightning under a name that matches its listing, and names are matched to the catalog exactly and never guessed. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Source: each model's own Hugging Face repository (huggingface.co), as of 20 Nov 2026. 162 repositories read, 4 did not answer.
Licence, parameter count, model class and gating: each model's own Hugging Face repository, the one OpenRouter names for the listing.
A licence is the tag the uploader put on the repository, read from nothing else and verified by nobody.
A parameter count is the total the repository's safetensors files declare; for a mixture of experts that is every expert, not the share one token runs through.
Vitna ran none of these evaluations and adjusted none of these figures.