BroadRouter

Nemotron 3.5 Lightning 30B A3B vs Nemotron 3 Nano 30B A3B API pricing

Updated

Nemotron 3.5 Lightning 30B A3B: USD 0.06 input, USD 0.16 output per 1M tokens (DeepInfra). Nemotron 3 Nano 30B A3B: USD 0.05 input, USD 0.20 output per 1M tokens (Novita AI). At 3 input tokens per output token, Nemotron 3 Nano 30B A3B costs 2.9% more than Nemotron 3.5 Lightning 30B A3B (USD 0.0875 vs USD 0.085 per 1M).

Nemotron 3 Nano 30B A3B is the release before Nemotron 3.5 Lightning 30B A3B in the same NVIDIA line (by version in the name), so this page shows what the newer release costs. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

How do Nemotron 3.5 Lightning 30B A3B and Nemotron 3 Nano 30B A3B differ on price?

Nemotron 3.5 Lightning 30B A3B and Nemotron 3 Nano 30B A3B prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Nemotron 3.5 Lightning 30B A3B and Nemotron 3 Nano 30B A3B API prices compared
PriceNemotron 3.5 Lightning 30B A3BNemotron 3 Nano 30B A3B
Model pageNVIDIA Nemotron 3.5 Lightning 30B A3B
NVIDIA · 5 providers
NVIDIA Nemotron 3 Nano 30B A3B
NVIDIA · 3 providers
Cheapest standard price, blended 3:1USD 0.085 lower
USD 0.06 in / USD 0.16 out at DeepInfra
DeepInfra page checked 2026-11-14
USD 0.0875
USD 0.05 in / USD 0.20 out at Novita AI
Novita AI page checked 2026-11-14
Cheapest inputUSD 0.05 tie
Crusoe Cloud source
USD 0.05 tie
Novita AI source
Cheapest cached inputUSD 0.01
Fireworks AI source
No standard price lists a cache price; cached tokens bill at the input price.
Cheapest outputUSD 0.16 lower
DeepInfra source
USD 0.20
Novita AI source
Maker's own APINVIDIA publishes no paid standard price on its own API that we found.NVIDIA publishes no paid standard price on its own API that we found.
Median standard priceUSD 0.06 / USD 0.20
input / output, 5 prices
USD 0.06 / USD 0.24
input / output, 3 prices
Context window1,048,576 tokens, largest stated; from 262,144 at some providers262,144 tokens, largest stated; from 128,000 at some providers
Providers with a standard price53

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do Nemotron 3.5 Lightning 30B A3B and Nemotron 3 Nano 30B A3B cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on Nemotron 3.5 Lightning 30B A3B and Nemotron 3 Nano 30B A3B
WorkloadNemotron 3.5 Lightning 30B A3BNemotron 3 Nano 30B A3BDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 5.94
Fireworks AI
USD 8.10
Novita AI
USD 2.16
Nemotron 3.5 Lightning 30B A3B lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 12.12
Fireworks AI
USD 15.00
Novita AI
USD 2.88
Nemotron 3.5 Lightning 30B A3B lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 46.80
Fireworks AI
USD 108.00
Novita AI
USD 61.20
Nemotron 3.5 Lightning 30B A3B lower

Nemotron 3.5 Lightning 30B A3B is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 2.31× as much as the cheaper one.

Does the cheaper model change with your input:output ratio?

The cheaper model changes with the mix: below 4 input tokens per output token, Nemotron 3.5 Lightning 30B A3B is cheaper; above 4, they cost the same. At the site's 3:1 blend, Nemotron 3.5 Lightning 30B A3B is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.

Price per 1M tokens of Nemotron 3.5 Lightning 30B A3B and Nemotron 3 Nano 30B A3B at different input:output mixes
Input : output tokensNemotron 3.5 Lightning 30B A3BNemotron 3 Nano 30B A3B
1 : 3 (long answers)USD 0.135 lower
DeepInfra
USD 0.1625
Novita AI
1 : 1USD 0.11 lower
DeepInfra
USD 0.125
Novita AI
3 : 1 (the site’s blend)USD 0.085 lower
DeepInfra
USD 0.0875
Novita AI
10 : 1 (retrieval, long prompts)USD 0.06364 tie
Crusoe Cloud
USD 0.06364 tie
Novita AI
30 : 1 (agents, big contexts)USD 0.05484 tie
Crusoe Cloud
USD 0.05484 tie
Novita AI

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do Nemotron 3.5 Lightning 30B A3B and Nemotron 3 Nano 30B A3B cost per character in other languages?

Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the Nemotron 3 Ultra tokenizer for Nemotron 3.5 Lightning 30B A3B (the same one for both, so the gap equals the price gap):

Input cost per 1M characters by language, Nemotron 3.5 Lightning 30B A3B and Nemotron 3 Nano 30B A3B
ContentNemotron 3.5 Lightning 30B A3BNemotron 3 Nano 30B A3B
EnglishUSD 0.011
Crusoe Cloud
USD 0.011
Novita AI
Arabic MSAUSD 0.015
Crusoe Cloud
USD 0.015
Novita AI
Egyptian ArabicUSD 0.016
Crusoe Cloud
USD 0.016
Novita AI
HindiUSD 0.019
Crusoe Cloud
USD 0.019
Novita AI
ChineseUSD 0.045
Crusoe Cloud
USD 0.045
Novita AI
SpanishUSD 0.012
Crusoe Cloud
USD 0.012
Novita AI
CodeUSD 0.013
Crusoe Cloud
USD 0.013
Novita AI

From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.

Check it on your own traffic

Questions

Is Nemotron 3.5 Lightning 30B A3B cheaper than Nemotron 3 Nano 30B A3B?

Yes. On a blend of 3 input tokens to 1 output token, Nemotron 3.5 Lightning 30B A3B costs USD 0.085 per 1M tokens and Nemotron 3 Nano 30B A3B USD 0.0875, at each model's cheapest standard price. For input alone, both start at USD 0.05 per 1M; for output alone, Nemotron 3.5 Lightning 30B A3B is (USD 0.16 against USD 0.20). This compares price only, not quality.

What do Nemotron 3.5 Lightning 30B A3B and Nemotron 3 Nano 30B A3B cost per 1M tokens?

Nemotron 3.5 Lightning 30B A3B: from USD 0.06 input and USD 0.16 output at DeepInfra; median of 5 standard prices USD 0.06 / USD 0.20. Nemotron 3 Nano 30B A3B: from USD 0.05 input and USD 0.20 output at Novita AI; median of 3 standard prices USD 0.06 / USD 0.24. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both Nemotron 3.5 Lightning 30B A3B and Nemotron 3 Nano 30B A3B?

None of the providers we track sells both at a standard price. Nemotron 3.5 Lightning 30B A3B is cheapest at DeepInfra and Nemotron 3 Nano 30B A3B at Novita AI, so running both means two accounts.

Which is cheaper for a coding agent or a chatbot, Nemotron 3.5 Lightning 30B A3B or Nemotron 3 Nano 30B A3B?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 46.80 a month on Nemotron 3.5 Lightning 30B A3B (Fireworks AI) against USD 108.00 on Nemotron 3 Nano 30B A3B (Novita AI), a difference of USD 61.20. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 5.94 a month on Nemotron 3.5 Lightning 30B A3B (Fireworks AI) against USD 8.10 on Nemotron 3 Nano 30B A3B (Novita AI), a difference of USD 2.16. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of Nemotron 3.5 Lightning 30B A3B and Nemotron 3 Nano 30B A3B change?

The cheaper model changes with the mix: below 4 input tokens per output token, Nemotron 3.5 Lightning 30B A3B is cheaper; above 4, they cost the same. At the site's 3:1 blend, Nemotron 3.5 Lightning 30B A3B is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.

Do Nemotron 3.5 Lightning 30B A3B and Nemotron 3 Nano 30B A3B have cached input pricing?

Nemotron 3.5 Lightning 30B A3B from USD 0.01 per 1M cached input tokens (Fireworks AI; 5 of 5 standard prices list a discount). Nemotron 3 Nano 30B A3B: no standard price lists a cached-input discount. Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, Nemotron 3.5 Lightning 30B A3B or Nemotron 3 Nano 30B A3B?

Nemotron 3.5 Lightning 30B A3B: up to 1,048,576 tokens, against 262,144 for Nemotron 3 Nano 30B A3B, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity