NVIDIA Nemotron 3.5 Lightning 30B A3B API pricing
Updated
Among the 5 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for NVIDIA Nemotron 3.5 Lightning 30B A3B is DeepInfra at USD 0.06 per 1M input tokens and USD 0.16 per 1M output tokens. The median across 5 standard prices is USD 0.06 / USD 0.20. Each price is read from the provider's own pricing page.
Does NVIDIA sell NVIDIA Nemotron 3.5 Lightning 30B A3B directly?
NVIDIA publishes no price for NVIDIA Nemotron 3.5 Lightning 30B A3B on its own API that we could find, so this page compares hosts only.
NVIDIA Nemotron 3.5 Lightning 30B A3B price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 21% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | DeepInfra cheapestnvidia/NVIDIA-Nemotron-3.5-LightningNotes and source quote“$0.06 in $0.16 out $0.03 cached / 1M tokens” | USD 0.06 | USD 0.03 | USD 0.16 | USD 0.085 | 262,144 | not stated | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | Crusoe Cloudnvidia/nemotron-3.5-lightning-30b-a3bNotes and source quote“Nemotron 3.5 Lightning 30B A3B $0.05 $0.20 $0.03” | USD 0.05 | USD 0.03 | USD 0.20 | USD 0.0875 | 1,048,576 | not stated | Crusoe Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 3 | Fireworks AIaccounts/fireworks/models/nemotron-lightning-3p5-30b-a3bNotes and source quote“NVIDIA Nemotron 3.5 Lightning 30B A3B | $0.05 / $0.01 / $0.20 | $0.0625 / $0.0125 / $0.25” | USD 0.05 | USD 0.01 | USD 0.20 | USD 0.0875 | 262,144 | not stated | Fireworks AI page checked 2026-11-14 re-checked 2026-11-16 |
| 4 | Microsoft AzureNotes and source quoteFoundry Models serverless, served by Fireworks on Azure, Data Zone deployment. "3.5 LN" read as Nemotron 3.5 Lightning. “FW NVIDIA Nemotron 3.5 LN Data Zone Input: $0.06/1M Tokens | Cached Input: $0.01/1M Tokens | Output: $0.22/1M Tokens” | USD 0.06 | USD 0.01 | USD 0.22 | USD 0.10 | not stated | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
| 5 | CoreWeave Forgenvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3BNotes and source quote“NVIDIA Nemotron 3.5 Lightning $0.07 $0.20 $0.04” | USD 0.07 | USD 0.04 | USD 0.20 | USD 0.1025 | 262,144 | not stated | CoreWeave Forge page checked 2026-11-15 re-checked 2026-11-16 |
| — | Fireworks AI priorityaccounts/fireworks/models/nemotron-lightning-3p5-30b-a3bNotes and source quotePriority mode. “NVIDIA Nemotron 3.5 Lightning 30B A3B | Priority $0.0625 / $0.0125 / $0.25” | USD 0.0625 | USD 0.0125 | USD 0.25 | USD 0.1094 | 262,144 | not stated | Fireworks AI page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Other tiers (priority): batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does NVIDIA Nemotron 3.5 Lightning 30B A3B cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| DeepInfra | USD 6.66 | USD 14.64 | USD 76.50 |
| Crusoe Cloud | USD 7.02 | USD 13.56 | USD 77.40 |
| Fireworks AI | USD 5.94 | USD 12.12 | USD 46.80 |
| Microsoft Azure | USD 6.66 | USD 14.10 | USD 51.30 |
| CoreWeave Forge | USD 8.28 | USD 17.64 | USD 98.10 |
For the support chatbot, the cheapest price (Fireworks AI, USD 5.94 a month) saves USD 0.72 against the median (USD 6.66). For the coding agent the gap is USD 29.70 a month (39% lower).
Which NVIDIA Nemotron 3.5 Lightning 30B A3B provider is cheapest for your traffic?
Crusoe Cloud and Fireworks AI have the lowest input price (USD 0.05) and DeepInfra the lowest output price (USD 0.16). They cost the same at 4 input tokens per output token. With more input than that, as with long prompts or retrieval, Crusoe Cloud and Fireworks AI are cheaper; with less, as with long answers, DeepInfra is.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| DeepInfra | USD 0.085 cheapest | USD 0.07375 | USD 0.06475 |
| Crusoe Cloud | USD 0.0875 | USD 0.08 | USD 0.074 |
| Fireworks AI | USD 0.0875 | USD 0.0725 cheapest | USD 0.0605 cheapest |
| Microsoft Azure | USD 0.10 | USD 0.08125 | USD 0.06625 |
| CoreWeave Forge | USD 0.1025 | USD 0.09125 | USD 0.08225 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
All 5 providers publish a cached-input price below the input price: DeepInfra (50% off), Crusoe Cloud (40% off), Fireworks AI (80% off), Microsoft Azure (83% off), CoreWeave Forge (43% off).
Context windows differ: 1,048,576 tokens at Crusoe Cloud; 262,144 tokens at DeepInfra, Fireworks AI and CoreWeave Forge. Microsoft Azure does not state one. The cheapest row is not always the one that fits a long prompt.
What does NVIDIA Nemotron 3.5 Lightning 30B A3B cost in other languages?
The same text needs a different number of tokens in each language. With the Nemotron 3 Ultra tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for NVIDIA Nemotron 3.5 Lightning 30B A3B:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.011 | Crusoe Cloud |
| Arabic MSA | USD 0.015 | Crusoe Cloud |
| Hindi | USD 0.019 | Crusoe Cloud |
| Chinese | USD 0.045 | Crusoe Cloud |
| Code | USD 0.013 | Crusoe Cloud |
From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.
Estimate your own bill
- LLM API cost calculator with NVIDIA Nemotron 3.5 Lightning 30B A3B preloaded: your traffic and cache rate, against any of 428 models.
- Nemotron 3 token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does NVIDIA Nemotron 3.5 Lightning 30B A3B compare with other NVIDIA models?
The NVIDIA models whose cheapest standard price is closest to NVIDIA Nemotron 3.5 Lightning 30B A3B's (USD 0.085 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| NVIDIA Nemotron 3 Nano 30B A3B | USD 0.05 | USD 0.20 | 262,144 | 3 |
| NVIDIA Nemotron 3 Super 120B A12B | USD 0.075 | USD 0.40 | 262,144 | 3 |
| NVIDIA Nemotron 3.5 Super VL | USD 0.10 | USD 0.40 | 1,000,000 | 6 |
| NVIDIA Nemotron 3 Ultra | USD 0.50 | USD 2.15 | 262,144 | 9 |
Priced closest from other makers: Phi-4 (Microsoft, USD 0.0875) · IBM Granite 4.2 8B (IBM, USD 0.0825) · DeepSeek V4 Flash 0731 (DeepSeek, USD 0.09).
Compare NVIDIA Nemotron 3.5 Lightning 30B A3B with
- Nemotron 3.5 Lightning 30B A3B vs Nemotron 3 Nano 30B A3B: API price side by side
Also compared: vs NVIDIA Nemotron 3 Nano 30B A3B.
Every NVIDIA Nemotron 3.5 Lightning 30B A3B price comparison · All model-vs-model price comparisons
All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the NVIDIA Nemotron 3.5 Lightning 30B A3B API cost per token?
From USD 0.05 per 1M input tokens (USD 0.00000005 per token) and USD 0.16 per 1M output tokens (USD 0.00000016 per token) at the lowest standard prices we found, which can come from different providers. The median of 5 standard prices is USD 0.06 input and USD 0.20 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for NVIDIA Nemotron 3.5 Lightning 30B A3B?
Among the 5 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is DeepInfra, ranked on a blend of 3 input tokens to 1 output token (USD 0.085 per 1M). For input alone the lowest price is USD 0.05 (Crusoe Cloud and 1 other, tied); for output alone, USD 0.16 (DeepInfra). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does NVIDIA sell NVIDIA Nemotron 3.5 Lightning 30B A3B on its own API?
NVIDIA publishes no price for NVIDIA Nemotron 3.5 Lightning 30B A3B on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is DeepInfra at USD 0.06 / USD 0.16 per 1M tokens.
Does NVIDIA Nemotron 3.5 Lightning 30B A3B have cached input pricing?
All 5 standard prices include one. The lowest is USD 0.01 per 1M at Fireworks AI; the median is USD 0.03. Providers without one bill cached input at the input price. What cached input means.
What is the NVIDIA Nemotron 3.5 Lightning 30B A3B context window?
Up to 1,048,576 tokens. 3 standard prices come with less, down to 262,144 tokens (CoreWeave Forge, DeepInfra and Fireworks AI). Check the context column before you pick the cheapest row for long prompts. Context window calculator.
How much does a coding agent cost per month on NVIDIA Nemotron 3.5 Lightning 30B A3B?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 46.80 a month at Fireworks AI, USD 76.50 at the median price and USD 98.10 at CoreWeave Forge. Try your own numbers.
Is there a batch, flex or priority price for NVIDIA Nemotron 3.5 Lightning 30B A3B?
Yes: priority from Fireworks AI at USD 0.0625 / USD 0.25 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.
Is NVIDIA Nemotron 3.5 Lightning 30B A3B free to use through an API?
No provider in our data lists a free price for NVIDIA Nemotron 3.5 Lightning 30B A3B as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.