Skip to content
CostPerPrompt

Nemotron 3 Nano 30B A3B API Pricing

NVIDIA · context window 262K · prices updated 2026-09-07

Input per 1M tokens
$0.05
Output per 1M tokens
$0.2
Cached input per 1M
$0.03
40% cheaper than fresh input

Where Nemotron 3 Nano 30B A3B sits on price

At $0.2 per million output tokens, Nemotron 3 Nano 30B A3B is a budget tier model — 11.0× cheaper than the median output price of $2.20, which puts it in the cheapest 10% of everything we track. It sits 3th cheapest of the 5 NVIDIA models we track. Output costs 4.0× input, the usual spread — trim both, starting with the answer length.

Output tokens per $1
5,000,000
One full context fill
$0.0131
Cheaper than
95% of tracked models

Cached input is 40% cheaper. On an input-heavy workload you need roughly a 63% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.

What real workloads cost on Nemotron 3 Nano 30B A3B

These three workloads are the ones teams actually run on a budget-priced model — a $0.2/1M model is not bought for the same job as one ten times the price.

Workload Per request Per month
High-volume classification — 200K requests/day (400 in / 20 out) Short output, huge volume: the input price dominates the bill. $0 $144
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0.0001 $1.65
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0003 $75.00

Model your exact traffic in the API cost calculator — it preloads Nemotron 3 Nano 30B A3B with caching and batch options.

Nemotron 3 Nano 30B A3B price history

Nemotron 3 Nano 30B A3B's price has not moved since we began tracking it on Aug 2, 2026 — 36 days of stability in a market where 64 of the 331 models we track have repriced over the same period, including 3 of NVIDIA's own 5 models.

Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).

Nemotron 3 Nano 30B A3B vs Qwen2.5 7B Instruct

The closest-priced alternative from another vendor is Qwen2.5 7B Instruct (Alibaba (Qwen)) — priced within a rounding error on output, with $0.05 more per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.

See Qwen2.5 7B Instruct pricing →

Cheaper alternatives

More NVIDIA models

Frequently asked questions

How much does the Nemotron 3 Nano 30B A3B API cost?

Nemotron 3 Nano 30B A3B costs $0.05 per million input tokens and $0.2 per million output tokens, with cached input at $0.03 per million (40% cheaper). That works out to roughly 5,000,000 output tokens per dollar.

What does the high-volume classification workload cost on Nemotron 3 Nano 30B A3B?

High-volume classification — 200K requests/day (400 in / 20 out) costs about $0 per request and $144 per month on Nemotron 3 Nano 30B A3B. Short output, huge volume: the input price dominates the bill.

What does it cost to fill Nemotron 3 Nano 30B A3B's 262K context window?

Sending 262K of input in a single request costs $0.0131 at $0.05 per million tokens — before any output. With prompt caching that same fill drops to about $0.0079 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.

Is Nemotron 3 Nano 30B A3B worth the price?

Nemotron 3 Nano 30B A3B is in the cheapest end of the market — cheaper than 95% of the models we track. At this price the question is not cost but capability: it is a good fit for classification, extraction, routing and bulk summarisation, and a poor fit for multi-step reasoning where a wrong answer costs more than the tokens saved.