What is the cheapest NVIDIA model?

Nemotron 3.5 Lightning is the lowest blended-price option among tracked active non-embedding models, or among all models if only embeddings are listed: $0.05 input and $0.14 output per million tokens ($0.07 blended). Blended pricing uses 75% input and 25% output for generation models; your cheapest option may differ with your workload.

Which NVIDIA model has the highest AA Intelligence score?

Nemotron 3.5 Lightning has the highest listed Artificial Analysis Intelligence Index score among tracked active NVIDIA models: 12.9. This is one evaluation, not a guarantee of the best result for every task. Models without measured results are not ranked as zero.

How do I calculate monthly NVIDIA API costs?

Multiply input tokens in millions by the input rate and add output tokens in millions multiplied by the output rate. For example, 20 million input and 5 million output tokens on Nemotron 3.5 Lightning cost an estimated $1.68 at the listed rates. This excludes tool charges, cache-specific charges, taxes and any endpoint-specific adjustments.

Which NVIDIA model has the largest context window?

Nemotron 3.5 Lightning has a listed context window of 262K tokens, the largest among tracked active NVIDIA models. Context capacity and maximum response length are separate limits; verify both on the model page and in the endpoint documentation.

What is the latest NVIDIA model in the catalog?

Nemotron 3.5 Lightning has the most recent listed release date among tracked active NVIDIA models: 2026-08-11. Models without a usable release date are excluded from this comparison. Catalog release dates do not guarantee immediate API availability.

Do NVIDIA models support image inputs?

1 tracked active models list image inputs, including Nemotron 3.5 Content Safety. Accepting images does not mean a model generates images; check each model's separate input and output formats and endpoint limits.

Can prompt caching lower NVIDIA API costs?

3 tracked active models have a listed cached-input rate, including Nemotron 3.5 Lightning, Nemotron 3 Nano 30B A3B, Nemotron 3 Ultra. Savings depend on eligible repeated input and the endpoint's cache rules, duration and any write charges.

Do NVIDIA models support tool calling?

4 tracked active models list tool-calling capabilities, including Nemotron 3.5 Lightning, Nemotron 3 Nano 30B A3B, Nemotron 3 Super. Verify the exact tool schema and availability with your API endpoint before integrating.

How should I compare NVIDIA benchmark scores and prices?

Compare scores within the same evaluation: Artificial Analysis Intelligence Index, DesignArena Elo, general Arena Elo and MMLU-Pro use different tasks and scales. Missing results are not zeroes. Pair a relevant measured benchmark with input/output pricing and tests of your own workload; the cheapest or highest-scoring model is not automatically the best fit.

Are retired NVIDIA models included in the price list?

The price list shows active models by default. Turn on Show retired models to include retired catalog entries, where available. A retained model page preserves reference information, not a promise that its API is still available.

Is NVIDIA an AI lab or an inference host?

NVIDIA is categorized as an AI lab in this catalog. Individual model pages list available API hosts separately; model creator and API host are different roles.

AI lab

NVIDIA API pricing & models

We track 5 NVIDIA models, priced from $0.05 per 1M input tokens with context windows up to 262K tokens.

Models tracked

Text & Reasoning · Vision

$0.07

Cheapest model

Nemotron 3.5 Lightning

12.9

Top quality score

Nemotron 3.5 Lightning

262K

Largest context

6-mo price trend 89%

Price list

All NVIDIA models and prices

Current NVIDIA API prices per 1M tokens, context windows and benchmark scores. Click a column to sort, or a model for full pricing details.

Show retired models


Nemotron 3.5 Lightning NVIDIA	$0.049	$0.14	262K	12.9	—	—	—	36%
Nemotron 3 Nano 30B A3B NVIDIA	$0.06	$0.24	262K	—	—	—	—	176%
Nemotron 3 Super NVIDIA	$0.085	$0.4	262K	—	—	—	—	173%
Nemotron 3 Ultra NVIDIA	$0.5	$2.2	262K	—	1148	—	—	106%
Nemotron 3.5 Content Safety NVIDIA	$0.2	$0.2	131K	—	—	—	—	0%

Nemotron 3.5 Lightning NVIDIA

Input /1M: $0.049
Output /1M: $0.14
Context: 262K
AA Intelligence: 12.9
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 36%

Nemotron 3 Nano 30B A3B NVIDIA

Input /1M: $0.06
Output /1M: $0.24
Context: 262K
AA Intelligence: —
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 176%

Nemotron 3 Super NVIDIA

Input /1M: $0.085
Output /1M: $0.4
Context: 262K
AA Intelligence: —
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 173%

Nemotron 3 Ultra NVIDIA

Input /1M: $0.5
Output /1M: $2.2
Context: 262K
AA Intelligence: —
DesignArena Elo: 1148
Arena Elo: —
MMLU-Pro: —
30d trend: 106%

Nemotron 3.5 Content Safety NVIDIA

Input /1M: $0.2
Output /1M: $0.2
Context: 131K
AA Intelligence: —
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

NVIDIA input vs output prices

USD per 1M tokens for each model.

NVIDIA price history

Blended price per 1M tokens over the last 6 months.

By use case

NVIDIA models by category

Text & Reasoning

5 models · cheapest

Nemotron 3.5 Lightning

$0.07 blended / 1M

Vision

1 model · cheapest

Nemotron 3.5 Content Safety

$0.20 blended / 1M

Comparisons

NVIDIA vs other AI providers

Compare Nemotron 3.5 Lightning with models from other AI providers, including pricing and benchmark results.

NVIDIA vs Google

Nemotron 3.5 Lightning vs Nano Banana Pro (Gemini 3 Pro Image)

$0.07 vs $4.50 · Arena Elo — vs 1211

NVIDIA vs Anthropic

Nemotron 3.5 Lightning vs Claude Opus 5.5

$0.07 vs $8.00 · Arena Elo — vs —

NVIDIA vs OpenAI

Nemotron 3.5 Lightning vs GPT-5.2 Pro

$0.07 vs $58 · Arena Elo — vs 1255

NVIDIA vs xAI

Nemotron 3.5 Lightning vs Grok 4.7

$0.07 vs $3.00 · Arena Elo — vs —

NVIDIA vs Meta

Nemotron 3.5 Lightning vs Muse Spark 1.3

$0.07 vs $2.00 · Arena Elo — vs —

NVIDIA vs DeepSeek

Nemotron 3.5 Lightning vs DeepSeek V4.1 Flash

$0.07 vs $0.34 · Arena Elo — vs —

FAQ

NVIDIA pricing FAQ

Tracked active NVIDIA models range from $0.05 to $0.50 per million input tokens. Output rates are listed separately for each model. Prices vary by model and API endpoint; these are token rates, not a subscription quote.