ModelsNVIDIANVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
nvidia/nvidia-nemotron-3.5-super-vl-120b-a12b1M context Compare →- MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
- $0.388
- Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
- $0.50
- Offers
- 2
- Providers
- 2
Cheapest right now
BaseTen
via Hugging Face$0.275 blended / 1M tokens
No change7D- in
- $0.20
- out
- $0.50
- Cached input
- –
See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 costs from $0.275 per million tokens (at a 3:1 input:output mix): the cheapest of 2 comparable offers, at BaseTen, checked on ; 2 offers are listed.
Offers by price, one per provider
Offers at or below a priceThe chart shows comparable offers only: one per provider (its cheapest route), standard tier, current prices only. The table below also lists the offers the chart leaves out, such as stale ones, priority tiers and prices converted from points, each with its signals.Offers ↑
1
2
Cheapest $0.275
BaseTen
Median $0.388
Most expensive $0.50
Venice
$0
$0.10
$0.20
$0.30
$0.40
$0.50
Cheapest that confirms no training on your prompts. The provider's published policy: prompts are not used for training.
$0.50 blended / 1M tokens
- in
- $0.25
- out
- $1.25
- Cached input
- $0.13
Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.
| Day | Cheapest offer | Official list price |
|---|---|---|
| 2026-10-25 | $0.275, BaseTen | – |
| 2026-10-26 | $0.275, BaseTen | – |
| 2026-10-27 | $0.275, BaseTen | – |
| 2026-10-28 | $0.275, BaseTen | – |
| 2026-10-29 | $0.275, BaseTen | – |
| 2026-10-30 | $0.275, BaseTen | – |
| 2026-10-31 | $0.275, BaseTen | – |
| Day | Cheapest offer | Official list price |
|---|---|---|
| 2026-10-17 | $0.275, BaseTen | – |
| 2026-10-18 | $0.275, BaseTen | – |
| 2026-10-19 | $0.275, BaseTen | – |
| 2026-10-20 | $0.275, BaseTen | – |
| 2026-10-21 | $0.275, BaseTen | – |
| 2026-10-22 | $0.275, BaseTen | – |
| 2026-10-23 | $0.275, BaseTen | – |
| 2026-10-24 | $0.275, BaseTen | – |
| 2026-10-25 | $0.275, BaseTen | – |
| 2026-10-26 | $0.275, BaseTen | – |
| 2026-10-27 | $0.275, BaseTen | – |
| 2026-10-28 | $0.275, BaseTen | – |
| 2026-10-29 | $0.275, BaseTen | – |
| 2026-10-30 | $0.275, BaseTen | – |
| 2026-10-31 | $0.275, BaseTen | – |
Cheapest offer
| Rank | Provider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it. | Input $/1M | Output $/1M | Blended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix. | PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. | ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut. | ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown. | Signals | Offer |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 0.20 | 0.50 | 0.275 | fp4 | 1M | ||||
| 2 | 0.25 | 1.25 | 0.50 | – | 262k |
No training on promptsTraining terms not published
-
$0.275BaseTen
Hugging Face
- in
- $0.20
- out
- $0.50
- Precision
- fp4
- Context
- 1M
Training terms not published
See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face -
$0.50Venice
direct
- in
- $0.25
- out
- $1.25
- Precision
- –
- Context
- 262k
No training on prompts
No offer matches these filters.
Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.
Monthly cost for your workload
Computed by the API for the three cheapest offers, per 30-day month.- BaseTen$19.50per month
- Venice$33.75per month+$14.25 vs the cheapest
The estimate could not be updated. Try again in a moment.
Compare NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 with
Related models
More from NVIDIA
- Nemotron 3.5 Super VL
- Nemotron 3 Nano 30B A3B
- Nemotron 3 Super
- Nemotron 3 Ultra
- Nemotron 3.5 Lightning
- Nemotron 3.5 Content Safety
Same index family
Use this data
The index is queryable. The API is free to use.Free API
curl https://api.inferindex.dev/cheapest?model=nvidia/nvidia-nemotron-3.5-super-vl-120b-a12bMCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp