Skip to main content
Watch: Stop Building Apps. Build Tools for AI Agents

Open-weight API pricing - last verified

NVIDIA Nemotron 3.5 Super VL 120B-A12B: where to run it and what it costs

3 offers from 3 providers list NVIDIA Nemotron 3.5 Super VL 120B-A12B at a per-token price. The lowest listed input price is $0.10 per 1M input tokens at DeepInfra (NVIDIA-Nemotron-3.5-Super-VL), with output at $0.40. No first-party API row is listed for this model. Prices are as listed on October 18, 2026; they change often and are not a benchmark.

124.5B total, 12B active, mixture of experts. Native context 1,048,576 tokens, per our local-models record (from the HF API (params, license, createdAt)).

Every offerQuotesRun it yourselfAll open-weight models

Offers
3
Providers
3
Lowest listed input
$0.10
First-party input
None listed

Per-token prices

Every NVIDIA Nemotron 3.5 Super VL 120B-A12B offer, sorted by input price

Each row is one build as the provider lists it, with its own model ID: dated snapshots, Fast and turbo builds and regional rows are never merged. Sorted by listed input price in USD per 1M input tokens; every price is in that same unit. Not stated means the provider's page does not say.
3 hosted offers for NVIDIA Nemotron 3.5 Super VL 120B-A12B, sorted by listed input price in USD per 1M input tokens
Provider and model IDInputUSD per 1M tokensOutputUSD per 1M tokensCached inputUSD per 1M tokensContext servedas the provider lists itQuantizationStatusSource
DeepInfranvidia/NVIDIA-Nemotron-3.5-Super-VLQuotes for this row$0.10$0.40$0.08256kInferred from an unlabelled tagBelow native 1,048,576Not statedNot stateddeepinfra.com
Together AInvidia/NVIDIA-Nemotron-3.5-Super-VLListed as: NVIDIA Nemotron 3.5 Super VLQuotes for this row$0.15$0.50$0.02262,144Below native 1,048,576NVFP4Serverless Inferencetogether.ai
Basetennvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12BListed as: Nemotron 3.5 Super VLQuotes for this row$0.20$0.50$0.041048kNot statedModel APIsbaseten.co
First-party
The model's own developer selling its API.
Peak-hour price
DeepSeek's listed price during its peak hours; off-peak is half, per its page. Alibaba's busy-hour rows work the same way.
Card shows N% off
A discount tag sits beside the price on the provider's catalog card. The number is the discounted one and may be temporary.
Inferred
Our reading, not the page's words: a name-only model match, a region taken from table order, or a context figure from an unlabelled tag.
Below native
The provider serves a shorter context than the model's native window in our local-models data.
Preview
The provider lists the model as a preview, for evaluation rather than production.

Context

Served below the native context window

NVIDIA Nemotron 3.5 Super VL 120B-A12B's native context is 1,048,576 tokens. These offers list a shorter one.

Evidence

The quote behind every value

Each value is copied from the provider's own page; one quote that backs several values shows once.

DeepInfra

NVIDIA-Nemotron-3.5-Super-VL

Model ID

“$0.08 cached, $0.10 in, $0.40 out / 1M”
deepinfra.com

Variant, Input, Output, Cached input

“NVIDIA-Nemotron-3.5-Super-VL 256k $0.10 / $0.08 cached $0.40”
deepinfra.com

Context served

“NVIDIA-Nemotron-3.5-Super-VL 256k”
deepinfra.com
  • Inferred from an unlabelled tag. Context inferred from an unlabelled tag: the quoted pricing row carries "256k" with no Context label.
  • Below native context. Served 256k; the model's native context is 1,048,576 tokens per HF API (params, license, createdAt).

Not stated

  • Batch: No per-model batch price listed on the pricing page.
  • Quantization: Quantization not stated on the pages used.
  • Status: No availability tier or release-stage label stated for this offer on the pages used.

Together AI

NVIDIA Nemotron 3.5 Super VL

Model ID

“NVIDIA NVIDIA Nemotron 3.5 Super VL nvidia/NVIDIA-Nemotron-3.5-Super-VL 262144 $0.15 $0.02 $0.50 NVFP4”
docs.together.ai

Variant, Input, Output, Cached input

“NVIDIA Nemotron 3.5 Super VL $0.15 $0.02 (cached) $0.50”
together.ai

Context served

“nvidia/NVIDIA-Nemotron-3.5-Super-VL 262144”
docs.together.ai

Quantization

“nvidia/NVIDIA-Nemotron-3.5-Super-VL 262144 $0.15 $0.02 $0.50 NVFP4”
docs.together.ai

Status

“Serverless Inference Most teams start with serverless inference”
together.ai

Not stated

  • Batch: No per-model batch price listed on the pricing page.

Baseten

Nemotron 3.5 Super VL

Model ID, Context served

“Nemotron 3.5 Super VL nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B 1048k 1048k”
docs.baseten.co

Variant, Input, Output, Cached input

“Nemotron 3.5 Super VL Nemotron 3.5 Super VL $0.20 $0.20 $0.04 $0.04 $0.50”
baseten.co

Input column, Output column, Cached input column

“Price per 1M tokens Model Input Cache Input Output”
baseten.co

Status

“Model APIs Instant access to pre-optimized models running on the Baseten Inference Stack.”
baseten.co

Not stated

  • Batch: No per-model batch price listed on the pricing page.
  • Quantization: Quantization not stated on the pages used.

Coverage

Not listed on the pages read

  • Fireworks AI: only the headline-model price table is covered; models outside it fall under size-based pricing and are not listed on the pages read.
  • Cerebras: the pay-as-you-go Developer tier lists only GPT OSS 120B and Qwen 3.8 27B; other models are Dedicated Inference by quote.
  • Cloudflare Workers AI: no Kimi K3, DeepSeek V4.1 Flash, Gemma 4 31B, MiniMax-M3 or Nemotron 3.5 rows on the pages read.
  • Together AI shows a Batch API price toggle but lists no per-model batch figures.

Alternatives

Run NVIDIA Nemotron 3.5 Super VL 120B-A12B yourself, or compare its first-party API

FAQ

How much does the NVIDIA Nemotron 3.5 Super VL 120B-A12B API cost?

Listed input prices run from $0.10 to $0.20 per 1M input tokens across 3 offers on October 18, 2026, and output from $0.40 to $0.50 per 1M output tokens. The lowest listed input price is at DeepInfra (NVIDIA-Nemotron-3.5-Super-VL). No first-party API row is listed.

Which providers serve NVIDIA Nemotron 3.5 Super VL 120B-A12B?

Together AI, DeepInfra and Baseten. Each lists one build, shown under the provider's own model name.

Do all providers serve NVIDIA Nemotron 3.5 Super VL 120B-A12B's full context window?

NVIDIA Nemotron 3.5 Super VL 120B-A12B's native context is 1,048,576 tokens in our local-models data. Served below that: DeepInfra (NVIDIA-Nemotron-3.5-Super-VL) at 256k and Together AI (NVIDIA Nemotron 3.5 Super VL) at 262,144.

Is there a batch price for NVIDIA Nemotron 3.5 Super VL 120B-A12B?

No per-model batch price for NVIDIA Nemotron 3.5 Super VL 120B-A12B is listed on the pages read. Together AI shows a Batch API price toggle but lists no per-model batch figures.

Sources

Last verified from each provider's own pages (5 sites). This is a directory of listed prices and what each provider states about the model it serves, not a benchmark. Prices change often; check the provider's page before you commit. Speed figures appear only where a provider states them, labelled Vendor-stated.

Newsletter

Know when open-weight API prices move

One email per week. New model releases, price changes and where to run them, and what they mean for what you build.

Related

Run open-weight models locally

The self-host alternative: downloads, memory needs and commands for each model.

Open-weight model licenses

Which of these models you may use commercially, and on what terms.

LLM API cost levers

Prompt caching, batch discounts and service tiers by provider.

Free LLM API tiers

Which providers have a standing free tier or credits.

OpenAI-compatible endpoints

Base URLs and limits for switching providers without rewriting code.

LLM gateways and routers

Route one model across several of these providers with fallbacks.

Other open-weight models: DeepSeek V4 Pro, DeepSeek V4.1 Flash, Qwen3.8-27B, Kimi K3, GLM-5.3, MiniMax-M3, gpt-oss-120b, gpt-oss-20b, Llama 4 Maverick, Gemma 4 31B, Mistral Large 3.

Providers on this page: Together AI, DeepInfra, Baseten.