Kyma APIKyma API
NVIDIA

NVIDIA

Nemotron 3.5 Super VL

NVIDIA's open vision-language model, a 120B hybrid Mamba-Transformer MoE with 12B active: reasoning, coding, tool use, and document, GUI and video understanding. 1M context, image input.

Modalities

Text+Image → Text

Below release

Not established

Weights

Published

nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

Where it sits in the catalogue Kyma measures

Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.

Price · input#18/84

$0.2025

output $0.675 · cached $0.027

median $1.013 · best $0.0494

Price · output#14/83

$0.675

per 1M tokens generated

median $3.645 · best $0.218

Availability · 30d#1/55

100%

30 observations since 2026-10-25

median 100.0% · best 100.0%

Throughput#4/23

123 tok/s

probe median, one fixed prompt

median 46.1 tok/s · best 160.1 tok/s

Response time#4/23

0.90 s

probe median, to a complete answer

median 1.33 s · best 0.46 s

Context

1.05M

max output 235,929

published by NVIDIA, not measured here

Tick above each rail is this model, below it the other 83. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.

Usage

How much this model is actually called here.

Rank

#91

of 112 active models

Tokens served

6.1K

all-time

Platform share

0.0%

of all tokens

Pricing

Pay per token. Cached input bills at this model’s own cached rate, listed below.

$0.2025 /1M input$0.675 /1M output
Hobby10 req/day · 2K in / 500 out
~$0.22/mo
Production1,000 req/day · 2K in / 500 out
~$22.28/mo
Scale20,000 req/day · 2K in / 500 out
~$446/mo
+ Estimate your workload
1,000
2,000
500
30%

Estimated monthly cost

$19.12

$0.6372 / day on Nemotron 3.5 Super VL

Same workload on:

Nemotron 3 Ultra 550B$91.13+377%
Qwen 3.8 27B$59.77+213%

Estimates use list pricing with cached input at this model's own cached rate. Actual bills depend on real token counts, and every response includes its exact cost.

How it compares

Against the peers people actually weigh it against.

SpecNemotron 3.5 Super VLNemotron 3 Ultra 550BQwen 3.8 27B
Input /1M$0.2025$0.675$0.3576
Output /1M$0.675$3.375$2.554
Context1M1M1M
ToolsYesYesYes
ReasoningYesYesYes
Throughput123 tok/s

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard — $0.50 free credit on the free tier, which covers Nemotron 3.5 Super VL. No card required.

    Get API key →
  2. 2

    Make your first request

    Drop in your key and send a chat completion — fully OpenAI-compatible.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron-3.5-super-vl",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'
  3. 3

    Stream responses

    Add "stream": true to receive tokens as they arrive.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron-3.5-super-vl",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of Nemotron 3.5 Super VL?

Nemotron 3.5 Super VL has a 1M-token context window — roughly 1542 pages of text in a single request.

How much does the Nemotron 3.5 Super VL API cost?

$0.2025 per 1M input tokens and $0.675 per 1M output tokens, with cached input at $0.027/1M — 87% off the input rate on repeated prompt prefixes. No subscription; you pay only for what you use.

Does Nemotron 3.5 Super VL support function calling?

Yes — Nemotron 3.5 Super VL supports tool/function calling and structured outputs (JSON mode), so it works with agent frameworks out of the box.

Are the weights for Nemotron 3.5 Super VL publicly available?

Yes. NVIDIA publishes Nemotron 3.5 Super VL's weights as nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16, so you can download and run the model yourself (https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16, read 2026-10-25). Kyma serves it because it is convenient and has failover behind it, not because it is the only way to reach it.

Is Nemotron 3.5 Super VL ever served below the precision its creator released it at?

Kyma cannot say. Answering it needs the precision NVIDIA released Nemotron 3.5 Super VL in, and we could not source that from NVIDIA's own material — so there is nothing to compare a route against. We publish "not established" rather than reading a low format as a downgrade: on several models in this catalogue a low format is exactly how the creator ships it.

How do I use Nemotron 3.5 Super VL?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to nemotron-3.5-super-vl. Signing up is free and includes $0.50 of credit on the free tier, which covers this model — no card required.

Start with $0.50 free credit on the free tier — no card required.Create account →

More models by NVIDIA

ModelContextInputOutput
NVIDIANemotron 3 Ultra 550B1M$0.675$3.375