impulse

Nvidia Nemotron 3.5 Super VL 120B A12B

Open weights
API id NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
Input / 1M
$0.10
at GMI Cloud
Output / 1M
$0.50
at GMI Cloud
Context window
33K
tokens
Max output
1M
tokens per reply
Hosts
3
3 listings
Released
-
date not published

Pricing

List prices at GMI Cloud, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.10$0.50
Cached input
50% off input
$0.05

What it costs a month

At GMI Cloud list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$63.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$54.00
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$108
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$360
Use your own numbers

Where to run it

3 hosts serve Nvidia Nemotron 3.5 Super VL 120B A12B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
GMI CloudInference
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
$0.10 / $0.50
W&B InferenceInference
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B
$0.15 / $0.50
+19% vs headline
BasetenInference
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B
$0.20 / $0.50
+38% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: NVIDIA Open Model License
Runtimes: TGI, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than GMI Cloud.

Smaller NVIDIA models

No cheaper NVIDIA model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Qwen3.8 Flash
    Alibaba Qwen · on AIHubMix
    $0.113 / $0.38
    Has every key capability
    10% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    11% less
  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    20% less
  • Ministral 8B 2512
    Mistral AI · on Mistral AI
    $0.15 / $0.15
    Has every key capability
    25% less

Call it

Using GMI Cloud's API.

Python
from litellm import completion

response = completion(
    model="gmi/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Nvidia Nemotron 3.5 Super VL 120B A12B cost?

On GMI Cloud, Nvidia Nemotron 3.5 Super VL 120B A12B costs $0.10 per million input tokens and $0.50 per million output tokens. Cached input costs $0.05 per million tokens.

Which APIs offer Nvidia Nemotron 3.5 Super VL 120B A12B?

Nvidia Nemotron 3.5 Super VL 120B A12B runs on 3 APIs: GMI Cloud, W&B Inference and Baseten.

What is Nvidia Nemotron 3.5 Super VL 120B A12B's context window?

33K tokens, with up to 1M tokens in one reply.

Is Nvidia Nemotron 3.5 Super VL 120B A12B being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Nvidia Nemotron 3.5 Super VL 120B A12B?

Models that cost less and keep most of what it can do: Qwen3.8 Flash on AIHubMix (10% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Nvidia Nemotron 3.5 Super VL 120B A12B's API model id?

Use NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 with GMI Cloud. Other hosts use their own ids: NVIDIA-Nemotron-3.5-Super-VL-120B-A12B on W&B Inference, NVIDIA-Nemotron-3.5-Super-VL-120B-A12B on Baseten.

Sources

Raw catalog entry for NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 on GMI Cloud
{
  "cache_read_input_token_cost": 5e-8,
  "input_cost_per_token": 1e-7,
  "litellm_provider": "gmi",
  "max_input_tokens": 32768,
  "mode": "chat",
  "output_cost_per_token": 5e-7,
  "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts"
}