impulse

Nemotron 3.5 Super 120B A12B

Open weights
API id nemotron-3.5-super-120b-a12b
Input / 1M
$0.20
at Perplexity
Output / 1M
$0.50
at Perplexity
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Perplexity, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.20$0.50
Cached input
80% off input
$0.04

What it costs a month

At Perplexity list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$83.10
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$75.60
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$136
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$600
Use your own numbers

Where to run it

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

HostIn / out per 1M
PerplexityGateway
nemotron-3.5-super-120b-a12b
$0.20 / $0.50

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 Perplexity.

Smaller NVIDIA models

No cheaper NVIDIA model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    27% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    27% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    5% less

Open-weight picks

  • Mistral Small 2603
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    5% less
  • Deepseekv4.1 Flash
    DeepSeek · on Sarvam
    $0.149 / $0.585
    Has every key capability
    6% less
  • Qwen3.8 27B
    Alibaba Qwen · on EmpirioLabs AI
    $0.17 / $0.50
    Has every key capability
    8% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    35% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedNemotron 3.5 Super 120B A12BLatest$0.20 / $0.50
  2. Mar 2026Nemotron 3 Super 120B A12BNot listed

Call it

Using Perplexity's API.

Python
from litellm import completion

response = completion(
    model="perplexity/nemotron-3.5-super-120b-a12b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Nemotron 3.5 Super 120B A12B cost?

On Perplexity, Nemotron 3.5 Super 120B A12B costs $0.20 per million input tokens and $0.50 per million output tokens. Cached input costs $0.04 per million tokens.

Which APIs offer Nemotron 3.5 Super 120B A12B?

Nemotron 3.5 Super 120B A12B runs on 1 API: Perplexity.

Is Nemotron 3.5 Super 120B A12B being retired?

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

Is there a newer version of Nemotron 3.5 Super 120B A12B?

No. Nemotron 3.5 Super 120B A12B is the newest model in its line.

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

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (27% less), GPT-6 Luna on OpenAI (27% less) and Mistral Small 2603 on Mistral AI (5% less). Savings are on a mix of 3 input tokens to 1 output token.

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

Use nemotron-3.5-super-120b-a12b with Perplexity.

Sources

Raw catalog entry for nemotron-3.5-super-120b-a12b on Perplexity
{
  "litellm_provider": "perplexity",
  "mode": "responses",
  "input_cost_per_token": 2e-7,
  "output_cost_per_token": 5e-7,
  "cache_read_input_token_cost": 4e-8,
  "source": "https://docs.perplexity.ai/docs/agent-api/models"
}