Nemotron 3.5 Super 120B A12B
nemotron-3.5-super-120b-a12bPricing
List prices at Perplexity, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.20 | $0.50 | |
| Cached input 80% off input | $0.04 | 80% off input |
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
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.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
PerplexityGateway nemotron-3.5-super-120b-a12b | $0.20 / $0.50 | nemotron-3.5-super-120b-a12b |
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 LicenseRuntimes: 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
- 27% less
- 27% less
- 5% less
Open-weight picks
- 5% less
- 6% less
- 8% less
- 35% less
Model line
Newer and older versions, at each lab's own price.
- UndatedNemotron 3.5 Super 120B A12BLatest$0.20 / $0.50
- Mar 2026Nemotron 3 Super 120B A12BNot listed
Call it
Using Perplexity's API.
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"
}