# NVIDIA Nemotron 3.5 Super

By Steven Van · 2026-10-01

The Agent API adds a text-only reasoning model with a 1M-token context window, priced at $0.20 per million input tokens, replacing Nemotron 3 Ultra.

The [Perplexity](<https://creatorstoolbox.com/tools/perplexity>) Agent API now supports NVIDIA's Nemotron 3.5 Super, using the model ID perplexity/nemotron-3.5-super-120b-a12b, according to the [Agent API models page](<https://docs.perplexity.ai/docs/agent-api/models>).

## Pricing and limits

- **$0.20** per million input tokens

- **$0.04** per million cached input tokens

- **$0.50** per million output tokens

- 1,048,576-token context window

- Up to 131,072 output tokens per response

- Text input only

The models page lists Nemotron 3.5 Super as a reasoning model. It has no optional service tiers, so it uses default processing only.

## Replaces Nemotron 3 Ultra

The model replaces perplexity/nemotron-3-ultra-550b-a55b, which is no longer listed in the Agent API or Orchestrator API model docs.

![Perplexity](<https://www.google.com/s2/favicons?domain=perplexity.ai&sz=128>)

Perplexity

AI-powered answer engine — ask anything and get cited, real-time answers from across the web.

[View Perplexity →](<https://creatorstoolbox.com/tools/perplexity>)

Sources

[Original source](<https://docs.perplexity.ai/changelog#october-2026>)

[Read NVIDIA Nemotron 3.5 Super on Creators Toolbox](<https://creatorstoolbox.com/blog/perplexity-nvidia-nemotron-3-5-super>)

---
Canonical source: https://creatorstoolbox.com/blog/perplexity-nvidia-nemotron-3-5-super