PARROTSIGHT

Nemotron 3 Super

StableLarge Language ModelNVIDIA

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

P50 50msP95 158ms$0.19 / 1M tokens262K ctx

Overview

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer... Nemotron 3 Super is served through the PARROTSIGHT unified API at NVIDIA's list price, with the same authentication, metering and regional pinning (MY / SG / ID) as every native model. No separate provider account is required.

  • 262K token context
  • OpenAI-compatible endpoint — migrate with a two-line change
  • Streaming (SSE) supported for all text outputs
  • Billed at provider list price, metered per token

Capabilities

Response quality94
Reasoning95
Speed80
Value76

API

https://api.parrotsight.com/v1/chat/completions

bash
curl -X POST https://api.parrotsight.com/v1/chat/completions \
  -H "Authorization: Bearer $PS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nvidia/nemotron-3-super-120b-a12b","messages":[{"role":"system","content":"You are a concise bilingual assistant."},{"role":"user","content":"Summarise this quarter's platform metrics in Malay and English."}],"stream":true}'

Version history

  1. v2026.3Latest2026-03-11

    Added to the PARROTSIGHT catalogue at NVIDIA list pricing.

More models

View all models