Nemotron 3 UltraChat
NVIDIA's 550B/55B-active frontier reasoning model for demanding agent workloads.
15.4sp50100%up4 rails262K ctx$0.008typical$1.08 → $2.88 /MTok
Playground
Providers
| Provider | Role | Context | Price · in / out |
|---|---|---|---|
| ddeepinfraNo trainingNo training on your data | Primary | 262K | $0.45 / $0.80/MToksame price, any rail |
| ddigitaloceanNo trainingNo training on your data. Zero-retention available | Fallback | 262K |
Routing controls
routing.strategyproviders.onlyPerformance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.003/req
- Input
- $0.45/M tok
- Cached input
- $0.18/M tok
- Output
- $0.80/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
nemotron-3-super
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nemotron-3-super",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choice
FAQ
What is Nemotron 3 Super?
NVIDIA's 120B/12B-active hybrid MoE for compute-efficient multi-agent reasoning and tool workflows.
How much does Nemotron 3 Super cost?
Nemotron 3 Super costs $0.45/M input tokens and $0.80/M output tokens.
What inputs and outputs does Nemotron 3 Super support?
Nemotron 3 Super accepts text and returns text.
How do I call Nemotron 3 Super?
POST /api/v1/chat/completions with `"model": "nemotron-3-super"`.
What other NVIDIA models are on NinjaChat?
Nemotron 3 Ultra, Nemotron 3.5 Lightning.
