Nemotron 3.5 LightningChat
NVIDIA's 3B-active hybrid Mamba-Transformer reasoning model at five cents per input MTok.
2 rails262K ctx$0.001typical$0.20 → $0.35 /MTok
Playground
Providers
| Provider | Role | Context | Price · in / out |
|---|---|---|---|
 fireworksNo trainingNo training on your data. Zero-retention available | Primary | 262K | $0.75 / $2.88/MToksame price, any rail |
| ddeepinfraNo trainingNo training on your data | Fallback | 262K |
Routing controls
routing.strategyPerformance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.007/req
- Input
- $0.75/M tok
- Cached input
- $0.21/M tok
- Output
- $2.88/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
nemotron-3-ultra
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nemotron-3-ultra",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choice
FAQ
What is Nemotron 3 Ultra?
NVIDIA's 550B/55B-active frontier reasoning model for demanding agent workloads.
How much does Nemotron 3 Ultra cost?
Nemotron 3 Ultra costs $0.75/M input tokens and $2.88/M output tokens.
What inputs and outputs does Nemotron 3 Ultra support?
Nemotron 3 Ultra accepts text and returns text.
How do I call Nemotron 3 Ultra?
POST /api/v1/chat/completions with `"model": "nemotron-3-ultra"`.
What other NVIDIA models are on NinjaChat?
Nemotron 3.5 Lightning.
