Nemotron 3 Nano OmniChat
NVIDIA's compact Omni model for image-aware reasoning and function-driven agent workloads.
1.2sp50100%up1 rail66K ctx$0.004typical$0.65 → $1.08 /MTok
Playground
Providers
| Provider | Context | Price · in / out | p50 | p95 | Uptime |
|---|---|---|---|---|---|
| ddeepinfraNo trainingNo training on your data | 262K | $0.20 / $0.35/MTok | 816ms | 816ms | 100% |
Routing controls
routing.strategyproviders.onlyproviders.excludeproviders.ordermax_cost_usddata_policydocs →Performance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.001/req
- Input
- $0.20/M tok
- Cached input
- $0.15/M tok
- Output
- $0.35/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
nemotron-3-nano
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nemotron-3-nano",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserrouting
FAQ
What is Nemotron 3 Nano 30B A3B?
NVIDIA's efficient 3B-active hybrid MoE reasoning model on DeepInfra's five-cent input rail.
How much does Nemotron 3 Nano 30B A3B cost?
Nemotron 3 Nano 30B A3B costs $0.20/M input tokens and $0.35/M output tokens.
What inputs and outputs does Nemotron 3 Nano 30B A3B support?
Nemotron 3 Nano 30B A3B accepts text and returns text.
How do I call Nemotron 3 Nano 30B A3B?
POST /api/v1/chat/completions with `"model": "nemotron-3-nano"`.
What other NVIDIA models are on NinjaChat?
Nemotron 3 Nano Omni, Nemotron 3 Super, Nemotron 3 Ultra, Nemotron 3.5 Lightning, Nemotron Nano 12B v2 VL.
