Nemotron 3 Nano 30B A3BChat
NVIDIA's efficient 3B-active hybrid MoE reasoning model on DeepInfra's five-cent input rail.
816msp50100%up1 rail262K ctx$0.001typical$0.20 → $0.35 /MTok
Models
Nemotron 3 Nano Omni
NVIDIA's compact Omni model for image-aware reasoning and function-driven agent workloads.
- Modalities
- textimagetext
- Price
- $0.65 / $1.08/M tok
- Context
- 66K
- Max output
- 66K
- Providers
- 1
Playground
Providers
| Provider | Context | Price · in / out | p50 | p95 | Uptime |
|---|---|---|---|---|---|
| ddigitaloceanNo trainingNo training on your data. Zero-retention available | 66K | $0.65 / $1.08/MTok | 1.2s | 1.4s | 100% |
Routing controls
routing.strategyproviders.onlyproviders.excludeproviders.ordermax_cost_usddata_policydocs →Performance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.004/req
- Input
- $0.65/M tok
- Cached input
- $0.20/M tok
- Output
- $1.08/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
nemotron-3-nano-omni
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-omni",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choice
FAQ
What is Nemotron 3 Nano Omni?
NVIDIA's compact Omni model for image-aware reasoning and function-driven agent workloads.
How much does Nemotron 3 Nano Omni cost?
Nemotron 3 Nano Omni costs $0.65/M input tokens and $1.08/M output tokens.
What inputs and outputs does Nemotron 3 Nano Omni support?
Nemotron 3 Nano Omni accepts text and image and returns text.
How do I call Nemotron 3 Nano Omni?
POST /api/v1/chat/completions with `"model": "nemotron-3-nano-omni"`.
What other NVIDIA models are on NinjaChat?
Nemotron 3 Nano 30B A3B, Nemotron 3 Super, Nemotron 3 Ultra, Nemotron 3.5 Lightning, Nemotron Nano 12B v2 VL.
