NVIDIA

Nemotron 3 Nano Omni

NVIDIA Nemotron 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems.

Model ID

nvidia/nemotron-3-nano-omni
Context window
256K
tokens
Max output
66K
tokens
Input
$0.05
per 1M tokens
Output
$0.2
per 1M tokens

Cache read $0.03

Quickstart

Call Nemotron 3 Nano Omni in one request.

Point the SDK you already use at xKiro and pass the model ID. The same key works for every model in the catalog.

SDK guides
main.py
import osfrom openai import OpenAI client = OpenAI(    api_key=os.environ["XKIRO_API_KEY"],    base_url="https://api.xkiro.com/v1",) res = client.chat.completions.create(    model="",    messages=[        {"role": "user", "content": "Explain HTTP caching in two sentences."},    ],) print(res.choices[0].message.content)
Response · Example

✓ 200 OK

"model": "nvidia/nemotron-3-nano-omni"

HTTP caching stores copies of responses so later requests can be served without contacting the origin server. Headers such as Cache-Control and ETag decide how long a copy stays fresh and how it is revalidated.

14 input · 42 output tokens · $0.0000091 at this model’s rates

Create an API key in the dashboard and export it as XKIRO_API_KEY.

Pricing

What Nemotron 3 Nano Omni costs.

Billed per million tokens at these rates, from your plan’s budget or your wallet.

  • $0.05

    Input

    per 1M tokens

  • $0.2

    Output

    per 1M tokens

  • $0.03

    Cache read

    per 1M tokens

On a plan

From $0.0017 / $0.0067 on a plan

Plan: up to −96%

Usage on a plan comes out of your allowance, so Nemotron 3 Nano Omni costs from $0.0017 / $0.0067 per 1M tokens when you use the whole allowance — up to 96% less than pay-as-you-go.

Compare plans →

Billed fairly

  • A request that fails before any output is generated is never billed
  • An identical blocking request retried within two minutes replays the first result — no double charge
  • If a stream breaks off or you cancel it, you pay only up to that point

Specifications

Limits and capabilities.

Context window
256,000 tokens
Max output
65,536 tokens
Input
Text · Image · Video
Output
Text
Provider
NVIDIA
Model ID
nvidia/nemotron-3-nano-omni
Good for
Coding · Long context

Capabilities

  • Tool useSupported
  • VisionSupported
  • Video inputSupported
  • ReasoningSupported

Reasoning effort

  1. off
  2. on

Set it with reasoning_effort in the OpenAI format, or thinking in the Anthropic format.

Reasoning guide

Supported parameters

  • max_tokens
  • temperature
  • top_p
  • stop
  • frequency_penalty
  • presence_penalty
  • seed
  • stream
  • tools
  • tool_choice
  • response_format
  • structured_outputs
  • reasoning
  • include_reasoning

Compare

Similar models.

Closest in price and context window — same provider first, then alternatives from other providers.

Browse all 69 models
Nemotron 3 Nano Omni compared with similar models, prices per 1M tokens
ModelInput / 1MOutput / 1M
Nemotron 3 Nano OmniThis modelVision · Video input · Reasoning · Tool use256K$0.05$0.2$0.03
Nemotron 3.5 Super VLVision · Reasoning · Tool use1M$0.15$0.5$0.02
Nemotron 3 UltraReasoning · Tool use1M$0.6$2.40$0.12
DeepSeek V4.1 Flash−50%Pay as you goVision · Reasoning · Tool use1.05M$0.075$0.15$0.3$0.6$0.0015
North Mini CodeReasoning · Tool use256KFree—
CodestralTool use256KFree—
Devstral 2Tool use256KFree—
modelnvidia/nemotron-3-nano-omni

Start building with Nemotron 3 Nano Omni.

Create a key, point your SDK at xKiro and call nvidia/nemotron-3-nano-omni.

No credit card · No auto-renewal · 26 free models, free forever