Nvidia Nemotron 3 Nano Omni Vision

Nvidia Nemotron 3 Nano Omni Vision

Playground

NVIDIA Nemotron 3 Nano Omni is an open, efficient reasoning model for enterprise agentic workflows, built on a 30B A3B hybrid Transformer-Mamba MoE architecture. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

NVIDIA Nemotron-3 Nano Omni Vision is a multimodal vision-language model for image understanding and analysis. Upload an image, provide an English prompt, and the model generates a text response for tasks such as image description, visual question answering, scene understanding, and structured visual analysis.

Why Choose This?

• Image understanding with natural-language prompts Ask questions about an image or request a description in plain English.

• Flexible response control Adjust max_tokens, temperature, and top_p to balance response length, determinism, and creativity.

• Optional system steering Use system_prompt to guide output style, role, or response constraints for more controlled behavior.

• Reasoning mode options Choose between no_think and think depending on your preferred response mode.

• Production-ready API Suitable for image analysis workflows, multimodal assistants, automated review pipelines, and visual understanding tools.

Parameters

How to Use

1. Upload or link your image — provide the image you want the model to analyze.
2. Write your prompt — ask the model to describe, explain, compare, classify, or answer questions about the image.
3. Add a system prompt (optional) — guide the response style, output format, or task framing.
4. Choose reasoning mode (optional) — use no_think or think depending on your workflow.
5. Set generation controls (optional) — adjust max_tokens, temperature, and top_p.
6. Submit — run the model and review the generated response.

Example Prompt

Describe this image in detail, including the setting, visible objects, mood, and any notable historical or architectural details.

Pricing

Billed by configured max_tokens.

Billing Rules

• Pricing is based on the configured max_tokens value.
• Cost is $0.006 per 1,000 max tokens.
• Increasing max_tokens increases cost linearly.
• prompt, image, system_prompt, reasoning_mode, temperature, and top_p do not change pricing directly.

Best Use Cases

• Image description — Generate clear descriptions of scenes, objects, and visual content.
• Visual question answering — Ask targeted questions about what appears in an image.
• Document and screenshot analysis — Extract meaning from UI screenshots, charts, diagrams, or other visual references.
• Content moderation and review workflows — Use text prompts to guide structured inspection of uploaded images.
• Multimodal assistants — Add image-aware understanding to support bots, tools, and internal workflows.
• Research and annotation tasks — Use guided prompts to summarize or analyze visual inputs consistently.

Pro Tips

• Write prompts in English for best compatibility.
• Be specific about what you want, such as description, object listing, comparison, or focused analysis.
• Use system_prompt when you need a consistent format, such as bullet summaries, JSON-style output, or domain-specific tone.
• Keep temperature lower when you want more stable and deterministic responses.
• Increase max_tokens only when you need longer outputs, since pricing is tied to that value.
• Use top_p and temperature together carefully to balance diversity and control.

Notes

• Both prompt and image are required.
• prompt is English only.
• Default settings include reasoning_mode = no_think, max_tokens = 1024, temperature = 0.7, and top_p = 0.95.
• Pricing depends on configured max_tokens, not on other generation settings.

Related Models

• NVIDIA Nemotron-3 Nano Omni Video — Analyze and understand video content with the same Omni model family.
• NVIDIA Nemotron-3 Nano Omni Audio — Process and understand audio inputs for multimodal workflows.
• NVIDIA Nemotron-3 Nano Omni Text — Use the text-only variant for language generation and text-based tasks.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "reasoning_mode": "no_think",
  "max_tokens": 1024,
  "temperature": 0.7,
  "top_p": 0.95
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/nvidia/nemotron-3-nano-omni/vision" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters