Nvidia Nemotron 3 Nano Omni Text

Nvidia Nemotron 3 Nano Omni Text

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 Text is a lightweight text-generation model for prompt-based language understanding and response generation. Provide an English prompt, and the model can generate answers, summaries, structured outputs, explanations, and other text-based responses with controllable length and sampling behavior.

Why Choose This?

• Fast text generation Generate responses quickly for chat, automation, summarization, and general language tasks.

• 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 tone, structure, formatting, or task behavior for more controlled outputs.

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

• Production-ready API Suitable for assistants, content tools, automation pipelines, internal workflows, and structured text generation tasks.

Parameters

How to Use

1. Write your prompt — describe the task, question, or output you want the model to generate.
2. Add a system prompt (optional) — guide the model’s role, format, or tone.
3. Choose reasoning mode (optional) — use no_think or think depending on your workflow.
4. Set generation controls (optional) — adjust max_tokens, temperature, and top_p.
5. Submit — run the model and review the generated response.

Example Prompt

Summarize the following product requirements into a concise executive brief with key goals, risks, and next steps.

Pricing

Billed by configured max_tokens.

Billing Rules

• Pricing is based on the configured max_tokens value.
• Cost is $0.01 per 1,000 max tokens.
• Increasing max_tokens increases cost linearly.
• prompt, system_prompt, reasoning_mode, temperature, and top_p do not change pricing directly.

Best Use Cases

• Question answering — Generate direct answers to prompts and tasks.
• Summarization — Condense long text into concise takeaways or structured briefs.
• Content drafting — Produce outlines, rewrites, explanations, and short-form written content.
• Structured generation — Generate bullet points, labeled sections, or formatted outputs with system guidance.
• Internal automation — Support workflow tools, copilots, and prompt-driven backend tasks.
• General language tasks — Handle classification, transformation, extraction, and text reasoning workflows.

Pro Tips

• Write prompts in English for best compatibility.
• Be explicit about the desired output format, such as summary, bullets, JSON-style structure, or step-by-step explanation.
• Use system_prompt when you need consistent tone, role behavior, or formatting rules.
• Keep temperature lower when you want more stable and deterministic results.
• Increase max_tokens only when you need longer outputs, since pricing is tied to that value.
• Use top_p and temperature carefully together to balance creativity and control.

Notes

• prompt is the only required field.
• prompt must be written in English.
• 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 Vision — Analyze images with the same Omni model family.
• NVIDIA Nemotron-3 Nano Omni Video — Analyze video content with temporal understanding.
• NVIDIA Nemotron-3 Nano Omni Audio — Process and understand audio inputs for multimodal workflows.

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",
  "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/text" \
  -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