Nemotron 3 Omni 30B API.
Bring different inputs together.

Nemotron 3 Omni 30B is listed in Blade’s catalogue for vision and audio understanding. Evaluate it for workflows that need to interpret more than written prompts.

€5 in free credits for every new customer.

Try Nemotron 3 Omni 30B

From €0.06 per million input tokens. View the pricing details.

Vision & audio
with Nemotron 3 Omni 30B.

Practical starting points for Nemotron 3 Omni 30B. Choose one task, define the expected output and measure the result on your own examples.

Triage visual issues

Combine a screenshot with a support question to draft a description of what is visibly wrong, where the endpoint supports image input.

Explore audio understanding

Evaluate spoken-content analysis on representative clips after confirming the audio route and supported input format.

Build media review workflows

Keep the source media alongside the generated explanation. Let a reviewer compare the interpretation with the original evidence.

Explore the vision & audio workflow ↗

Nemotron 3 Omni 30B pricing

Nemotron 3 Omni 30B
API pricing.

These are catalogue “From” rates in EUR. Dynamic pricing can change the applicable price. Confirm your model, request route and active billing unit before estimating a workload.

See Nemotron 3 Omni 30B on the rate card ↗

Input / 1M tokens: From€0.06
Output / 1M tokens: From€0.18

A concrete example
10,000 input tokens + 2,000 output tokens = €0.000960 at the displayed starting rates.

Illustration only; excludes retries, other models and paid tools. Catalogue updated 2026-10-22.

Check current rates ↗

API integration

How to use
the Nemotron 3 Omni 30B API.

Use the Blade model ID nemotron3-omni-30b and keep your API key in your backend environment. Verify account access and supported parameters before connecting production traffic.

Create a Blade API key in the console.
Run pip install openai and set BLADE_API_KEY.
Check the model list below, then use the console’s confirmed inference example for this model.

Read the API reference ↗

python

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.models.blade.sh/v1",
    api_key=os.environ["BLADE_API_KEY"],
    timeout=120.0,
)

model_id = "nemotron3-omni-30b"
models = client.models.list()
match = next(
    (item for item in models.data
     if item.id == model_id),
    None,
)
if match is None:
    raise RuntimeError("Model not listed for this account")
print(match.model_dump_json(indent=2))

Install openai and set BLADE_API_KEY. This checks the account’s model list; it does not run inference. Copy the confirmed model-specific inference request from the console before integrating.

Nemotron 3 Omni 30B API FAQ.

What can I use Nemotron 3 Omni 30B for?

Nemotron 3 Omni 30B is listed in Blade’s catalogue for vision and audio understanding. Evaluate it for workflows that need to interpret more than written prompts. Its Blade model ID is nemotron3-omni-30b.

How much does Nemotron 3 Omni 30B cost on Blade?

Input / 1M tokens: from €0.06. Output / 1M tokens: from €0.18. These are dynamic catalogue starting rates as of 2026-10-22, not fixed prices for every request. Check the console for current rates.

What should I confirm before integrating?

The catalogue confirms vision and audio positioning, but does not map the alias to a precise upstream checkpoint or document every input route. Confirm those details before sending media.

Upstream Nemotron Omni family reference; Blade’s exact checkpoint mapping and supported media routes require confirmation.

Model reference: Publisher model reference ↗. Hosted configuration and pricing: Blade catalogue, 2026-10-22.

Choose by task, input type and billing unit. Browse all models ↗

Nemotron 3 Omni 30B API.Bring different inputs together.

Vision & audiowith Nemotron 3 Omni 30B.