01
Review lengthy specifications
Supply the relevant specification and ask for contradictions, missing requirements and references to the supporting passages.
Nemotron 3 Nano 30B API.
Keep the context together.
Nemotron 3 Nano 30B is a long-context reasoning option in Blade’s catalogue. Evaluate it for assistants that need to work across substantial technical material in one request.
€5 in free credits for every new customer.
Try Nemotron 3 Nano 30BFrom €0.034 per million input tokens. View the pricing details.
Long-context reasoning
with Nemotron 3 Nano 30B.
Practical starting points for Nemotron 3 Nano 30B. Choose one task, define the expected output and measure the result on your own examples.
02
Plan multi-step work
Break a complex request into reviewable steps. Have your application track completion instead of assuming the model has executed them.
03
Analyse connected changes
Provide related modules and a proposed change. Check whether the response preserves important interfaces and constraints.
Nemotron 3 Nano 30B pricing
Nemotron 3 Nano 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 Nano 30B on the rate card ↗- Input / 1M tokens
- From€0.034
- Output / 1M tokens
- From€0.136
A concrete example
10,000 input tokens + 2,000 output tokens = €0.000612 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 Nano 30B API.
Use the Blade model ID nemotron3-nano-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 openaiand setBLADE_API_KEY. - Run a small request and inspect the output before building the rest of your workflow.
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,
)
reply = client.chat.completions.create(
model="nemotron3-nano-30b",
messages=[{
"role": "user",
"content": "Plan a staged migration from one API version to another. Include compatibility checks and rollback criteria.",
}],
max_tokens=4096,
)
print(reply.choices[0].message.content)Install openai and set BLADE_API_KEY. This sends a billed request. Check supported parameters and handle timeouts, rate limits and incomplete responses.
Use Nemotron 3 Nano 30B
with Claude Code or Codex.
Connect a skill or API runner that sends a focused task to nemotron3-nano-30b. Your main assistant keeps the project context, reviews the proposal and runs the checks.
01 / BriefClaude Code or Codex
Define the task and select the files.
02 / GenerateNemotron 3 Nano 30B
Propose code through Blade’s API.
03 / CheckYour project
Review the diff. Run the tests.
A configured integration is required. Your assistant retains its main model; delegated Blade requests are billed separately. Evaluate the result on your task before expanding the workflow.
Set up coding delegation ↗Nemotron 3 Nano 30B API FAQ.
What can I use Nemotron 3 Nano 30B for?
Nemotron 3 Nano 30B is a long-context reasoning option in Blade’s catalogue. Evaluate it for assistants that need to work across substantial technical material in one request. Its Blade model ID is nemotron3-nano-30b.
How much does Nemotron 3 Nano 30B cost on Blade?
Input / 1M tokens: from €0.034. Output / 1M tokens: from €0.136. 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 upstream Nemotron Nano family supports reasoning workflows. Blade’s listed context, quantization and supported request parameters take precedence over upstream serving examples.
Nemotron Nano family reference; confirm the checkpoint behind the Blade alias when reproducing publisher evaluations.
Can I use Nemotron 3 Nano 30B with Claude Code or Codex?
Yes, through a configured delegation skill or API runner. Your primary assistant sends a task to Blade and reviews the result. It keeps its own model, and Blade requests are billed separately. Follow the delegation guide.
Model reference: Publisher model reference ↗. Hosted configuration and pricing: Blade catalogue, 2026-10-22.
Explore related models.
Choose by task, input type and billing unit. Browse all models ↗