How is this model different from Nemotron 3 Nano (30B/A3B)?

They use different architectures. Nvidia Nemotron Nano 9B V2 is a dense 9B model with a context window of 131.1K tokens. Nemotron 3 Nano is a sparse MoE (30B total, 3B active) with a 1M-token context for multi-agent throughput. Choose based on whether your constraint is footprint (9B v2) or context scale (Nemotron 3 Nano).

What does thinking budget control mean in practice?

You can instruct the model to reason briefly or in depth on a per-request basis. Brief reasoning produces faster, cheaper responses for straightforward tasks. Deep reasoning takes longer but improves accuracy on complex problems.

Where are input and output prices listed?

Pricing appears on this page and updates as providers adjust their rates. AI Gateway routes traffic through the configured provider.

NVIDIA

Nvidia Nemotron Nano 9B V2

Nvidia Nemotron Nano 9B V2 is a dense hybrid Mamba-Transformer reasoning model that matches or exceeds Qwen3-8B accuracy at up to 6x the throughput, with built-in thinking budget control.

View API reference

Input and output price: Prices from: Input $0.04, Output $0.16, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'nvidia/nemotron-nano-9b-v2',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out Nvidia Nemotron Nano 9B V2 by NVIDIA. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

Nvidia Nemotron Nano 9B V2

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Free Tier	Release Date

Bedrock

Legal:Terms•Privacy

131K

0.2 s

149 tps

$0.06/M

$0.23/M

—

08/18/2025

DeepInfra

Legal:Terms•Privacy

131K

0.2 s

118 tps

$0.04/M

$0.16/M

—

08/18/2025

Getting started

Call Nvidia Nemotron Nano 9B V2 through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'nvidia/nemotron-nano-9b-v2',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Nvidia Nemotron Nano 9B V2 request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'nvidia/nemotron-nano-9b-v2',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
  });

  console.log(result.text);
}

main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `nvidia/nemotron-nano-9b-v2`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Nvidia Nemotron Nano 9B V2 supports up to `131,072` output tokens. Reasoning tokens count toward this limit.
`reasoning`	`'provider-default' \| 'none' \| 'minimal' \| 'low' \| 'medium' \| 'high' \| 'xhigh'`	No	Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under `providerOptions` take precedence when both are set. See the Reasoning section below.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 131K-token context window

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK provider docs.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'nvidia/nemotron-nano-9b-v2',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['bedrock', 'deepinfra'],
      },
    },
  });

  console.log(result.text);
}

main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'nvidia/nemotron-nano-9b-v2',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  console.log(result.text);
}

main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'nvidia/nemotron-nano-9b-v2',
    prompt: 'What is the weather in San Francisco?',
    tools: {
      getWeather: tool({
        description: 'Get the current weather for a location',
        inputSchema: z.object({ location: z.string() }),
        execute: async ({ location }) => ({ location, temperatureC: 18 }),
      }),
    },
  });

  console.log(result.text);
}

main().catch(console.error);

Copy link to headingMore models by NVIDIA

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

nvidia/nemotron-3.5-lightning

262K

0.2 s

521 tps

$0.05/M

$0.15/M

Read$0.01/M

—

08/11/2026

nvidia/nemotron-3-ultra-550b-a55b

0.3 s

186 tps

$0.50/M

$2.40/M

Read$0.12/M

—

06/04/2026

nvidia/nemotron-3-super-120b-a12b

256K

0.2 s

130 tps

$0.15/M

$0.65/M

—

03/11/2026

nvidia/nemotron-3-nano-30b-a3b

262K

0.3 s

128 tps

$0.05/M

$0.24/M

—

12/15/2025

nvidia/nemotron-nano-12b-v2-vl

131K

0.1 s

45 tps

$0.20/M

$0.60/M

—

10/28/2025

Copy link to headingAbout Nvidia Nemotron Nano 9B V2

NVIDIA released Nvidia Nemotron Nano 9B V2 on August 18, 2025 as the compressed reasoning variant of the Nemotron Nano 2 family. It is a 9B-parameter model with a context window of 131.1K tokens.

Nvidia Nemotron Nano 9B V2 matches or exceeds Qwen3-8B on complex reasoning tasks at up to 6x the throughput. The hybrid Mamba-Transformer architecture contributes to this efficiency. Mamba layers handle sequence processing with sub-quadratic memory scaling, while Transformer attention layers maintain precision on retrieval-heavy tasks within the context window.

Nvidia Nemotron Nano 9B V2 also supports thinking budget control. You can prompt it to reason briefly for simple tasks (faster, cheaper) or thoroughly for hard problems (slower, more accurate). Adjust the latency-accuracy tradeoff at inference time without switching models. Technical report and assets: https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: Nvidia Nemotron Nano 9B V2 is a compact dense reasoning model. Evaluate whether its capability tier fits your workload before committing at production scale. Compare $0.06 and $0.23.
Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use Nvidia Nemotron Nano 9B V2

Best for

High-throughput reasoning: Workloads where 6x speed over comparable models matters
Thinking budget control: Applications that vary reasoning depth per request
Cost-sensitive production: Compact reasoning models that reduce infrastructure spend

Consider alternatives when

1M-token context: Nemotron 3 Nano (30B/3B active) supports that scale
Vision or multimodal: Nemotron Nano 12B v2 VL is the right choice
Multi-agent orchestration: The sparse MoE design of Nemotron 3 Nano is better suited to that pattern

Copy link to headingConclusion

Nvidia Nemotron Nano 9B V2 is a dense reasoning model. It delivers high throughput and accuracy with thinking budget control for tuning the speed-accuracy tradeoff per request. Route it through AI Gateway.

Copy link to headingFrequently Asked Questions

How is this model different from Nemotron 3 Nano (30B/A3B)?
They use different architectures. Nvidia Nemotron Nano 9B V2 is a dense 9B model with a context window of 131.1K tokens. Nemotron 3 Nano is a sparse MoE (30B total, 3B active) with a 1M-token context for multi-agent throughput. Choose based on whether your constraint is footprint (9B v2) or context scale (Nemotron 3 Nano).
What does thinking budget control mean in practice?
You can instruct the model to reason briefly or in depth on a per-request basis. Brief reasoning produces faster, cheaper responses for straightforward tasks. Deep reasoning takes longer but improves accuracy on complex problems.
Where are input and output prices listed?
Pricing appears on this page and updates as providers adjust their rates. AI Gateway routes traffic through the configured provider.

Your use is subject to NVIDIA's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Nvidia Nemotron Nano 9B V2

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Tool calling

Copy link to headingMore models by NVIDIA

Copy link to headingAbout Nvidia Nemotron Nano 9B V2

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Nvidia Nemotron Nano 9B V2

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions