Skip to content

NVIDIA · Chat

Nemotron Nano 9b V2

NVIDIA 🇺🇸ChatOpen weights. One of its sources says the weights are publicly available.The maker currently plans to deprecate it within the next 180 days (30 Mar 2027). Plans can change.

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so.\

llminfo IQ
110.6
Market median price
$0.1025 blended / 1M
Max context
131K
Listings
15

Evidence and sources

🤗 nvidia/NVIDIA-Nemotron-Nano-9B-v2llminfo IQ 110.6, ranked among chat models. From 19 benchmarks. Plenty of data behind it.How llminfo IQ is computedFair value (52.1). Costs per task about what its benchmark results predict. From 2 benchmarks with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 12 Aug 2025Maker HQ: US (source)
Sources: AWS Bedrock Runtime data, FlowDot data, LiteLLM data, Models.dev data, Kilo AI Gateway data, Hugging FacePrimary data from AWS Bedrock Runtime from FlowDot: name from LiteLLM: deprecation date from Models.dev: weights availability from Kilo AI Gateway: description from Hugging Face: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Trade-offs

Deprecation scheduled

The maker plans to deprecate it on 30 Mar 2027, within the next 180 days.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 7 maker's prices; 1 official partner's price; 2 market median prices.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured outputBatch API

Listings

 Flowdotnvidia/nemotron-nano-9b-v2:free · freeSource: FlowDot data128K$0.00$0.00—
 OpenRouternvidia/nemotron-nano-9b-v2:free · freeSource: Helicone Costs dataNot published by the provider$0.00$0.00—
 DeepInfradeepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2Source: LiteLLM data131K$0.04$0.16—
 Aihubmixnvidia-nemotron-nano-9b-v2Source: AIHubMix data docsNot published by the provider$0.044$0.176—
 Amazon Web Servicesnvidia.nemotron-nano-9b-v2Sources: AWS Bedrock Runtime data, LiteLLM data, Models.dev data128K$0.06batch $0.03$0.23batch $0.12—
 Kilonvidia/nemotron-nano-9b-v2Sources: Kilo AI Gateway data, Models.dev data131K$0.06$0.23$0.00
 Vercelnvidia/nemotron-nano-9b-v2Sources: Models.dev data, Vercel AI Gateway data131K$0.06$0.23—
 Merge Gatewaynvidia/nemotron-nano-9b-v2Source: Models.dev data128K$0.06$0.23—
 Together AInvidia/NVIDIA-Nemotron-Nano-9B-v2Sources: LiteLLM data, Together AI data131K$0.06$0.25—
 Fireworks AIfireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2Source: LiteLLM data128K$0.20$0.20—
Show all 13 listings

Showing 10 of 13: the cheapest per 1M input tokens from each provider.

2 listings without a price are hidden.

These providers advertise this model. Researchers have found some resellers serving a different, cheaper model, so see how to check whether a provider meets your needs.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Long context

Reasoning

Math

AIME 2025Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MATH-500Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Coding

Instruction following

IFEvalSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Other

Data credits: Data by LLM Stats · BullshitBench by Peter Gostev, MIT (licence) · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence)

Also known as: bedrock/ap-northeast-1/nvidia.nemotron-nano-9b-v2, bedrock/ap-south-1/nvidia.nemotron-nano-9b-v2, bedrock/eu-south-1/nvidia.nemotron-nano-9b-v2, bedrock/eu-west-1/nvidia.nemotron-nano-9b-v2, bedrock/eu-west-2/nvidia.nemotron-nano-9b-v2, bedrock/sa-east-1/nvidia.nemotron-nano-9b-v2, bedrock/us-gov-east-1/nvidia.nemotron-nano-9b-v2, bedrock/us-gov-west-1/nvidia.nemotron-nano-9b-v2, bedrock_mantle/ap-northeast-1/nvidia.nemotron-nano-9b-v2, bedrock_mantle/ap-south-1/nvidia.nemotron-nano-9b-v2, bedrock_mantle/ap-southeast-2/nvidia.nemotron-nano-9b-v2, bedrock_mantle/ap-southeast-3/nvidia.nemotron-nano-9b-v2, bedrock_mantle/eu-central-1/nvidia.nemotron-nano-9b-v2, bedrock_mantle/eu-north-1/nvidia.nemotron-nano-9b-v2, bedrock_mantle/eu-south-1/nvidia.nemotron-nano-9b-v2, bedrock_mantle/eu-west-1/nvidia.nemotron-nano-9b-v2, bedrock_mantle/eu-west-2/nvidia.nemotron-nano-9b-v2, bedrock_mantle/nvidia.nemotron-nano-9b-v2, bedrock_mantle/sa-east-1/nvidia.nemotron-nano-9b-v2, bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-9b-v2, bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-9b-v2, deepinfra/nvidia/nvidia-nemotron-nano-9b-v2, fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2, nvidia-nemotron-nano-9b-v2, nvidia.nemotron-nano-9b-v2, nvidia.nemotron-nano-9b-v2:0, nvidia/nemotron-nano-9b-v2, nvidia/nemotron-nano-9b-v2:free, nvidia/nvidia-nemotron-nano-9b-v2, together_ai/nvidia/nvidia-nemotron-nano-9b-v2, us-gov.nvidia.nemotron-nano-9b-v2

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works