Nemotron Nano 9B V2
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.
- Input / output price
- $0.06 / $0.23 per 1M
- Context
- 128K tokens
- Released
- Aug 18, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Bedrock bedrock/nemotron-nano-9b-v2 | $0.06/M | $0.23/M |
Is a provider down? AWS Bedrock status
Pricing
USD per 1M tokens on Bedrock, after gateway discounts.
- Input
- $0.06 per 1M
- Output
- $0.23 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better48tokens/sacross providers
Response latency
Lower is better0.3sacross providers
Benchmarks
6 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBenchhuggingface.co | 71.1% | huggingface.co | Aug 18, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| BFCL-v3huggingface.co | 66.9% | huggingface.co | Aug 18, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MATH-500huggingface.co | 97.8% | huggingface.co | Aug 18, 2025 |
| AIME 2025huggingface.co | 72.1% | huggingface.co | Aug 18, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| IFEvalhuggingface.co | 90.3% | huggingface.co | Aug 18, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| RULER 128Khuggingface.co | 78.9% | huggingface.co | Aug 18, 2025 |
Apps
Use Nemotron Nano 9B V2 in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Nemotron Nano 9B V2 FAQ
Short answers, built from the data on this page.
Nemotron Nano 9B V2 is a model from NVIDIA, released on Aug 18, 2025. 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.
On the Respan gateway, Nemotron Nano 9B V2 costs $0.06 per 1M input tokens and $0.23 per 1M output tokens on Bedrock, after gateway discounts.
Nemotron Nano 9B V2 is served by Bedrock.
Nemotron Nano 9B V2 accepts up to 128K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "nemotron-nano-9b-v2". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Nemotron Nano 9B V2 has 6 published benchmark scores, including LiveCodeBench 71.1%, BFCL-v3 66.9%, and MATH-500 97.8%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.