Nemotron-Nano-9B-v2
Released
2025-08-18
Last refreshed
2026-10-26
Status
Researched 19d ago
Open weightsCommercial use: permittedCodingRAGAgentsLong contextClassificationJSON / Tool use
NVIDIA AI releases · 27 in the last 12 monthsChangelog →
Specifications
- Family
- Nemotron Nano 2
- Released
- 2025-08-18
- Context
- 128K
- Parameters
- 9B
- Architecture
- Decoder Only
- Knowledge cutoff
- 2024-09
- Specialization
- general
- Openness
- Open weights
- License
- NVIDIA Open ModelPermitted
- Weights
- Available
- Code
- Unknown
Created by
Pricing
Output / 1M
$0.230
Input / 1M
$0.060
Cheapest of 3 routes · AWS Bedrock
Created by
Pricing
Output / 1M
$0.230
Input / 1M
$0.060
Cheapest of 3 routes · AWS Bedrock
About
Nemotron-Nano-9B-v2 is NVIDIA AI's Nemotron Nano 2 model. Its knowledge cutoff is 2025-03.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ ARAG
Q/$ BAgents
Q/$ AProviders(3)
Compare all 3Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| AWS Bedrock | $0.060 | $0.230 | Serverless Scheduled retirement: March 30, 2027 |
| Vercel AI Gateway | $0.060 | $0.230 | Serverless |
| NVIDIA NIM | - | - | ServerlessPartial |
Deprecated provider routes(1)
| Provider | Status | Catalog ID |
|---|---|---|
| OpenRouter | Deprecated | nvidia/nemotron-nano-9b-v2 |
Available via routers & gateways(2)
Amazon Bedrock Intelligent Prompt Routing
RouterAWS Bedrock's native prompt router that predicts each model's performance per request and routes between two models of the same family (Anthropic Claude, Meta Llama or Amazon Nova).
Passthrough + feeAWS Bedrock
NVIDIA LLM Router Blueprint
RouterNVIDIA's open-source AI blueprint for LLM routing that selects the optimal model per prompt via intent classification or neural auto-routing; deprecated in favor of NVIDIA NeMo Switchyard.
Free OSSNVIDIA NIM
Capabilities
Structured Outputs
Benchmark peer barsfor Coding
LiveCodeBenchRank 55 of 79
Benchmark scores(7)
Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 72.1 | AIME25, reasoning on (accuracy)Observed 2026-10-08 | — | ||
| 97.8 | MATH500, reasoning on (accuracy)Observed 2026-10-08 | — | ||
| 64.0 | GPQA, reasoning on (accuracy)Observed 2026-10-08 | — | ||
| 71.1 | LCB, reasoning on (accuracy)Observed 2026-10-08 | — | ||
| 66.9 | BFCL v3, reasoning on (accuracy)Observed 2026-10-08 | — | ||
| 6.5 | HLE, reasoning on (accuracy)Observed 2026-10-08 | — | ||
| 78.9 | RULER (128K) (accuracy)Observed 2026-10-08 | — |
Migration checks
No linked migration route is available for this model yet.
API versions
NVIDIA Nemotron Nano 9B v2