NVIDIA Nemotron Nano 9B V2 (Reasoning)
AI model by NVIDIA. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. NVIDIA Nemotron Nano 9B V2 (Reasoning) is a budget-tier option from NVIDIA at $0.16/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, NVIDIA Nemotron Nano 9B V2 (Reasoning) reports 95 tok/s output speed and 7880ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, NVIDIA Nemotron Nano 9B V2 (Reasoning) costs $0.06 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-10-08.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
NVIDIA Nemotron Nano 9B V2 (Reasoning)Current | $0.04 | $0.16 | 95 tok/s |
| Qwen3.5 4B (Non-reasoning) | $0.03 | $0.15 | 23 tok/s |
| Sarvam 105B (high) | $0.04 | $0.17 | — |
| Qwen3.5 4B (Reasoning) | $0.03 | $0.15 | 29 tok/s |
| Agnes 3.0 Flash | $0.05 | $0.15 | 237 tok/s |
| Ministral 3 8B | $0.15 | $0.15 | 89 tok/s |