Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Sarvam 105B (high) | NVIDIA Nemotron Nano 9B V2 (Reasoning) |
|---|---|---|
| Input ($/M tokens) | $0.042 | $0.04 |
| Output ($/M tokens) | $0.17 | $0.16 |
Data from Artificial Analysis API — 12 benchmarks
NVIDIA Nemotron Nano 9B V2 (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.07/M tokens vs $0.07/M for Sarvam 105B (high).
Sarvam 105B (high) wins 5 out of 12 benchmarks compared to 4 for NVIDIA Nemotron Nano 9B V2 (Reasoning). See the detailed benchmark chart above for per-category results.
Sarvam 105B (high) generates tokens faster at 155 tok/s vs 97 tok/s. Sarvam 105B (high) also has lower time-to-first-token (1.20s vs 5.11s).
Choose based on your priorities: NVIDIA Nemotron Nano 9B V2 (Reasoning) for lower cost, Sarvam 105B (high) for stronger benchmark performance, and Sarvam 105B (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.