Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Sarvam 30B (high) | Llama 3.1 Instruct 8B |
|---|---|---|
| Input ($/M tokens) | $0.026 | $0.075 |
| Output ($/M tokens) | $0.11 | $0.095 |
Data from Artificial Analysis API — 12 benchmarks
Sarvam 30B (high) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.05/M tokens vs $0.08/M for Llama 3.1 Instruct 8B.
Llama 3.1 Instruct 8B wins 8 out of 12 benchmarks compared to 4 for Sarvam 30B (high). See the detailed benchmark chart above for per-category results.
Sarvam 30B (high) generates tokens faster at 232 tok/s vs 154 tok/s. However, Llama 3.1 Instruct 8B has lower time-to-first-token (0.55s vs 1.16s).
Choose based on your priorities: Sarvam 30B (high) for lower cost, Llama 3.1 Instruct 8B for stronger benchmark performance, and Sarvam 30B (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.