Meta-Llama-3-8B-Instruct vs Sarvam 105B
Sarvam 105B is cheaper on output tokens, while Sarvam 105B offers a larger context window. Choose Meta-Llama-3-8B-Instruct or Sarvam 105B based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Meta-Llama-3-8B-Instruct | Sarvam 105B |
|---|---|---|
| Provider | Azure | NanoGPT |
| Input / 1M tokens | $0.30 | $0.05 |
| Output / 1M tokens | $0.61 | $0.21 |
| Context window | 8K | 131K |
| Parameters | — | — |
| Open weights | Yes | Yes |
| Released | Apr 2024 | Feb 2026 |
| GPQA Diamond score | 26.1 | — |
FAQ
Is Meta-Llama-3-8B-Instruct or Sarvam 105B cheaper?
Sarvam 105B is cheaper on output tokens ($0.21 vs $0.61 per 1M).
Which has the larger context window, Meta-Llama-3-8B-Instruct or Sarvam 105B?
Sarvam 105B has the larger context window (131K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.