Compare pricing, benchmarks, and capabilities across 3 AI models
| Model | Provider | Input $/1M↕ | Output $/1M↕ | Context↕ | Intelligence↑ | Speed↕ | Latency | API |
|---|---|---|---|---|---|---|---|---|
Sarvam M (Reasoning) | Sarvam | — | — | — | 8.4 | — | — | |
Sarvam 30B (high) | Sarvam | — | — | — | 12.3 | 294 tok/s | 1.2s | |
Sarvam 105B (high) | Sarvam | — | — | — | 18.2 | 124 tok/s | 1.2s |
Enter your expected usage to compare costs across models
e.g. 1,000,000 = ~750,000 words
Usually 30–50% of input volume
3 models selected
Prices are approximate and may vary. Check provider documentation for current pricing.