Model creator
Sarvam
Every Sarvam model in the BenchSift catalogue, with its scores, ranks, prices and capabilities as the sources publish them.
- Models
- 4
- Open weights
- 4
- 4 of 4 models
- Latest release
- Mar 6, 2026
- Sarvam 105B (High) · First dated model: May 20, 2025
- Median price
- $0.0605
- $0.047 to $0.074 per million tokens, across 2 priced models
Models
4Reasoning levels are folded into one entry. The rank is the whole catalogue's: sorting does not change it.
- Sarvam 105B (High)8.8#496 of 782$0.074110 t/s
Text · Reasoning · Open weights · Mar 6, 2026 · $0.074 · 110 t/s
- Sarvam 30B (High)6.6#622 of 782$0.047—
Text · Reasoning · Open weights · Mar 6, 2026 · $0.047
- Sarvam M (Reasoning, Based on Mistral Small 3.1)5.3#718 of 782——
Text · Reasoning · Open weights · May 23, 2025
- Sarvam-M———
Text · Reasoning · Open weights · May 20, 2025
Where these figures come from
Each catalogue model is tied to its creator by the identity Artificial Analysis publishes, or OpenRouter's and Models.dev's for models it does not track. Counts fold the reasoning levels of one model together. Ranks compare each measure with every measured model in the catalogue, configurations included, as model pages do. The price is the published blended price (3 input tokens to 1 output token).
Figures computed by BenchSift from the catalogue: Artificial Analysis, OpenRouter, Models.dev and Hugging Face. A value no model carries is not shown.
Data retrieved on Nov 12, 2026.