Sarvam 105B (high) is a text-based AI model by Sarvam. It features 96 tok/s output speed, free pricing. It scores 18.2 on the intelligence index.
Output Speed
96 tok/s
Latency (TTFT)
1.55s
Blended Price
$0.00/M
| Input (Prompt) | Free |
| Output (Completion) | Free |
| Cache Read | Free |
| Cache Write | Free |
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Sarvam 105B (high) is completely free to use.
Sarvam 105B (high) has a lower coding score of 9.8. For demanding coding tasks, consider a model with a higher coding benchmark.
Sarvam 105B (high) generates output at 96 tok/s. Time to first token is 1.55s.
Yes, Sarvam 105B (high) is available for free.
Last updated:
See the alternatives section above for models with similar capabilities. You can also compare Sarvam 105B (high) head-to-head with any model on our comparison page.