Sarvam-105B

Sarvam-105B is a flagship Indian-language reasoning model for enterprise multilingual applications. It is the first version of the sarvam line in the registry. It has a context window of 131072 tokens and a max output of 131072 tokens. It accepts and returns text. It supports reasoning mode and tool calling. Weights are open. Price starts at $0.04 per million input tokens and $0.16 per million output tokens. Cached input is $0.0336 per million tokens.

First version of its line in the registry.

Range across the hosts that serve it: up to $0.054 per 1M input tokens.

• ·131072 token context window
• ·131072 token max output
• ·Supports reasoning mode and tool calling
• ·Open weights
• ·Priced from $0.04 per million input tokens

• Reach for it for enterprise multilingual applications
• Reach for it for Indian-language reasoning tasks
• Reach for it for long-context text processing

3 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window?

The context window is 131072 tokens, and the max output is also 131072 tokens.

Are the weights open?

Yes, the weights are open.

What is the price?

Price starts at $0.04 per million input tokens and $0.16 per million output tokens. Cached input is $0.0336 per million tokens.