modelbenchmark.io

sarvam-m

sarvam-m

Compare

Efficient Indian-language reasoning model for chat, coding, and multilingual work

Specification

most-agreed values

Context
128K
Max output
8K
Released
2025-07-25
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
free
Output
free
Cache read
free
Cache write
free

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Cache write, 1 hoursarvam · sarvamfree

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nvidia · sarvamaifreefree128K8K
sarvam · sarvamfreefreefreefree8K32K