Sarvam logo

Sarvam 30B

sarvam/sarvam-30b

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

Input modalitiesT
Output modalitiesT
Source-linkedsarvamOpen weightsReleased 2026-02-18
Report data
Context window128K
Maximum output128K
Provider offers1
Knowledge cutoffUndisclosed
Capabilities

What this model supports

ReasoningYes
Tool callingYes
Structured outputNo
AttachmentsNo
Temperature controlYes
Open weightsYes
Creator
Sarvam
Family
sarvam
Modalities
Text
License
Not documented
Release date
2026-02-18
Model ID
sarvam/sarvam-30b
Market availability

Provider pricing

Report price →
Providers offering Sarvam 30B
ProviderProvider model IDContextInput / 1MOutput / 1MCached / 1MFeaturesAll pricing
FastRouter logoFastRoutersarvam/sarvam-30b128K$0.02 if offer.cost.input is defined else '—'}}$0.1 if offer.cost.output is defined else '—'}}$0 if offer.cost.cache_read is defined else '—'}}R T ·
View
{
  "input": 0.02,
  "output": 0.1
}
Evidence

Published benchmark results

Insufficient benchmark coverage. ModelBench does not infer a score from price, context size, or model name.