Sarvam-30B

by Sarvam AIChat

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

Context
65.5K tokens
Max output
65,536 tokens
Released
2026-02-18
Weights
Open

sarvam/sarvam-30b

Specifications

Full facts as recorded, incl. what is unknown.

Released
2026-02-18
Weights
Open
Input
Text
Output
Text
Context window
65,536 max across endpoints
Max output
65,536
Providers
1 + 1 gateway, not counted as providers
Epoch Capabilities Index
not evaluated
Direct price range
$0.02 in at FastRouter, via gateway, fees not verified
More details
Last updated
2026-03-06
Knowledge cutoff

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel toolsunknown
  • Structured outputunknown
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt cachingunknown
  • Web searchunknown
  • Computer useunknown
  • System messagesunknown
  • Assistant prefillunknown
  • Temperature
  • Streamingunknown
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Cost calculator

Loading endpoints…

Similarly priced models

Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).

ModelBlended/1MIn/1MOut/1MContextvs Sarvam-30B
Llama 3.2 3B InstructMeta$0.0333$0.03$0.05131K+0%
Granite 4.0 H MicroIBM$0.0328$0.017$0.112131K−2% cheaper
GPT OSS 20BOpenAI$0.03$0.018$0.09131K−10% cheaper
Mistral NemoMistral AI$0.0292$0.029$0.03131K−12% cheaper
Nex-N2.5-MiniNex AGI$0.0375$0.025$0.10262K+13%
Ling 3.0 FlashinclusionAI$0.028$0.021$0.063262K−16% cheaper
Ministral 3BMistral AI$0.04$0.04$0.04131K+20%
Voxtral Mini 3B 2507Mistral AI$0.04$0.04$0.04—+20%

More from Sarvam AI

Newest Sarvam AI models in the catalogue. All Sarvam AI models

ModelReleasedContextListed price
Sarvam-105B2026-02-18131K$0.04 via FastRouter
sarvam-m2025-07-258.2Kunpriced
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model