Sarvam 30B
Summary
Sarvam 30B is an open-weight language model from Sarvam, released on 18 Feb 2026. It accepts text and generates text, with a 128K-token context window and up to 128K output tokens per response.
Efficient Indian-language reasoning model for chat, coding, and multilingual work
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Sarvam |
|---|---|
| Release date | 18 Feb 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [models.dev] |
| Context window | 128K (128,000 tokens) [models.dev] |
| Max output | 128K tokens [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
Sarvam 30B API pricing by provider
USD per million tokens. Sorted by input price.
We do not currently track a paid API listing for this model.
Frequently asked questions
What is the context window of Sarvam 30B?
Sarvam 30B has a context window of 128,000 tokens (128K) and can generate up to 128,000 tokens in a single response, according to models.dev.
Is Sarvam 30B open source?
Sarvam 30B is an open-weight model. Check the license terms before commercial use.
When was Sarvam 30B released?
Sarvam released Sarvam 30B on 18 Feb 2026, according to models.dev.
Change history
No changes detected since we started tracking this model. We re-check every source daily.