Sarvam
Rendered from D1 model snapshot · D1 read 114msCache check: checkingsarvam/sarvam-30b
Sarvam 30B
Efficient Indian-language reasoning model for chat, coding, and multilingual work
This model's cache
This model page returns the exact headers below. The page and /api/models/sarvam--sarvam-30b share the model:sarvam--sarvam-30b tag, so invalidation stays scoped to this model.
Cache key
/models/sarvam--sarvam-30bCache-Control
public, max-age=300, stale-while-revalidate=3600Cache-Tag
catalogmodel:sarvam--sarvam-30bWorkers Cache derives the key from this path/query, plus the Worker entrypoint and current Worker version.
export const Route = createFileRoute('/models/$modelSlug')({
headers: () => ({
'Cache-Control': 'public, max-age=300, stale-while-revalidate=3600',
'Cache-Tag': 'catalog,model:sarvam--sarvam-30b',
}),
})Invalidate this cache tag
await ctx.cache.purge({ tags: ['model:sarvam--sarvam-30b'] })Use this when one model changes and you do not want to evict the whole catalog.
SarvamReasoningTool callingTemperature control
- Released
- Feb 18, 2026
- Last updated
- Feb 18, 2026
- Context window
- 128K tokens
- Max output
- 128K tokens
- Open weights
- Yes
- Family
- Sarvam
Starts at
$0.02
per 1M input tokens
Output
$0.1
Sellers
2
No cart or checkout in this MVP — pick a provider below and open their docs when you're ready to use it.
Capabilities & modalities
Reasoning
Tool calling
Structured output
Attachments
InputText
OutputText
Provider shelf
Where to get Sarvam 30B
Sorted by lowest input price
More from Sarvam