Sarvam
Rendered from D1 model snapshot · D1 read 110msCache check: checkingsarvam/sarvam-105b
Sarvam 105B
Flagship Indian-language reasoning model for enterprise multilingual applications
This model's cache
This model page returns the exact headers below. The page and /api/models/sarvam--sarvam-105b share the model:sarvam--sarvam-105b tag, so invalidation stays scoped to this model.
Cache key
/models/sarvam--sarvam-105bCache-Control
public, max-age=300, stale-while-revalidate=3600Cache-Tag
catalogmodel:sarvam--sarvam-105bWorkers 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-105b',
}),
})Invalidate this cache tag
await ctx.cache.purge({ tags: ['model:sarvam--sarvam-105b'] })Use this when one model changes and you do not want to evict the whole catalog.
SarvamReasoningTool callingTemperature control
- Released
- Sep 1, 2025
- Last updated
- Sep 1, 2025
- Context window
- 131.1K tokens
- Max output
- 131.1K tokens
- Open weights
- Yes
- Family
- Sarvam
Starts at
$0.04
per 1M input tokens
Output
$0.16
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 105B
Sorted by lowest input price
More from Sarvam