ModelPickr

Models / Sarvam AI / Sarvam 105B

Sarvam AI · sarvam

Sarvam 105B

Flagship Indian-language reasoning model for enterprise multilingual applications

$0.04 in · $0.16 out

per 1M tokens · provider rate closest to the median. No first-party Sarvam AI price was listed. The reference price is FastRouter's rate, the provider closest to the median.

Provider input prices run from $0.04 to $0.054 per 1M tokens. Output prices run from $0.16 to $0.21.

Context
131,072
Max output
131,072
Cache read
—
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
—
Released
Sep 1, 2025
Updated in source
Sep 1, 2025
Knowledge
—
Providers
3

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

Estimated monthly cost

Sarvam 105B

$0.48

Cache hit is ignored because this model has no cache-read price.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
FastRouterreference$0.04$0.16———
NanoGPT$0.054$0.21$0.034——
Sarvam AI—————