tokenstat
homepricingstatshelpsign in
tokenstat
Nano Gpt

Sarvam 105B

nano-gpt/sarvam-105b · rates as of · Benchmarks · Plans · Calculator

Compact GPT model for low-latency assistance and high-volume workloads

Cheapest input
$0.04
$/MTok · models.dev
Cheapest output
$0.16
$/MTok
Context
131K
tokens
Offers
2
1 source

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestsarvam/sarvam-105bFastRouter$0.04$0.16$0131K
models.devsarvam-105bNanoGPT$0.045$0.177$0.028131K

Capabilities

  • Reasoning
  • Tool calling
  • Open weights
  • In: text
  • Out: text
Released: 2026-05-12Family: sarvam

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash