inferenstack — the market read on AI inference · last observation 2026-09-20. See the boards
Price spread

Sarvam 105B

sarvam· 2025-09-01· 131K ctx
open weightstool callreasoning quant: unknown

spread (output)

1.3×

$0.160 – $0.212 · 2 providers

2 providers priced
ProviderInputOutputCache rdBlended
FastRouter
relay router
$0.040$0.160—$0.051*
NanoGPT
relay router
$0.054$0.212$0.034$0.055

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.