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

DeepSeek-R1-Distill-Qwen-32B

deepseek· 2025-01-20· 131K ctx· mit
open weights quant: unknown

spread (output)

16×

$0.300 – $4.88 · 3 providers

3 providers priced
ProviderInputOutputCache rdBlended
NovitaAI
relay router
$0.300$0.300—$0.300*
Alibaba (China)
relay router
$0.287$0.861—$0.339*
Cloudflare Workers AI
relay router
$0.497$4.88—$0.896*

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