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

Hy4 preview

tencent· 2026-08-28· 1.0M ctx
open weightstool callreasoningstructured quant: unknown

spread (output)

1.4×

$2.00 – $2.88 · 11 providers

11 providers priced
ProviderInputOutputCache rdBlended
Vancine
relay router
$0.670$2.00$0.034$0.386
Kilo Gateway
relay router
$0.834$2.50$0.042$0.482
DevPass (LLM Gateway)
relay router
$0.834$2.50$0.042$0.482
LLM Gateway
relay router
$0.834$2.50$0.042$0.482
NanoGPT
relay router
$0.834$2.50$0.042$0.482
OpenCode Go
relay router
$0.834$2.50$0.042$0.482
OpenRouter
unknown
$0.834$2.50$0.042$0.482
Tencent TokenHub
relay router
$0.834$2.50$0.042$0.482
Tencent Token Plan
relay router
$0.834$2.50$0.042$0.482
Vercel AI Gateway
unknown
$0.834$2.50$0.042$0.482
CrossModeloutlier
relay router
$0.960$2.88$0.048$0.633

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