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

Claude Opus 4.1 (latest)

anthropic· 2025-08-05· 200K ctx
API onlytool callreasoningstructured quant: unknown

spread (output)

1.2×

$64.00 – $75.00 · 13 providers

13 providers priced
ProviderInputOutputCache rdBlended
Poe
relay router
$13.00$64.00$1.30$11.51
Azure Cognitive Services
unknown
$15.00$75.00$1.50$13.40
FastRouter
relay router
$15.00$75.00$1.50$13.40
Helicone
relay router
$15.00$75.00$1.50$13.40
Kilo Gateway
relay router
$15.00$75.00$1.50$13.40
NanoGPT
relay router
$15.00$75.00$1.50$11.87
Neon
relay router
$15.00$75.00$1.50$13.40
OpenCode Zen
relay router
$15.00$75.00$1.50$13.40
OpenRouter
unknown
$15.00$75.00$1.50$13.40
Pioneer
relay router
$15.00$75.00$1.50$13.40
Requesty
relay router
$15.00$75.00$1.50$13.40
Azure
hyperscaler
$15.00$75.00$1.50$13.40
ZenMux
relay router
$15.00$75.00$1.50$13.40

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