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

Claude Sonnet 4.5

anthropic· 2025-09-29· 200K ctx
API onlytool callreasoningstructured quant: unknown

spread (output)

7.0×

$2.14 – $15.00 · 10 providers

10 providers priced · 1 omitted (stale)
ProviderInputOutputCache rdBlended
QiHang
relay router
$0.430$2.14—$0.586*
Jiekou.AI
relay router
$2.70$13.50—$3.68*
Anthropic
first party lab
$3.00$15.00$0.300$2.68
Helicone
relay router
$3.00$15.00$0.300$2.68
302.AI
relay router
$3.00$15.00—$4.09*
LLM Gateway
relay router
$3.00$15.00$0.300$2.68
LLM Gateway
relay router
$3.00$15.00$0.300$2.68
Merge Gateway
unknown
$3.00$15.00$0.300$2.68
NanoGPTstale
relay router
$3.00$15.00$0.300$2.37
DevPass (LLM Gateway)
relay router
$3.00$15.00$0.300$2.68
Abacus
relay router
$3.00$15.00—$4.09*

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