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

Claude Haiku 4.5

anthropic· 2025-10-15· 200K ctx
API onlytool callreasoningstructured quant: unknown

spread (output)

8.5×

$0.710 – $6.00 · 13 providers

13 providers priced · 1 omitted (stale)
ProviderInputOutputCache rdBlended
QiHang
relay router
$0.140$0.710—$0.192*
Jiekou.AI
relay router
$0.900$4.50—$1.23*
Anthropic
first party lab
$1.00$5.00$0.100$0.894
DaoXE
relay router
$1.00$5.00$0.100$1.20
FreeModel
unknown
$1.00$5.00$0.100$0.894
Helicone
relay router
$1.00$5.00$0.100$0.894
DevPass (LLM Gateway)
relay router
$1.00$5.00$0.100$0.894
LLM Gateway
relay router
$1.00$5.00$0.100$0.894
LLM Gateway
relay router
$1.00$5.00$0.100$0.894
Merge Gateway
unknown
$1.00$5.00$0.100$0.894
NanoGPTstale
relay router
$1.00$5.00$0.100$0.791
302.AI
relay router
$1.00$5.00—$1.36*
Abacus
relay router
$1.00$5.00—$1.36*
UnoRouteroutlier
relay router
$1.20$6.00—$1.64*

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