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

o4-mini

openai· 2025-04-16· 200K ctx
API onlytool callreasoningstructured quant: unknown

spread (output)

2.0×

$4.00 – $8.00 · 21 providers

21 providers priced
ProviderInputOutputCache rdBlended
Poe
relay router
$0.990$4.00$0.250$0.793
Azure
hyperscaler
$1.10$4.40$0.275$0.875
Azure Cognitive Services
unknown
$1.10$4.40$0.275$0.875
Cloudflare AI Gateway
unknown
$1.10$4.40$0.275$0.875
Eden AI
relay router
$1.10$4.40$0.275$0.875
Helicone
relay router
$1.10$4.40$0.275$0.875
Impossibl
relay router
$1.10$4.40$0.275$0.875
Jiekou.AI
relay router
$1.10$4.40—$1.40*
Kilo Gateway
relay router
$1.10$4.40$0.275$0.875
DevPass (LLM Gateway)
relay router
$1.10$4.40$0.275$0.875
LLM Gateway
relay router
$1.10$4.40$0.275$0.875
LLM Gateway
relay router
$1.10$4.40$0.275$0.875
Merge Gateway
unknown
$1.10$4.40$0.275$0.875
NanoGPT
relay router
$1.10$4.40$0.550$1.05
NEAR AI Cloud
relay router
$1.10$4.40$0.275$0.875
OpenAI
first party lab
$1.10$4.40$0.275$0.875
OpenRouter
unknown
$1.10$4.40$0.275$0.875
Abacus
relay router
$1.10$4.40—$1.40*
Vercel AI Gatewayoutlier
unknown
$1.10$4.40$0.275$0.875
Requestyoutlier
relay router
$1.21$4.84$0.302$0.963
Vercel AI Gatewayoutlier
unknown
$2.00$8.00$0.500$1.59

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