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

Inkling

thinkingmachines· 2026-07-15· 1.0M ctx· apache-2.0
open weightstool callreasoningstructured quant: unknown

spread (output)

2.3×

$4.05 – $9.36 · 24 providers

24 providers priced · 1 omitted (stale)
ProviderInputOutputCache rdBlended
OpenRouter
unknown
free/—free/——free/—
Kilo Gatewaystale
relay router
free/—free/——free/—
Nvidia
relay router
free/—free/——free/—
Eden AI
relay router
$1.00$4.05$0.170$0.831
Eden AI
relay router
$1.00$4.05$0.170$0.749
Fireworks AI
relay router
$1.00$4.05$0.170$0.749
Hugging Face
relay router
$1.00$4.05—$1.28*
Baseten
relay router
$1.00$4.05—$1.28*
Kilo Gateway
relay router
$0.950$4.05$0.160$0.729
Vercel AI Gateway
unknown
$1.00$4.05$0.170$0.749
Merge Gateway
unknown
$1.00$4.05$0.170$0.749
Together AI
open weights host
$1.00$4.05$0.170$0.749
NanoGPT
relay router
$1.00$4.05$0.170$0.749
Neon
relay router
$1.00$4.05$0.170$0.749
OpenRouter
unknown
$1.00$4.05$0.170$0.749
Deep Infra
open weights host
$0.950$4.05$0.160$0.729
Eden AI
relay router
$0.950$4.05$0.160$0.729
Eden AI
relay router
$1.00$4.05$0.170$0.749
Charm Hyper
relay router
$1.09$4.41$0.185$0.816
LLMTR
relay router
$1.87$4.68—$2.13*
Impossibl
relay router
$1.87$4.68$0.374$1.17
Requesty
relay router
$1.87$4.68$0.374$1.17
Thinking Machinesoutlier
first party lab
$1.87$4.68$0.374$1.17
Modal
relay router
$1.20$5.00$0.270$0.954
Venice AI
unknown
$1.25$5.06$0.212$0.937
Thinking Machinesoutlier
first party lab
$3.74$9.36$0.748$2.35
Abacusoutlier
relay router
$3.74$9.36$0.748$2.35

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