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

Qwen3 Coder Flash

alibaba· 2025-07-28· 1M ctx
API onlytool call quant: unknown

spread (output)

4.4×

$0.574 – $2.50 · 13 providers

13 providers priced
ProviderInputOutputCache rdBlended
Alibaba (China)
relay router
$0.144$0.574—$0.183*
Merge Gateway
unknown
$0.144$0.574$0.029$0.110
Kilo Gateway
relay router
$0.195$0.975$0.039$0.187
OpenRoutertiered
unknown
$0.195$0.975$0.039$0.187
LLMTR
relay router
$0.300$1.50—$0.409*
NanoGPT
relay router
$0.300$1.50$0.150$0.314
LLM Gateway
relay router
$0.300$1.50$0.060$0.287
Eden AI
relay router
$0.300$1.50$0.060$0.287
DevPass (LLM Gateway)
relay router
$0.300$1.50$0.060$0.287
Alibaba
first party lab
$0.300$1.50—$0.409*
DigitalOcean
relay router
$0.450$1.70$0.090$0.335
Ofoxoutlier
relay router
$0.500$2.50$0.060$0.424
Ofoxoutlier
relay router
$0.500$2.50$0.060$0.424

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