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

DeepSeek V4 Flash Vision Exp

deepseek· 2026-08-21· 1.0M ctx· mit
open weightstool callreasoningstructured quant: unknown

spread (output)

6.6×

$0.200 – $1.32 · 18 providers

18 providers priced
ProviderInputOutputCache rdBlended
CrofAI
relay router
$0.080$0.200$0.0070$0.044
OpenCode Zen
relay router
$0.140$0.280$0.028$0.081
AMD
relay router
$0.140$0.280$0.0028$0.065
OrcaRouter
relay router
$0.147$0.295$0.020$0.080
DeepSeek
first party lab
$0.150$0.600$0.0030$0.097
Eden AI
relay router
$0.150$0.600$0.0030$0.097
OpenCode Go
relay router
$0.150$0.600$0.0030$0.097
AIHubMix
unknown
$0.155$0.620$0.0031$0.101
OpenRouter
unknown
$0.216$0.647$0.0069$0.122
NanoGPT
relay router
$0.220$0.660$0.0070$0.125
Fireworks AI
relay router
$0.220$0.660$0.0070$0.125
Vercel AI Gateway
unknown
$0.220$0.660$0.0070$0.125
above.dev
relay router
$0.242$0.726$0.0077$0.137
CrossModel
relay router
$0.270$1.08$0.0054$0.197
Ofox
relay router
$0.440$1.32$0.014$0.249
Kilo Gateway
relay router
$0.440$1.32$0.028$0.258
Hugging Face
relay router
$0.440$1.32—$0.520*
Deep Infra
open weights host
$0.440$1.32$0.014$0.249

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