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

DeepSeek V4 Flash 0731

deepseek· 2026-07-31· 1.0M ctx· mit
open weightstool callreasoningstructured quant: unknown

spread (output)

19×

$0.070 – $1.34 · 53 providers

53 providers priced
ProviderInputOutputCache rdBlended
SCNet Token Plan
relay router
free/—free/—$0free/—
Alibaba Token Plan (China)
relay router
free/—free/—$0free/—
Nvidia
relay router
free/—free/——free/—
Alibaba Token Plan
relay router
free/—free/—$0free/—
OpenRouter
unknown
free/—free/——free/—
Kilo Gatewayoutlier
relay router
free/—free/——free/—
Merge Gateway
unknown
$0.035$0.070$0.0070$0.020
OpenRouter
unknown
$0.040$0.080$0.016$0.028
CrofAI
relay router
$0.080$0.100$0.0030$0.033
Vercel AI Gateway
unknown
$0.076$0.153$0.014$0.044
NanoGPT
relay router
$0.050$0.160$0.013$0.036
NanoGPT
relay router
$0.050$0.160$0.013$0.036
Cortecs
relay router
$0.055$0.174$0.0090$0.037
Eden AIoutlier
relay router
$0.065$0.180—$0.075*
Ambient
relay router
$0.080$0.180$0.016$0.048
Deep Infra
open weights host
$0.060$0.180$0.015$0.042
Eden AIoutlier
relay router
$0.060$0.180$0.015$0.042
DigitalOcean
relay router
$0.080$0.252$0.025$0.061
Perplexity Agent
unknown
$0.130$0.260$0.028$0.077
Baseten
relay router
$0.130$0.260$0.028$0.077
RunInfra
relay router
$0.130$0.270$0.010$0.066
OpenReason
relay router
$0.137$0.274—$0.150*
Inceptron
relay router
$0.130$0.280$0.030$0.080
Bothub
relay router
$0.100$0.280—$0.116*
Eden AIoutlier
relay router
$0.140$0.280$0.028$0.093
Eden AIoutlier
relay router
$0.140$0.280$0.140$0.153
Eden AIoutlier
relay router
$0.140$0.280$0.030$0.083
Hugging Face
relay router
$0.140$0.280—$0.153*
Nebius Token Factory
relay router
$0.140$0.280$0.140$0.153
Together AI
open weights host
$0.140$0.280$0.030$0.083
CoreWeave
relay router
$0.130$0.280$0.070$0.105
AIHubMix
unknown
$0.142$0.284$0.028$0.083
Melious
relay router
$0.116$0.290$0.023$0.073
OrcaRouter
relay router
$0.147$0.295$0.020$0.080
Eden AIoutlier
relay router
$0.250$0.300$0.063$0.135
TensorX
relay router
$0.250$0.300$0.060$0.134
Venice AI
unknown
$0.175$0.350$0.035$0.102
GreenPT
relay router
$0.160$0.399$0.046$0.109
Alibaba
first party lab
$0.200$0.400$0.040$0.116
AKI.IO
relay router
$0.200$0.500$0.100$0.164
Requesty
relay router
$0.280$0.560$0.070$0.172
Requesty
relay router
$0.280$0.560$0.070$0.172
Merge Gateway
unknown
$0.280$0.560$0.070$0.172
Ollama Cloud
relay router
$0.220$0.660$0.0070$0.125
Fireworks AI
relay router
$0.220$0.660$0.0070$0.125
Eden AIoutlier
relay router
$0.220$0.660$0.022$0.134
Eden AIoutlier
relay router
$0.220$0.660$0.0070$0.125
Venice AI
unknown
$0.350$0.700$0.087$0.215
Eden AIoutlier
relay router
$0.458$0.917—$0.500*
Ofox
relay router
$0.308$0.924$0.0098$0.174
Scaleway
relay router
$0.468$0.936$0.094$0.272
IteraCompute
relay router
$0.340$1.05$0.035$0.211
EmpirioLabs AIoutlier
relay router
$0.424$1.27$0.424$0.501
Cloudflare Workers AIoutlier
relay router
$0.440$1.32$0.014$0.249
Chutesoutlier
relay router
$0.440$1.32$0.044$0.268
Charm Hyperoutlier
relay router
$0.440$1.32$0.044$0.268
Eden AIoutlier
relay router
$0.440$1.32$0.014$0.249
Kilo Gatewayoutlier
relay router
$0.440$1.32$0.028$0.258
Volcengine Arkoutlier
relay router
$0.445$1.34$0.015$0.252

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