Qwen 2 VL 72B

Alibaba · vision · Open-source · GPU Tier A

liveContext 32K

Requests 30d+14.2%

960.7K

Tokens 30d+18.4%

2.2B

Revenue 30d+20.2%

$1.2K

Gross margin+1.2%

48%

Revenue − node payouts

Active users+9.4%

164

Active nodes+3.4%

1,212

Input $/1M

$0.5

Output $/1M

$0.7

p50 latency

420ms

p95 latency

1.3s

Error rate

3.3%

Usage over time (30d)

Pricing simulator

Elasticity-based what-if · Qwen 2 VL 72B

Input price ($/1M)Output price ($/1M)

Projected revenue 30d

$1.2K

0.0%

Projected requests

961k

0.0%

Projected margin

58%

Model assumes elasticity of -1.2 on total price. Replace with regression-derived elasticity per model when telemetry is wired.

p95 latency over time (30d)

Price comparison

$/1M tokens

No competitor pricing configured for this model yet. Add benchmark data in app/models/[id]/page.tsx.

Revenue economics

How this model generates revenue

Developer pays

$0.5 in + $0.7 out per 1M tokens

Node operator earns

44% of revenue distributed as payout · Tier A

FAR AI gross margin

48%