Llama 3.1 8B Instruct

Meta · text · Open-source · GPU Tier B

liveContext 128K

Requests 30d+14.2%

2.3M

Tokens 30d+18.4%

5.9B

Revenue 30d+20.2%

$335.2

Gross margin+1.2%

54%

Revenue − node payouts

Active users+9.4%

528

Active nodes+3.4%

2,888

Input $/1M

$0.05

Output $/1M

$0.08

p50 latency

280ms

p95 latency

720ms

Error rate

1.3%

Usage over time (30d)

Pricing simulator

Elasticity-based what-if · Llama 3.1 8B Instruct

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

Projected revenue 30d

$335.2

+0.0%

Projected requests

2301k

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

FAR AI

Input

$0.05

Output

$0.08

Together AI

In: $0.18 · Out: $0.18

FAR saves

−64%

Groq

In: $0.05 · Out: $0.08

+-0%

Fireworks AI

In: $0.2 · Out: $0.2

FAR saves

−68%

Revenue economics

How this model generates revenue

Developer pays

$0.05 in + $0.08 out per 1M tokens

Node operator earns

38% of revenue distributed as payout · Tier B

FAR AI gross margin

54%