Llama 3.1 70B Instruct

Meta · text · Open-source · GPU Tier A

liveContext 128K

Requests 30d+14.2%

2.9M

Tokens 30d+18.4%

6.6B

Revenue 30d+20.2%

$2.6K

Gross margin+1.2%

48%

Revenue − node payouts

Active users+9.4%

444

Active nodes+3.4%

3,589

Input $/1M

$0.35

Output $/1M

$0.55

p50 latency

420ms

p95 latency

1.3s

Error rate

1.5%

Usage over time (30d)

Pricing simulator

Elasticity-based what-if · Llama 3.1 70B Instruct

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

Projected revenue 30d

$2.6K

0.0%

Projected requests

2862k

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

$0.35

Output

$0.55

Together AI

In: $0.88 · Out: $0.88

FAR saves

−49%

Groq

In: $0.59 · Out: $0.79

FAR saves

−35%

Fireworks AI

In: $0.9 · Out: $0.9

FAR saves

−50%

Revenue economics

How this model generates revenue

Developer pays

$0.35 in + $0.55 out per 1M tokens

Node operator earns

44% of revenue distributed as payout · Tier A

FAR AI gross margin

48%