Llama 3.1 405B Instruct

Meta · text · Open-source · GPU Tier S

liveContext 128K

Requests 30d+14.2%

1.9M

Tokens 30d+18.4%

5.4B

Revenue 30d+20.2%

$7.2K

Gross margin+1.2%

40%

Revenue − node payouts

Active users+9.4%

310

Active nodes+3.4%

2,419

Input $/1M

$1.2

Output $/1M

$1.8

p50 latency

720ms

p95 latency

2.1s

Error rate

2.3%

Usage over time (30d)

Pricing simulator

Elasticity-based what-if · Llama 3.1 405B Instruct

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

Projected revenue 30d

$7.2K

0.0%

Projected requests

1926k

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

$1.2

Output

$1.8

Together AI

In: $3.5 · Out: $3.5

FAR saves

−57%

Fireworks AI

In: $3 · Out: $3

FAR saves

−50%

Revenue economics

How this model generates revenue

Developer pays

$1.2 in + $1.8 out per 1M tokens

Node operator earns

52% of revenue distributed as payout · Tier S

FAR AI gross margin

40%