Invoice INV-2025-07

July 2025 · clifford@trinidy.com

Back to Billing

July 2025

Exempt — Demo

INV-2025-07Issued Jul 1, 2025·Gold ED 26

Amount Due

$0.00

$23,712.00 waived

VTN Deployments

active during this period

Total Tokens Generated

4.76B

17.9M requests

Total TPS Blocks Used

5,750 / 10,400

55.3% of account block allocated

VTN Line-Item Cost

$13,110.00

4 endpoints · reference only

Unallocated Reserve

4,650 TPS

$10,602.00/mo still reserved

Total Invoice (reference)

$23,712.00

Waived — demo account

TPS Block Allocation

Your 10,400 TPS account block, cut into per-VTN endpoint sub-blocks at $2.28/TPS/mo.

GPT-OSS-120B Production · 3,000 TPS

Llama3 EU Inference · 1,500 TPS

Qwen2.5 Code Assist · 1,000 TPS

Llama3 Staging · 250 TPS

Unallocated · 4,650 TPS

VTN Deployments — Usage & Cost Breakdown

4 endpoints

GPT-OSS-120B Production

Active

nx2-p100-gptoss120b-prod

$6,840.00/mo

3,000 TPS block · $2.28/TPS

Daily TPS usage · 31-day period

avg 62% of block

Model

gpt-oss-120b

Region

us-east-1

Tokens Generated

3.13B

Total Requests

11.6M

Uptime

99.61%

Effective $ / 1M tok

$2.19

Llama3 EU Inference

Active

nx2-p100-llama3-eu-a1

$3,420.00/mo

1,500 TPS block · $2.28/TPS

Daily TPS usage · 31-day period

avg 59% of block

Model

llama-3.1-70b-instruct

Region

eu-west-1

Tokens Generated

1.46B

Total Requests

5.5M

Uptime

99.79%

Effective $ / 1M tok

$2.34

Qwen2.5 Code Assist

Active

nx2-p100-qwen25-code-tp2

$2,280.00/mo

1,000 TPS block · $2.28/TPS

Daily TPS usage · 31-day period

avg 10% of block

Model

qwen-2.5-32b-it-fast-tp2

Region

us-west-2

Tokens Generated

165.7M

Total Requests

750.0K

Uptime

99.9%

Effective $ / 1M tok

$13.76

Llama3 Staging

Active

nx2-p100-llama3-staging

$570.00/mo

250 TPS block · $2.28/TPS

Daily TPS usage · 31-day period

avg 0% of block

No usage this period

Model

llama-3.1-8b-instruct-fast-tp2

Region

us-west-2

Tokens Generated

Total Requests

Uptime

99.69%

Effective $ / 1M tok

—

Line-Item Summary

VTN Endpoint	TPS Block	Rate	Status	Cost / mo
GPT-OSS-120B Production	3,000 TPS	$2.28/TPS	Active	$6,840.00
Llama3 EU Inference	1,500 TPS	$2.28/TPS	Active	$3,420.00
Qwen2.5 Code Assist	1,000 TPS	$2.28/TPS	Active	$2,280.00
Llama3 Staging	250 TPS	$2.28/TPS	Active	$570.00
Unallocated reserve capacity	4,650 TPS	$2.28/TPS	Reserved	$10,602.00
Total (10,400 TPS block)				$23,712.00

This account is exempt from billing. The amounts above reflect what would be charged on a standard plan and are shown for reference only.