aivyuh-finops 0.1.0

V7 AI FinOps SDK — transparent cost telemetry for Anthropic and OpenAI Python clients

aivyuh-finops

Transparent cost telemetry for Anthropic and OpenAI Python clients. Part of the V7 AI FinOps platform.

Wrap your existing AI SDK client in one line — aivyuh-finops captures model, tokens, cost, and latency metadata and sends it to the V7 backend. It never reads or stores prompt or response content.

Install

pip install aivyuh-finops

With provider extras:

pip install aivyuh-finops[anthropic]   # includes anthropic SDK
pip install aivyuh-finops[openai]      # includes openai SDK
pip install aivyuh-finops[all]         # both

Quickstart

Anthropic

from anthropic import Anthropic
from aivyuh_finops import wrap_anthropic

client = wrap_anthropic(Anthropic(), {
    "telemetry_endpoint": "https://finops-api.aivyuh.com/telemetry",
    "customer_id": "cust-123",
    "project": "my-app",
    "tags": {"feature": "chat", "team": "product"},
})

# Use the client exactly as before — all types are preserved
message = client.messages.create(
    model="claude-sonnet-4-6-20260320",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello, Claude!"}],
)

OpenAI

from openai import OpenAI
from aivyuh_finops import wrap_openai

client = wrap_openai(OpenAI(), {
    "telemetry_endpoint": "https://finops-api.aivyuh.com/telemetry",
    "customer_id": "cust-123",
    "project": "my-app",
    "tags": {"feature": "search", "team": "platform"},
})

# Use the client exactly as before
completion = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello, GPT!"}],
)

Configuration

Option	Type	Required	Description
telemetry_endpoint	str	Yes	V7 telemetry ingest URL (https://finops-api.aivyuh.com/telemetry)
customer_id	str	Yes	Your customer ID for cost attribution
project	str	No	Project name for grouping costs
tags	dict[str, str]	No	Custom key-value tags attached to every request
disable_telemetry	bool	No	Set True to disable (useful in tests)

Production API Endpoint

https://finops-api.aivyuh.com/telemetry

POST telemetry payloads are accepted with a 202 Accepted response. The endpoint is fire-and-forget — if unreachable, your application is unaffected.

How It Works

1. wrap_anthropic() / wrap_openai() monkey-patches messages.create() or chat.completions.create().
2. After each successful call, it extracts usage metadata (model, tokens, latency) and estimates cost.
3. A background thread sends the telemetry payload via HTTP POST — errors are silently swallowed.
4. Your original response is returned untouched. Zero external dependencies (uses urllib + threading).

Requirements

• Python >= 3.10
• anthropic >= 0.40.0 and/or openai >= 1.50.0 (optional peer dependencies)

License

MIT