tollgateai 0.1.0

Track real LLM model usage and compute live gross margin with Tollgate.

tollgateai (Python SDK)

Track real LLM model usage and compute live gross margin with Tollgate. The SDK reads the actual usage off each provider response — you never hand-count tokens. Zero dependencies.

pip install tollgateai

Create an API key in Tollgate → Integrations, then set:

export TOLLGATE_API_KEY=tg_live_xxx
# optional, defaults to the hosted app:
export TOLLGATE_BASE_URL=https://tollgateapp.vercel.app

Auto-instrumentation (recommended)

Wrap your provider client once; every call reports real usage in the background.

Anthropic

from anthropic import Anthropic
from tollgate import create_tollgate_client, wrap_anthropic

tollgate = create_tollgate_client()  # reads TOLLGATE_API_KEY
anthropic = wrap_anthropic(
    Anthropic(), tollgate,
    customer_id="cust_A",     # your end customer
    revenue_unit_cents=50,    # what you charge for this unit ($0.50)
)

# Use the client normally — usage is tracked automatically.
anthropic.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=512,
    messages=[{"role": "user", "content": "Summarize this ticket…"}],
)

OpenAI

from openai import OpenAI
from tollgate import create_tollgate_client, wrap_openai

tollgate = create_tollgate_client()
openai = wrap_openai(OpenAI(), tollgate, customer_id="cust_A")

openai.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}],
)

revenue_unit_cents can also be a callable of the response, e.g. revenue_unit_cents=lambda res: 50 if res.something else 0.

Manual tracking

For providers without a wrapper (Bedrock, custom gateways) or full control:

from tollgate import create_tollgate_client

tollgate = create_tollgate_client()

tollgate.track({
    "customerId": "cust_A",
    "runId": "run_12345",
    "provider": "anthropic",
    "model": "claude-sonnet-4-6",
    "tokensIn": 1200,
    "tokensOut": 450,
    "reasoningTokens": 0,
    "cachedTokens": 0,
    "revenueUnitCents": 50,
    "idempotencyKey": "run_12345#step_1",  # exactly-once: safe to retry
})

Notes

• Idempotent. Events dedupe on idempotencyKey (auto-set to the provider response id by the wrappers), so retries never double-count.
• No prompt content is ever sent — only token counts and metadata.
• Streaming responses are not auto-tracked yet (the wrappers only report when a non-streaming usage is present). Track those manually for now.
• Non-blocking. Auto-instrumented tracking runs on a background thread; failures go to on_error (default: log a warning) and never break your call.

Licensed for use with Tollgate. Not open source.