tokli 0.0.0

Report-only usage tracking for OpenAI, Anthropic, Gemini, DeepSeek, xAI, Mistral, Qwen, GLM, Kimi and OpenRouter — wrap your client, we read the tokens.

tokli

Report-only usage tracking for tokli — a cost & usage dashboard for AI APIs. Wrap your existing provider client, keep calling it exactly as before, and tokli reports the token usage in the background. We never see your provider API key and we never sit in your request's critical path.

Supports OpenAI, Anthropic, Gemini, DeepSeek, xAI, Mistral, Qwen, GLM, Kimi and OpenRouter.

0.0.0 is a placeholder release reserving the name. The wrappers land in 0.1.0.

Install

pip install tokli

openai, anthropic and google-genai are optional extras — tokli has zero runtime dependencies and never pulls a provider SDK into your app.

Quickstart

from openai import OpenAI
from tokli import wrap_openai

client = wrap_openai(OpenAI())  # ingest key from TOKLI_INGEST_KEY
client.chat.completions.create(model="gpt-5.4", messages=messages)

The returned client behaves exactly like the original: every attribute we don't instrument passes straight through, and isinstance(client, OpenAI) still holds. AsyncOpenAI works through the same wrap_openai — there is no separate async wrapper.

Without an ingest key (neither the ingest_key argument nor TOKLI_INGEST_KEY), the wrapper is a silent no-op: your app keeps working exactly as before, nothing is reported.

Config

Argument	Env var	Default	Notes
ingest_key	TOKLI_INGEST_KEY	—	Required. Without it, the wrapper is a no-op.
endpoint	TOKLI_ENDPOINT	https://api.tokli.dev	Ingest API base URL.
timeout_ms	TOKLI_TIMEOUT_MS	2000	Timeout for the fire-and-forget report request.
flush_ms	TOKLI_FLUSH_MS	2000	How long to wait at exit for pending reports; 0 disables.
on_error	—	no-op	Called if reporting fails; never raises into your code.

How it works

Your code keeps calling the provider with your own key. After the response comes back, the SDK reads the usage object already present in it and sends those raw numbers to tokli, fire-and-forget — it never blocks your request, your event loop, or your key. Cost is computed server-side against a versioned price table, not by the SDK.

Reporting can never break your app: if anything in our own path raises — including your on_error handler — you still get the provider's response untouched.

Links

• tokli.dev
• Source & issues