AI cost tracking for OpenAI, Anthropic, Gemini & 7 more

Stop getting scared by your AI bill.

Change one line of code and see your spend by day, model and feature — with budget alerts before it spikes. Report-only: your API keys never leave your app.

Start tracking — it's free See how it works

Free while in early access · No credit card · Keys never leave your app

Turn the page

Quickstart

Up and running in under five minutes.

Install

terminal

npm install @tokli/node

pip install tokli

Wrap your client

index.ts

import OpenAI from "openai";import { wrapOpenAI } from "@tokli/node"; const openai = new OpenAI();const wrapped = wrapOpenAI(openai, {  ingestKey: process.env.TOKLI_INGEST_KEY,});// usage is reported automatically

import Anthropic from "@anthropic-ai/sdk";import { wrapAnthropic } from "@tokli/node"; const anthropic = new Anthropic();const wrapped = wrapAnthropic(anthropic, {  ingestKey: process.env.TOKLI_INGEST_KEY,});// usage is reported automatically

import { GoogleGenAI } from "@google/genai";import { wrapGemini } from "@tokli/node"; const client = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY });const wrapped = wrapGemini(client, {  ingestKey: process.env.TOKLI_INGEST_KEY,});// usage is reported automatically

import OpenAI from "openai";import { wrapDeepSeek } from "@tokli/node"; const client = new OpenAI({ baseURL: "https://api.deepseek.com" });const wrapped = wrapDeepSeek(client, {  ingestKey: process.env.TOKLI_INGEST_KEY,});// usage is reported automatically

import OpenAI from "openai";import { wrapXai } from "@tokli/node"; const client = new OpenAI({ baseURL: "https://api.x.ai/v1" });const wrapped = wrapXai(client, {  ingestKey: process.env.TOKLI_INGEST_KEY,});// usage is reported automatically

import OpenAI from "openai";import { wrapMistral } from "@tokli/node"; const client = new OpenAI({ baseURL: "https://api.mistral.ai/v1" });const wrapped = wrapMistral(client, {  ingestKey: process.env.TOKLI_INGEST_KEY,});// usage is reported automatically

import OpenAI from "openai";import { wrapQwen } from "@tokli/node"; const client = new OpenAI({ baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1" });const wrapped = wrapQwen(client, {  ingestKey: process.env.TOKLI_INGEST_KEY,});// usage is reported automatically

import OpenAI from "openai";import { wrapGlm } from "@tokli/node"; const client = new OpenAI({ baseURL: "https://api.z.ai/api/paas/v4" });const wrapped = wrapGlm(client, {  ingestKey: process.env.TOKLI_INGEST_KEY,});// usage is reported automatically

import OpenAI from "openai";import { wrapKimi } from "@tokli/node"; const client = new OpenAI({ baseURL: "https://api.moonshot.ai/v1" });const wrapped = wrapKimi(client, {  ingestKey: process.env.TOKLI_INGEST_KEY,});// usage is reported automatically

import OpenAI from "openai";import { wrapOpenRouter } from "@tokli/node"; const client = new OpenAI({ baseURL: "https://openrouter.ai/api/v1" });const wrapped = wrapOpenRouter(client, {  ingestKey: process.env.TOKLI_INGEST_KEY,});// usage is reported automatically

from openai import OpenAIfrom tokli import wrap_openai client = OpenAI()wrapped = wrap_openai(client)# reads TOKLI_INGEST_KEY from your env# usage is reported automatically

from anthropic import Anthropicfrom tokli import wrap_anthropic client = Anthropic()wrapped = wrap_anthropic(client)# reads TOKLI_INGEST_KEY from your env# usage is reported automatically

from google import genaifrom tokli import wrap_gemini client = genai.Client()wrapped = wrap_gemini(client)# reads TOKLI_INGEST_KEY from your env# usage is reported automatically

from openai import OpenAIfrom tokli import wrap_deepseek client = OpenAI(base_url="https://api.deepseek.com")wrapped = wrap_deepseek(client)# reads TOKLI_INGEST_KEY from your env# usage is reported automatically

from openai import OpenAIfrom tokli import wrap_xai client = OpenAI(base_url="https://api.x.ai/v1")wrapped = wrap_xai(client)# reads TOKLI_INGEST_KEY from your env# usage is reported automatically

from openai import OpenAIfrom tokli import wrap_mistral client = OpenAI(base_url="https://api.mistral.ai/v1")wrapped = wrap_mistral(client)# reads TOKLI_INGEST_KEY from your env# usage is reported automatically

from openai import OpenAIfrom tokli import wrap_qwen client = OpenAI(base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1")wrapped = wrap_qwen(client)# reads TOKLI_INGEST_KEY from your env# usage is reported automatically

from openai import OpenAIfrom tokli import wrap_glm client = OpenAI(base_url="https://api.z.ai/api/paas/v4")wrapped = wrap_glm(client)# reads TOKLI_INGEST_KEY from your env# usage is reported automatically

from openai import OpenAIfrom tokli import wrap_kimi client = OpenAI(base_url="https://api.moonshot.ai/v1")wrapped = wrap_kimi(client)# reads TOKLI_INGEST_KEY from your env# usage is reported automatically

from openai import OpenAIfrom tokli import wrap_openrouter client = OpenAI(base_url="https://openrouter.ai/api/v1")wrapped = wrap_openrouter(client)# reads TOKLI_INGEST_KEY from your env# usage is reported automatically

Works with 10 providers

OpenAI
Anthropic
Gemini
DeepSeek
xAI
Mistral
Qwen
GLM
Kimi
OpenRouter

What you get

Every call, priced to the micro-cent.

Set TOKLI_INGEST_KEY and every call shows up here — by day, model and feature. Without the key the wrapper is a silent no-op.

Daily spend chart, with the current day marked as partial — By day

Cost drivers: spend per feature tag, each with its share of the total — By feature

Spend by model, with calls, tokens and cost for each one — By model

Control

Know before the invoice.

Monthly budget ruler showing spend against the expected pace for today — **A pace needle, not a progress bar.** See if today's spend is ahead of where the month should be — and what it projects to.

Daily spend chart with outlier days flagged as spikes — **Spike days, flagged.** Days that break your pattern get marked on the chart — and budget alerts email you before the line is crossed.

Last event · 3 min ago

Always know it's flowing. The dashboard shows when the last event landed, and warns if ingestion goes quiet.

The bottom line

Your AI bill, explained.

Setup1 line of code
Your API keys shared0
Added latency0 ms
Price while in early access$0.00

Start tracking — it's free

No credit card · Uninstall = delete one line

FAQ

Before you add it to production.

Does tokli see my provider API keys?

No. tokli is report-only: your code calls the provider with your own key, and the SDK reads token usage from responses you already receive. Your keys never leave your app.

Does the SDK add latency to my LLM calls?

No. Usage is reported fire-and-forget after your call completes — tokli never sits in the request path.

What happens if tokli goes down?

Nothing happens to your app. The wrapper fails open: if the ingest key is missing or reporting fails, it's a silent no-op and your calls work exactly as before.

Does it work with streaming responses?

Yes. Every supported provider reports token usage in the final stream event, and the SDK captures it without touching your stream. A few providers need stream_options: { include_usage: true } on streaming calls — each wrapper's docs say whether yours does.

Which providers and models are supported?

OpenAI, Anthropic, Gemini, DeepSeek, xAI, Mistral, Qwen, GLM, Kimi and OpenRouter, with costs computed server-side from a versioned price table. Calls to unknown models are still recorded and flagged — never dropped.

How much does tokli cost?

tokli is free while in early access. No credit card required.