The moment it happens

Read receipts you photograph

Send your bot a photo of a receipt and get the merchant, date and total back.

Runs: The moment it happens
Apps: Telegram
AI: Not needed
Access: bot token

Send this to your assistant

Create a ClickRuntime automation: when I send a receipt photo to my Telegram bot, use my OpenAI key to read the merchant, date and total, and reply with them.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Add to ChatGPT Add to Claude

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A freelancer collects paper receipts in a pocket, a small business owner photographs invoices on a supplier visit, and a traveler snaps menus and signs in another language. Typing the figures into a spreadsheet later is tedious and error-prone. Receipts fade, get lost or pile up until tax time, when the missing ones cost real money. Small amounts matter when they repeat.

When you send a photo to your Telegram bot, ClickRuntime downloads the largest version with getFile, passes it to the vision model you connect with your own key, and replies with a description or the extracted fields such as merchant, date and total. You can optionally log each result to state for later export.

It suits freelancers, small teams and travelers who want to capture paper quickly and read it later.

What you get out of it

Receipts are captured at the moment you get them
Taking a photo while you are still at the counter means nothing is lost in a pocket. Expenses are recorded when you remember them, not weeks later. Even a quick snap in a taxi or a cafe is enough to preserve the details.
Typing figures by hand ends
The merchant, date and total come back as text you can copy. That cuts transcription errors, which are a common source of mismatches at reconciliation time. A wrong digit in a total is exactly the kind of slip that makes a ledger fail to balance later.
Tax season becomes less stressful
A running list of extracted receipts gives your accountant what they need. Deductible expenses are less likely to be forgotten, which can mean real money saved. Capturing everything in time can be worth far more than the small cost of reading each photo.
Descriptions help beyond receipts
The same flow can describe a photo, read a sign or translate a menu. One bot covers several small tasks that would otherwise need different apps. Menus, street signs, handwritten notes and whiteboards all fit the same simple flow.
You control the vision model and cost
Because it uses your own key, you choose the provider and see usage on your own account. There is no hidden charge from an extra service. That keeps costs honest, since you pay only for the photos you actually send.

How it works

What happens, step by step

When you send a photo of a receipt to your Telegram bot, ClickRuntime downloads the clearest version straight away.
It sends the photo to your own image-reading AI model.
The bot replies with the merchant, date and total it found on the receipt.

Before it runs live

Connect Telegram
Paste your automation's link into the other app's webhook settings

What you get

RunsThe moment it happens

Read receipts you photographjust nowSucceeded

Telegram · ReceiptsMerchant: Northwind Café / Date: 2026-10-18 / Total: $14.60

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.

Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

Changes you can ask for

Act only on the items that match your own rules, and skip the rest
Add an AI step, for example to summarize, sort or draft a reply
Add another app, for example also send it to Slack
Combine it with other Telegram steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.

photo_receipt_reading_via_the_bot.pyexample

import base64
from clickruntime import on_event, http, credentials

def tg(method, **params):
    r = http.post(f"https://api.telegram.org/bot{credentials.secret('TELEGRAM_BOT_TOKEN')}/{method}", json=params)
    r.raise_for_status()
    return r.json()["result"]

@on_event
def handle(event):
    msg = (event.json or {}).get("message") or {}
    if "photo" not in msg:
        return {"read": False}
    path = tg("getFile", file_id=msg["photo"][-1]["file_id"])["file_path"]
    img = http.get(f"https://api.telegram.org/file/bot{credentials.secret('TELEGRAM_BOT_TOKEN')}/{path}").content
    r = http.post("https://api.openai.com/v1/chat/completions",
                  headers={"Authorization": f"Bearer {credentials.secret('OPENAI_API_KEY')}"},
                  json={"model": "gpt-4o-mini", "messages": [{"role": "user", "content": [
                      {"type": "text", "text": "Read this receipt. Reply as: Merchant / Date / Total"},
                      {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64," + base64.b64encode(img).decode()}}]}]})
    answer = r.json()["choices"][0]["message"]["content"]
    tg("sendMessage", chat_id=msg["chat"]["id"], text=answer)
    return {"read": True}

FAQ

Common questions

Which vision model does it use?

The one you connect with your own API key, for example a vision-capable model from OpenAI. Its use is billed to your account. ClickRuntime's built-in AI is used for text, so image reading relies on your key.

How accurate is the receipt reading?

Clear, flat, well-lit photos give good results. Crumpled, faded or angled receipts are less reliable, so check totals before you rely on them for accounts. Retaking the photo usually fixes problems. Retaking the photo is quick and costs very little.

Can it save the results to a spreadsheet?

It can log each result to state, and you can have a regular email with the list as a CSV. Connecting to a specific spreadsheet depends on the tool, so tell your assistant where you keep your records.

What permissions does it need?

bot token. Nothing else in your accounts is used.

Does it need AI?

No. It runs without AI, so it doesn't use your plan's AI allowance.

How many runs does it use?

One run for each event the app sends.

Can I change how it works?

Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

The moment it happens