Give your Telegram community fast token answers. A chat bot reads each message and returns live insights from a crypto market API. Great for trading groups, token projects, and community managers who need quick, clear replies.

When a user sends a message, the Telegram trigger captures it and adds a session id so the bot can keep chat context. A smart agent uses an OpenAI model and a short memory window to understand the question and call the right DexScreener tools. It can search pairs, check top boosts, fetch token profiles, look up pools, and resolve contract or pair addresses in real time. The same assistant can also listen through an n8n chat endpoint for web chat use. Answers are sent back to Telegram as a simple message your audience can read right away.

Setup needs a Telegram bot token and an OpenAI API key. DexScreener calls use public endpoints, so no key is required. Expect research time to drop from minutes per query to seconds, which lifts engagement and cuts repeat questions. Useful for daily market updates, quick token checks, and guiding new members who ask about contracts or pairs.

• Telegram Trigger listens for new messages and passes the chat id for replies.
• Optional chat endpoint receives questions through an n8n web chat entry point.
• Set node adds a sessionId from the Telegram chat id to keep per user context.
• Window Buffer Memory keeps recent messages so the agent remembers short history.
• OpenAI Chat Model uses gpt 4o mini to read intent and format answers.
• Agent routes questions to DexScreener tools based on the user prompt.
• DexScreener calls include token profiles, latest and top boosts, pair search, pools, pairs by token, and pair lookups by chain and address.
• Telegram node posts the final answer back to the user in the same chat.

• Reduce manual token lookups from 10 minutes to under 30 seconds per request
• Automate up to 80 percent of routine pair and price questions in chat
• Improve answer accuracy by using live API data instead of screenshots
• Handle dozens of simultaneous questions without adding moderators
• Connect Telegram, OpenAI and DexScreener in one reliable flow
• Cut back and forth with users by 50 percent during busy hours

1. Import the template into n8n: Create a new workflow in n8n > Click the three dots menu > Select 'Import from File' > Choose the downloaded JSON file.
2. You'll need accounts with Telegram, OpenAI and DexScreener. See the Tools Required section above for links to create accounts with these services.
3. Create a Telegram bot with BotFather and copy the bot token. Keep the bot in a test chat so you can send messages easily.
4. In the n8n credentials manager, create a Telegram credential. Select Create new credential, enter your bot token, and save.
5. Open the Telegram Trigger node. Select your Telegram credential and confirm updates include message. Save the node.
6. Open the Telegram send node. Select the same Telegram credential and confirm chatId is set to {{$('Telegram Trigger').item.json.message.chat.id}}.
7. Open the OpenAI Chat Model node. In the credential dropdown, click Create new credential, paste your OpenAI API key from the OpenAI dashboard, select gpt 4o mini, and save.
8. No DexScreener key is required. Check each DexScreener tool node uses the provided URL and the Accept header is set to */*.
9. Open the Adds SessionId node and verify the expression uses {{$json.message.chat.id}} and Include Other Fields is enabled.
10. Confirm the agent node is connected to the OpenAI model, memory, and all DexScreener tools. Save and activate the workflow.
11. Test in Telegram by sending a query such as top boosted tokens or a token contract address. You should receive a clear answer in seconds.
12. Optional test for web chat: trigger the n8n chat endpoint and send a message. If no reply, make sure the workflow is active and your instance is reachable online.
13. Troubleshoot common issues: if the bot does not respond, recheck the Telegram credential and ensure the workflow is active. For OpenAI errors, verify your API key and quota. If you hit DexScreener rate limits, add a Wait node or lower request frequency.