Telegram Bot Token, Chat ID, and LLM Provider Setup Guide

Before you begin

You will need:

• A mobile phone number for Telegram account creation.
• Access to the Telegram app or Telegram Web.
• Permission to add a bot to the target private chat, group, supergroup, or channel.
• Hermes admin/settings access.
• Developer accounts for any LLM providers you want Hermes to use.

1. Create a Telegram account from zero

Illustrative screenshot: account signup with a mobile phone number.

2. Create a Telegram bot token with BotFather

Telegram bots are created through the verified BotFather bot. BotFather generates the HTTP API token that Hermes will use to send messages.

Illustrative screenshot: BotFather returns a redacted bot token.

Steps

1. Open Telegram and search for @BotFather.
2. Start the conversation and send /newbot.
3. Enter a display name, for example Hermes Alert Bot.
4. Enter a unique username ending in bot, for example hermes_alert_demo_bot.
5. Copy the generated token. It looks similar to 1234567890:AA....
6. Store the token in a server-side secret store, environment variable, or Hermes settings. Do not expose it in client-side code.

Confirm the token works

curl "https://api.telegram.org/bot<TELEGRAM_BOT_TOKEN>/getMe"

A valid token returns "ok": true and a bot profile containing the bot username.

3. Get the target Telegram chat ID

The chat_id is the unique identifier of the private chat, group, supergroup, or channel where Hermes should send notifications. Private chat IDs are usually positive numbers. Group, supergroup, and channel IDs are usually negative numbers; supergroups and channels often begin with -100.

Option A — Private chat ID

1. Open your bot in Telegram.
2. Tap Start or send /start.
3. Send a normal message such as hello.
4. Call getUpdates and read message.chat.id.

curl "https://api.telegram.org/bot<TELEGRAM_BOT_TOKEN>/getUpdates?timeout=20"

Option B — Group or supergroup chat ID

1. Add the bot to the group or supergroup.
2. Send a command addressed to the bot, for example /start@your_bot_username.
3. Call getUpdates and read message.chat.id.

Option C — Channel chat ID

1. Add the bot as a channel administrator.
2. Publish a new channel post after the bot has been added.
3. Call getUpdates and read channel_post.chat.id.

Illustrative screenshot: read the highlighted chat.id value from the API response.

Option D — Public group or channel username

If the target has a public username, you can often use @username directly in Telegram Bot API calls. To convert it to a numeric ID, call getChat:

curl "https://api.telegram.org/bot<TELEGRAM_BOT_TOKEN>/getChat?chat_id=@your_public_group_or_channel"

Send a final test message

curl -X POST "https://api.telegram.org/bot<TELEGRAM_BOT_TOKEN>/sendMessage" \
  -d "chat_id=<TARGET_CHAT_ID>" \
  -d "text=Hermes Telegram test message"

4. Configure Telegram notifications in Hermes

Illustrative screenshot: Telegram integration fields in Hermes.

5. Configure LLM provider API keys, URLs, and models

Illustrative screenshot: Hermes LLM provider cards can expand and collapse.

Illustrative screenshot: most providers follow the same pattern — create key, copy base URL, copy exact model ID.

curl https://api.openai.com/v1/models \
  -H "Authorization: Bearer <OPENAI_API_KEY>" 

curl "https://<resource>.openai.azure.com/openai/deployments/<deployment>/chat/completions?api-version=<api-version>" \
  -H "api-key: <AZURE_OPENAI_API_KEY>" \
  -H "Content-Type: application/json" 

curl https://api.anthropic.com/v1/messages \
  -H "x-api-key: <ANTHROPIC_API_KEY>" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model":"claude-sonnet-4-6","max_tokens":64,"messages":[{"role":"user","content":"Say hello"}]}'

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3-flash-preview:generateContent" \
  -H "x-goog-api-key: <GEMINI_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"Say hello"}]}]}'

curl https://api.groq.com/openai/v1/chat/completions \
  -H "Authorization: Bearer <GROQ_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"model":"llama-3.3-70b-versatile","messages":[{"role":"user","content":"Say hello"}]}'

curl https://api.mistral.ai/v1/models \
  -H "Authorization: Bearer <MISTRAL_API_KEY>" 

curl https://api.deepseek.com/models \
  -H "Authorization: Bearer <DEEPSEEK_API_KEY>" 

curl https://api.x.ai/v1/models \
  -H "Authorization: Bearer <XAI_API_KEY>" 

curl https://openrouter.ai/api/v1/models \
  -H "Authorization: Bearer <OPENROUTER_API_KEY>" 

curl http://localhost:11434/v1/models \
  -H "Authorization: Bearer ollama" 

curl https://<provider-or-gateway-domain>/v1/models \
  -H "Authorization: Bearer <CUSTOM_LLM_API_KEY>" 

6. Troubleshooting

Telegram getUpdates returns {"ok":true,"result":[]}

• Send a new message to the bot after calling the API. Old messages may not appear.
• Check that the token belongs to the exact bot you are messaging by running getMe.
• Delete any webhook before using getUpdates:

curl "https://api.telegram.org/bot<TELEGRAM_BOT_TOKEN>/deleteWebhook"

• For groups, send /start@your_bot_username rather than a plain message.
• For channels, make the bot an administrator and publish a new post after adding it.

LLM provider test fails

• Confirm the key is active, not expired, and has billing/credits.
• Confirm the base URL includes the correct path, usually /v1 for OpenAI-compatible providers.
• Confirm the model name is exact. Many errors come from using a marketing model name instead of the API model ID.
• For Azure OpenAI, use the deployment name in Hermes when required by the adapter.
• For local Ollama, confirm Hermes can reach the host. In Docker, localhost may mean the container, not your laptop.

References

Use the official provider documentation below to verify current account screens, model availability, pricing, and regional access before publishing the guide.

1. Telegram FAQ — account signup and privacy
2. Telegram Bot Features — BotFather, tokens, group privacy mode
3. Telegram Bot API — getUpdates, Chat, getChat, webhooks
4. OpenAI API platform docs
5. OpenAI models page
6. Anthropic Claude API overview
7. Anthropic models overview
8. Google Gemini API key docs
9. Google Gemini API reference
10. Microsoft Azure OpenAI / Foundry docs
11. Groq API docs
12. Mistral AI developer docs
13. DeepSeek API docs
14. xAI API docs
15. OpenRouter API docs
16. Ollama API docs