# URLs for Online Service Blocks

To ensure the proper functioning of blocks with online services, it is necessary to configure access at the server or machine level where the connection occurs via RDP, VNC, or AnyDesk.

Below is the current list of URLs for the online service blocks being used:

<table data-header-hidden><thead><tr><th width="176"></th><th width="406"></th><th width="235"></th></tr></thead><tbody><tr><td><strong>Service Name</strong></td><td><strong>URL</strong></td><td><strong>Notes</strong></td></tr><tr><td>ChatGPT</td><td><code>https://api.openai.com/v1/chat/completions</code></td><td><p>Default access:</p><p><code>https://sherpa.wiregeo.com</code><br><br></p></td></tr><tr><td>Sherpa AI Server</td><td>Connects to the server where the application is installed (in the Assistant settings)</td><td>The address depends on the local installation, usually an internal IP or domain name</td></tr><tr><td>YandexGPT</td><td><code>https://iam.api.cloud.yandex.net/iam/v1/tokens</code><br><br><code>https://llm.api.cloud.yandex.net/foundationModels/v1/completion</code></td><td><br></td></tr><tr><td>GigaChat</td><td><code>https://gigachat.devices.sberbank.ru/api/v1/chat/completions</code></td><td><br></td></tr><tr><td>Claude</td><td><code>https://api.anthropic.com/v1/messages</code></td><td><br></td></tr><tr><td>GroqChat</td><td><code>https://api.groq.com/openai/v1/chat/completions</code></td><td><br><br></td></tr><tr><td>OpenRouter</td><td><code>https://openrouter.ai/api/v1/chat/completions</code></td><td><br></td></tr></tbody></table>

Access to these addresses is required for the corresponding blocks to function:

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXf3P0Z_ONengwPdrtZDauJ1m9lKsMI5hGKR5wCf9ZkHQaa3zkZW5tk0SxaFzW7PfDIuCVRqB_XUD5efGQZaeHTolvhDW3FlTdywEIN_KC4v4Ko-_I_sgSZesy-FqFTPhMqT4Uhtvw?key=c-kfAEp7VBchDYgccZTyJA" alt=""><figcaption></figcaption></figure>

Detailed descriptions of these blocks can be found in the corresponding sections:

{% embed url="<https://docs.sherparpa.ru/sherpa-designer/spravochnik-blokov/mashinnoe-obuchenie-machine-learning/zapros-k-chatgpt-openaichatrequest>" %}

{% embed url="<https://docs.sherparpa.ru/sherpa-designer/spravochnik-blokov/mashinnoe-obuchenie-machine-learning/zapros-k-sherpa-ai-server-sherpaaiserverrequest>" %}

{% embed url="<https://docs.sherparpa.ru/sherpa-designer/spravochnik-blokov/mashinnoe-obuchenie-machine-learning/zapros-k-yandexgpt-yandexgptrequest>" %}

{% embed url="<https://docs.sherparpa.ru/sherpa-designer/spravochnik-blokov/mashinnoe-obuchenie-machine-learning/zapros-k-gigachat-sbergigachatrequest>" %}

{% embed url="<https://docs.sherparpa.ru/sherpa-designer/spravochnik-blokov/mashinnoe-obuchenie-machine-learning/zapros-k-claude-clauderequest>" %}

{% embed url="<https://docs.sherparpa.ru/sherpa-designer/spravochnik-blokov/mashinnoe-obuchenie-machine-learning/zapros-k-groqchat-groqchatrequest>" %}

{% embed url="<https://docs.sherparpa.ru/sherpa-designer/spravochnik-blokov/mashinnoe-obuchenie-machine-learning/zapros-k-openrouter-openrouterchatrequest>" %}

More about connecting third-party services:

{% embed url="<https://docs.sherparpa.ru/sherpa-robot-i-sherpa-assistant/podklyuchenie-storonnikh-servisov>" %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.sherparpa.ru/en/sherpa-rpa/sherpa-designer/url-adresa-po-kotorym-obrashayutsya-bloki-onlain-servisov.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.