OpenAI Compatible Base URL Checker
This is an OpenAI-compatible API tester: check repeated /v1, complete endpoint paths, query parameters, and client URL-joining rules. All analysis stays in the current browser.
Waiting for address to be filled in
Fill in the Base URL currently used by other websites or projects. After checking, the recommended configuration and final request path will be displayed.
Diagnosis details
How do you check an OpenAI-compatible API URL?
Paste the current configuration into the tool first, then compare the final URL with client logs. Whether the field is called API Host, Endpoint, or Base URL matters less than where the client actually sent the request.
- 01
First check if there are duplicate paths
/v1/v1、/chat/completions/chat/completionsAll indicate that the client and configuration have repeatedly appended paths. - 02
Look at the response type again
Returning an HTML login page usually indicates that the request did not enter the API route; returning a JSON error continues to check authentication, models, and parameters.
- 03
Make the minimum request last
Query the model list first, and then send the short text request. After the basic call is successful, SSE, tool call and multi-modality are added.
Base URL FAQ
Tools can only verify configuration splices, actual authentication and model capabilities require actual requests.
Should the Base URL contain /v1?
Depends on whether the client automatically appends /v1. When customizing base_url directly using OpenAI SDK, it is usually filled in /v1; if the client explicitly states that it will be automatically appended, only the domain name or upper-level path is filled in. Ultimately request logs are more reliable than interface field names.
Why does /v1/v1/chat/completions appear?
The configuration value already contains /v1, and the client appends it automatically. One of the layers should be removed based on client rules and the final request address should be rechecked.
Will this tool request the API gateway I filled in?
No. The checking process only analyzes the URL string in the current browser, does not send network requests, and does not require an API Key. To verify real API responses, use model checking tools.
Why am I prompted to fill in the complete chat/completions address?
The Base URL field of most clients only accepts the base path, and the client will append models, chat/completions, or responses by itself. Filling the complete endpoint into the Base URL can easily result in duplicate paths.
How do you check an OpenAI-compatible API URL?
Paste the Base URL currently used by the client into the checker. Preview the final models, chat/completions, and responses URLs, then use client logs to confirm whether /v1 was appended twice. This tool analyzes only the URL string; it does not verify your API key or a live response.
Continue reading Model not found and /v1/v1 troubleshooting、OpenAI Compatible quick access, or view OpenAI API Reference .