The Gemini has two kinds of basic quota errors.

1. The usual limit on the number of requests per minute/day:

"code": 429, "message": "Resource has been exhausted (eg check quota).", "status": "RESOURCE_EXHAUSTED", "details": null

This limit will be fixed automatically as soon as you stop exceeding it. You can read about the maximum number of requests per minute and per day at corresponding page of Google AI. At the time of the last update of this page, the free version of Gemini has:

In this case, the limits are summed up. That is, total limit for one API key: 75 requests per minute, or 15950 requests per day. However, to do this, your program must be able to automatically switch the model used while running. ClipAI can do it.

The same response can be given if the quota is not used up, but the load on Gemini servers is increased at the moment. This happens both on free and paid accounts.

2. Limit per region:

Quota exceeded for quota metric 'Generate Content API requests per minute'
and limit 'GenerateContent request limit per minute for a region'
of service 'generativelanguage.googleapis.com' for consumer 'project_number:...'

Despite what is stated in the answer, this error usually means that your key is locked. Wherein, judging by user reviews, in this case, you only need to reissue the API key: the account is often not blocked. This usually happens because the program you are using is too aggressive in using different API keys, for example, to generate a single article. This is prohibited by the Gemini rules, which is why it causes blocking.

The following error usually means the same thing:

API key expired. Please renew the API key.

Сообщение Ошибка квоты Google Gemini появились сначала на ClipAI.

• Work stopped in all templates at the same time;
• The buttons in Zennoposter are pressed, but work does not start when you click on “Start” (at the same time, you have read with this instruction), and also does not stop or be interrupted;
• The log may show "An error occurred while loading the project".

Most likely, the reason is one of the following:

1. Your Internet connection has been down for a long time, or there are some problems with it now. Restart Zennoposter/Zennobox and everything should work. If it doesn't work, check out this of the manual, especially paragraph 4.
2. You installed Zennoposter/Zennobox on another PC, or switched the license to another PC. You can fix this in the Hardware tab Zennolab personal account.
3. Recently your IP address changed or you turned on a VPN. In this case, try turning off the VPN, or go to the browser of the PC you are using. Zennolab personal account and log into your account.
4. In the "Stop" tab at the bottom of the Zennoposter screen, you have non-standard values. All 3 fields should say "-1".
5. There is a window with error information in the background that you did not notice. Check if it is there: you may only need, for example, to specify the correct date and time on your PC.

Сообщение Зависает Zennoposter/Zennobox появились сначала на ClipAI.

You could set the value here manually, or click one of the buttons at the top of the Zennoposter screen to increase this value (+1, +10, +100, or ∞):

• If here was specified at startup “1”—within this parameter, everything is configured correctly. It is necessary to look at the value that was at startup, and not what it is now, because during successful execution the value of this parameter decreases.
• If "-1" is an infinite number of executions. Of course, in this case, ClipAI will write articles on the same topics endlessly until work is interrupted.
• If any other value, and non-multi-threaded mode is selected, this is precisely the problem, it should be set to “1”.

Also check that input file (if the file is used as input) not in the same folder, which is indicated in the “Output data” tab of the input settings. If at the same time in the same settings tab it is also indicated “Save ...” - “Requests in one execution - in one file (with the name of the input file)”, then the above problem may occur, because received articles are written to a file with input data with these settings. ClipAI often warns in the log if the input settings are selected incorrectly.

If in the “Output Data” tab you select “Queries in one execution - into one file” - do not forget that when you run the same article again (or an article from the same input file) will added to the same file, as in the previous launch. If you don’t want this to happen, set “Each request to a separate file.”

Сообщение Пишется несколько статей в одной появились сначала на ClipAI.

A random number appears at the end of the file name:

This happens if in the input settings, on the “Output Data” tab, the “Save…” option is set to “Each request in a separate file.” In this case, for example, in the parameter “All executions with one request - in one file,” numbers are not added.

This is due to the fact that there cannot be two files with the same name in the same folder. Therefore, in order for each request to actually be in a separate file, you need to somehow change the file name. This is why numbers are added.

Here you can read about the different saving modes in the ClipAI and find out which one is best for your application.

Сообщение Как убрать цифры в конце названий файлов? появились сначала на ClipAI.

Also, the “How much to do” parameter at the bottom of the Zennoposter/Zennobox screen should be set to a value equal to the required number of articles. In this case, the number of threads will not be greater than the number of articles set in the “How many to do” parameter.

Сообщение Пишется несколько одинаковых статей, или после запуска ClipAI «Максимум потоков» становится «1» появились сначала на ClipAI.

Let's note right away: this happens not because the content is generated by AI. If you encounter pessimization in the search results or a search engine filter (for example, “MPK” - “Low Useful Content” from Yandex; or Low Value Content from Google or Adsense), or are simply afraid to encounter it, we recommend doing the following:

1. [Relevant for the Yandex search engine]. In "Yandex.Metric", or similar services, check whether there have been clicks to your site from the following or similar referrers:

factorial-eval.s3.yandex.net iframe-yang.yandex iframe-toloka.com

Carefully read the content on the pages you clicked on. Is there anything on them that can be considered useless content that does not satisfy the user’s request, or contains false facts?

2. Perhaps you embed tables to pages with topics in which they are clearly superfluous?

3. Perhaps you write articles on topics that are quite rare (for example, the legislation of an unfamiliar country or information about non-international companies); or on topics that depend on the date of writing (for example, news)? If so, the content will be of high quality only if to connect the AI's knowledge to the Internet.

4. Is there too much “water” or logical repetition in the articles on your website? If this is the case, you need to reduce the number of output characters in the settings. This is not about any automated review metrics, but about how your article is visible to the average visitor.

5. Check if there are too many ads on your site. This can affect if there is a lot of it, or if it is too “aggressive”.

6. It is believed that such a problem may arise if articles were added to the site too quickly. We didn’t notice this, but just in case, you can use the “Scheduled” status in the “Publication” tab along with randomizing the publication date in the same tab.

7. Subjective factors that the reviewer may not like. For example: website design, no content ("anchors") of the article, strange fonts, and so on. Remember that sometimes the result of getting a filter or blocking in search engines is precisely manual review by an ordinary person.

8. Try to enable automatic creation of comments when publishing. There are cases when this helped to get out from under the search engine filter.

Сообщение Страницы попали под фильтр поисковой системы! Что делать? появились сначала на ClipAI.

1. Check what's in tab “Settings” at the bottom of the Zennoposter screen in “How much to do” is not set to “0”.
2. Check what's in tab “Settings” at the bottom of the Zennoposter screen in “Maximum threads” is not set to “0”.
3. There, check that the “Proxy” parameter is set to “Do not use”. This value should be set even if you have set a proxy in the input settings.
4. Click button "Settings" in the top-left corner of Zennoposter, and then turn off "Resource Tracking".
5. Perhaps you have non-standard values in the "Stop" tab at the bottom of the Zennoposter screen? All 3 fields should say "-1".
6. Check the Log tab at the bottom of the Zennoposter screen. Perhaps there is some information there.

If all else fails, also check out this instruction.

Сообщение Нажимаю «Старт», но ничего не происходит. появились сначала на ClipAI.

1. Change GPT model. GPT-4 is approximately 10 times more expensive than GPT-3.5. And the old version of GPT-3.5 is usually more expensive than the new one. At the same time, GPT-3.5 along with ClipAI Plus often writes text better (and cheaper) than GPT4!
2. Disable image generation, or switch from DALLE to other sources. AI Image Creation - quite an expensive task.
3. In the “Parameters” tab of the input settings, enable “Priority on...” - “Token saving”. This may increase the number of logical repetitions in the text, but will significantly reduce costs.
4. Reduce the number of characters in the text (Processing tab).
5. If you need text of less than ~3000 characters, it may make sense to switch to the “Short Article Writing Mode”. Sometimes this will not only reduce token costs, but also improve the quality of the text.
6. If you use the short article writing mode, try disabling the “Check for matches when continuing text” option in the “Processing” tab. Or increase the value in the “Match check aggressiveness” parameter.
7. The balance will be spent less if you use English-language requests (set in the “Processing” tab). This does not affect the language of the output text.

Сообщение Слишком быстро расходуется баланс в OpenAI появились сначала на ClipAI.