Clean and deduplicate
Remove duplicate, empty and inconsistent records, and normalize field values.
AI APIOpenAI-compatible · Free after a top-up
Let AI organize the data you collect, free
Accounts that have topped up call the AI API at no charge: clean, deduplicate, classify, extract fields or summarize, in whatever format you need. It is OpenAI-compatible, so changing the base_url is enough.
- $0
- Cost per call after a top-up
- OpenAI
- API format
POST /api/v1/chat/completionsFrom collected results to organized data
01Your results and instructionsOpenAI-compatible · Free after a top-up
02Call the AI APIPOST /api/v1/chat/completions
03Returned in your formatReady to store or analyze
Collect, then organize in the same pipeline
Write the task and the output format into the prompt; the AI API returns results you can store, filter or analyze.
Classify and label
Label each record by sentiment, topic, intent or your own categories.
Extract and summarize
Pull out prices, brands or contact details, or write one-line summaries.
Common uses
Each one is an ordinary chat/completions call; you choose the prompt and the output format.
Keep your SDK, change the base URL
With the OpenAI SDK, set base_url to https://api.everyinfra.com/api/v1 and use your EveryInfra API key.
Free calls, limits by total top-ups
Any account that has topped up can use it, and calls do not use your balance. Requests per minute and requests in flight follow your total top-ups; trial credit and credit codes do not count.
- Price
- Free after a top-up
How it may be used, and its limits
The AI API is for organizing the data you collect with EveryInfra. If it is used for something else, or the calls look clearly abnormal, we may pause the AI API for that account; the account itself, its other APIs and its balance are not affected.
- Topped up, under $100 in total: 50 requests per minute and up to 5 at once
- $100 or more in total: 500 requests per minute and up to 50 at once
- $500 or more in total: 5,000 requests per minute and up to 500 at once
- Trial credit and credit codes do not count toward total top-ups.
- Tiers are ceilings, not guaranteed throughput. Going over a limit returns 429 with Retry-After.
Frequently asked questions
Is the AI API free?
Yes, and it does not use your balance. Any account that has topped up can call it, with limits by total top-ups: 50 requests per minute and up to 5 at once below $100; 500 and 50 from $100; 5,000 and 500 from $500; trial credit and credit codes do not count.
How do I connect?
It is OpenAI-compatible: with the OpenAI SDK, set base_url to https://api.everyinfra.com/api/v1 and use your EveryInfra API key. The chat endpoint is POST /api/v1/chat/completions, and streaming is supported.
What can I use it for?
Organizing the data you collect with EveryInfra: cleaning, deduplicating, classifying, extracting fields, summarizing and translating, in the output format you set in the prompt. If it is used for something else, or the calls look clearly abnormal, we may pause the AI API for that account; the account itself, its other APIs and its balance are not affected.
Can I use it without a top-up?
No. An account that has never topped up gets 403 ai_topup_required; any top-up enables it. Trial credit and credit codes are not top-ups.
What happens over the limit?
When you reach the per-minute limit, or too many requests are in flight, the API returns 429 with Retry-After; wait that many seconds and retry. When the whole service is busy it returns 503, also with Retry-After.
Which models are available?
Two: gemini-3.6-flash, the default, and the lighter gemini-flash-lite. GET /api/v1/models returns the same list and needs no key. A misspelled model returns 422 with the likely correct name.