# Web search API pricing per 1,000 searches

Web search API pricing per 1,000 searches, read 2026-10-13: Perplexity, Brave, Tavily, Exa, Cloudflare and the search built into OpenAI, Claude and Gemini.

## Summary

Web search API pricing in October 2026 differs up to fifteen times between vendors for the same 1,000 searches, and the search built into the big model APIs adds a token bill on top. This post compares Perplexity, Brave, Tavily, Exa, Cloudflare, OpenAI, Anthropic and Gemini, with each price linked to the vendor's own page and read on 2026-10-13.

Two things changed this month. Perplexity moved its Agent API presets to Fast Search at $1.00 per 1,000 ([Perplexity changelog](https://docs.perplexity.ai/changelog), read 2026-10-13), and Cloudflare launched a Web Search API inside AI Gateway with Exa, Linkup and Ceramic as partners ([Cloudflare blog](https://blog.cloudflare.com/introducing-web-search-api/), read 2026-10-13). This post puts the prices in one table, explains why "one search" means different things per vendor, and shows how an agent reads the price before each call.

## Web search API pricing in one table

The table lists the vendor's pay as you go price for 1,000 searches, the unit it bills and what one search returns. Free tiers and plans are left out unless they change the first 1,000 calls.

| API | Per 1,000 searches | What one search returns | Source |
|---|---|---|---|
| Perplexity Search API, Fast Search | $1.00 | Ranked web results | Perplexity pricing, read 2026-10-13 |
| Perplexity Search API, standard | $5.00 | Ranked web results with filters | Perplexity pricing, read 2026-10-13 |
| Brave Search API, Search plan | $5.00, with $5 of free credit a month | Results with extra text for LLMs | Brave Search API, read 2026-10-13 |
| Exa, Instant | $4.00 | Up to 10 results | Exa pricing, read 2026-10-13 |
| Exa, Fast or Auto | $7.00 | Up to 10 results | Exa pricing, read 2026-10-13 |
| Exa, Deep | $12.00 | Up to 10 results | Exa pricing, read 2026-10-13 |
| Exa, Deep-reasoning | $15.00 | Up to 10 results | Exa pricing, read 2026-10-13 |
| Tavily, basic search | $8.00 (1 credit at $0.008) | Results with content | Tavily credits, read 2026-10-13 |
| Tavily, advanced search | $16.00 (2 credits) | Results with more content | Tavily credits, read 2026-10-13 |
| Cloudflare Web Search API | Partner's list price, no markup | The partner's results | Cloudflare blog, read 2026-10-13 |

Tavily gives 1,000 free credits in each calendar month, so the first 1,000 basic searches cost nothing ([Tavily credits](https://docs.tavily.com/documentation/api-credits), read 2026-10-13). Exa bills page text apart from the search, at $1 per 1,000 pages per content type ([Exa pricing](https://exa.ai/pricing), read 2026-10-13). Cloudflare publishes no number of its own: it charges the partner's API price from your AI Gateway credit balance.

## What does the search built into model APIs cost?

The model APIs charge per search and then bill the search results as tokens. So the per 1,000 price is a floor, not the bill.

| Model API tool | Per 1,000 searches | On top | Source |
|---|---|---|---|
| OpenAI web search tool | $10.00 | Search content tokens at model rates | OpenAI pricing, read 2026-10-13 |
| Anthropic web search tool | $10.00 | Search results count as input tokens | Anthropic pricing, read 2026-10-13 |
| Gemini, grounding with Google Search | $14.00 after 5,000 free a month | Paid tier only | Gemini API pricing, read 2026-10-13 |
| Perplexity Agent API, `web_search` tool, standard | $2.50 | Model tokens | Perplexity pricing, read 2026-10-13 |
| Perplexity Agent API, `web_search` tool, Fast Search | $1.00 | Model tokens | Perplexity changelog, read 2026-10-13 |

The token line is the one people miss. Anthropic counts the results of every search as input tokens in that turn and in later turns of the conversation. A search that pulls 5,000 tokens of results can cost more in tokens than the search fee itself, at the model's input rate.

## Why does web search API pricing use different units?

A search is a different unit per vendor, so compare what you get per call, not only the price. There are three kinds of answer.

1. **Results only.** Titles, links and snippets. Perplexity Search API and Brave Search return this, and your agent still has to read the pages.
2. **Results with page text.** Tavily returns content with each result. Exa returns results, and page text is a separate line on the bill.
3. **An answer.** The model API tools search, read and write an answer in one step, and you pay for the tokens that took.

If your agent needs the full text of 5 pages per question, a results-only API plus a page reader can cost less than a search that bundles text, or more. Count both calls before you pick. Reading a page as markdown is its own job, covered on the [URL to markdown API page](https://looot.ai/use-cases/url-to-markdown-api).

## How do you pay per search without a subscription for each vendor?

Call the search providers through one prepaid balance and read the price before each call. That is what looot does for agents: the job `web.search` has several providers behind it, each with its own live price. The table below reads the cheapest price per call from the looot catalog when this page loads. Multiply by 1,000 to compare with the tables above.

Web search through looot, live price per call. Prices read on 2026-10-14 from the live looot catalog. They change when a provider changes its price.

| Option | Cheapest provider | Price per call |
|---|---|---|
| Search the web, cheapest provider | Firecrawl | $0.0010 per call |
| Search the web with Brave | Brave Search | $0.0050 per call |
| Search the web with Exa | Exa | $0.0070 per call |
| Search the web with Tavily | Tavily Search and Extract API | $0.0080 per call |
| Search the web with Linkup | Linkup | $0.0050 per call |

Each provider has a page with its jobs and how to connect it to an agent: [Exa](https://looot.ai/mcp/exa), [Tavily](https://looot.ai/mcp/tavily) and [Linkup](https://looot.ai/mcp/linkup). The job itself, with inputs and output, is on the [web search API page](https://looot.ai/use-cases/web-search-api). If you need Google's own results as rows rather than a web search, that is a SERP API, and its prices are in [SERP API pricing](https://looot.ai/blog/serp-api-cost-reading-the-live-catalog).

This prompt compares the live prices for your own workload without spending anything:

## What this post cannot tell you

- **Search quality.** We compare prices and units, not how good the results are. Run your own questions through two or three providers.
- **Your token bill.** For the model API tools, the search fee is a floor. Tokens depend on the model and how many results it reads.
- **Volume discounts.** Several vendors sell plans and enterprise prices. We list only the pay as you go price each vendor publishes.
- **Cloudflare's numbers.** Cloudflare charges each partner's list price and publishes no table of its own in the launch post.
- **Scheduled searches.** Running the same search on a timer needs scheduled runs, not available yet in looot.

Last checked 2026-10-13. Vendor prices were read that day from the pages linked in each row. looot prices in the live table are read from the catalog when the page loads. We will re-read every vendor price within 92 days.

## Questions

### What is the cheapest web search API?

On published pay as you go prices, Perplexity's Fast Search at $1.00 per 1,000 requests was the lowest we found ([Perplexity pricing](https://docs.perplexity.ai/getting-started/pricing), read 2026-10-13). It returns results only, so add the cost of reading pages if your agent needs the text.

### How does web search API pricing compare with the search built into model APIs?

The model API tools cost $10.00 to $14.00 per 1,000 searches before tokens ([OpenAI pricing](https://developers.openai.com/api/docs/pricing) and [Gemini API pricing](https://ai.google.dev/gemini-api/docs/pricing), read 2026-10-13), against $1.00 to $15.00 for the search APIs ([Perplexity pricing](https://docs.perplexity.ai/getting-started/pricing) and [Exa pricing](https://exa.ai/pricing), read 2026-10-13). The model tools also write an answer, and the results they read are billed as tokens.

### How much does the Brave search API cost?

The Search plan is $5.00 per 1,000 requests, and Brave adds $5 of free credit in each calendar month ([Brave Search API](https://brave.com/search/api/), read 2026-10-13). The Answers plan is billed apart, per request plus tokens.

### Exa vs Tavily: which costs less per search?

For a plain search, Exa Instant at $4.00 per 1,000 costs less than Tavily basic at $8.00 per 1,000 ([Exa pricing](https://exa.ai/pricing) and [Tavily credits](https://docs.tavily.com/documentation/api-credits), read 2026-10-13). Tavily includes content with results and gives 1,000 free credits a month, so the answer depends on volume and on whether you need the page text.

### What does Cloudflare's web search API cost?

Cloudflare charges the partner's list API price with no markup, from your AI Gateway credit balance. The launch post names Exa, Linkup and Ceramic as partners and gives no price table of its own.

### Can I use a web search API without a separate account for each vendor?

Yes. Through looot your agent calls the `web.search` job on several providers with one prepaid balance and reads each price before the call runs. It cannot use your own volume plan with a vendor.

### Should I call the search vendor directly?

Call the vendor directly if you use one provider at high volume and can sign its plan. A gateway helps when your agent needs more than one provider, or other data jobs, on one balance and one key.

## For agents

### Compare web search API pricing for my workload

```text
Use looot to compare web search prices for my agent before I pick a provider. First set up https://looot.ai/skill.md. Inspect the job web.search and list each provider with its price per call and what one call returns (results only, or results with page text). Then estimate the cost of 1,000 searches a day for 30 days with the cheapest provider and with the provider that returns page text. Do not run any paid call.
```