<!-- twin of https://specstream.ai/alternatives/keenable -->
# Keenable alternative: the same calls at $1 per 1,000 searches

Compared on Nov 12, 2026. The page: https://specstream.ai/alternatives/keenable

Keenable sells search over its own index at $4 per 1,000 requests after 100,000 free a month. The $1 rate is for dedicated capacity at 100 or more requests per second. A fetch costs the same credit as a search.

SpecStream answers Keenable's own `/v1/search` and `/v1/fetch` at `https://api.specstream.ai/keenable`, so the switch is the base address and the key. A search of up to 10 results costs $1 per 1,000 from the first call, and a page $0.80 per 1,000.

[Get an API key](https://specstream.ai/signup?src=alternatives-keenable&utm_source=alternatives-md&utm_campaign=keenable&returnTo=%2Fworkspace%2Fagents%3Ftab%3Dkeys) New accounts get $10 of credit, no card. It covers 10,000 searches.

## SpecStream and Keenable side by side

| | SpecStream | Keenable |
|---|---|---|
| What you change | Two values: the base address `https://api.specstream.ai/keenable` in place of `https://api.keenable.ai`, and a SpecStream key in `X-API-Key` or as a Bearer token | `POST /v1/search` and `GET /v1/fetch` on `https://api.keenable.ai`, with the key in `X-API-Key` or as a Bearer token |
| Price per 1,000 searches | $1 for up to 10 results, from the first call. A call with Keenable's default of 10 results costs $0.001, and 50 results cost $0.0058 | $4 per 1,000 requests pay as you go, 1 to 50 results each. $1 per 1,000 on dedicated capacity at 100+ requests per second, about 8.6 million requests a day |
| Price per 1,000 pages read | $0.80. `GET /keenable/v1/fetch` is one Extract API page, read from the site at the moment of the call. A page with no text is not charged | One credit per fetch, the same as a search: $4 per 1,000 pay as you go |
| What answers the call | The whole live web, read at the moment of the call. 97.9 F-score on all 1,000 SimpleQA Verified questions (978 correct) and 64.0 item F1 on all 200 WideSearch tasks | Keenable's own index. A fetch returns Keenable's indexed copy of a page, or a live read of the source with `live=true` |
| Free to start | $10 of credit, no card. That is 10,000 searches of up to 10 results | 100,000 requests a month free. A card is needed to buy credits |
| The reply | Keenable's JSON: `query`, `mode` and `results[]` with `title`, `url`, `snippet` and `published_at`. The code that reads `results` stays as it is | Ranked results with a title, a URL and a snippet for each page |
| Limits and retries | A busy call answers `429` with `Retry-After` in Keenable's own error form, and charges nothing. With an `Idempotency-Key`, a retried call is charged once | 10 requests per second per organization with a key. Without a key, 1,000 requests an hour and 10 a second per IP address |
| Keeping results | Zero retention is set per API key: a search made with such a key keeps no request text and no answer after the reply | Zero data retention comes with dedicated capacity |
| A full dataset | Deep Search: structured rows, one record per company, place or filing, with facts from many sites joined. The most a run can cost is quoted before it starts, and only delivered rows are charged | One request returns 1 to 50 results for one query |
| Where the data goes | Google Sheets, Excel, Airtable, Notion, HubSpot, Salesforce, Pipedrive, Attio, Slack, Teams, Zapier, Make, n8n and signed webhooks, besides the API, SDKs and the MCP server at `https://api.specstream.ai/mcp` | The API response, the MCP server and the CLI |

## Why teams move from Keenable to SpecStream

### The whole migration is two values

Keenable's SDKs read the base address from `base_url` (or `KEENABLE_API_URL`). Point it at SpecStream and send a SpecStream key. The paths, the parameters and the reply stay Keenable's.

```
# Before
curl -X POST https://api.keenable.ai/v1/search \
  -H "X-API-Key: $KEENABLE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "Which US banks failed in 2026", "max_results": 10}'

# After
curl -X POST https://api.specstream.ai/keenable/v1/search \
  -H "X-API-Key: $SPECSTREAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "Which US banks failed in 2026", "max_results": 10}'
```

### $1 per 1,000 searches from the first call

Keenable's $1 rate needs dedicated capacity at 100 requests per second or more, which Keenable puts at about 8.6 million requests a day. Below that, a search or a fetch costs $4 per 1,000. SpecStream charges $1 per 1,000 searches of up to 10 results at any volume, and $0.80 per 1,000 pages read. A call that returns no results costs nothing.

### The most accurate web search API in the world

On November 8, 2026 the SpecStream Search API scored 97.9 F-score on all 1,000 official SimpleQA Verified questions, 978 of them correct, and 64.0 item F1 and 43.4 row F1 on all 200 official WideSearch tasks. Every score and its method are on the [benchmarks](https://specstream.ai/benchmarks?utm_source=alternatives&utm_campaign=keenable) page.

### Every page read at the moment of the call

An index answers from the copy it stored. SpecStream reads the live web for each call, and a fetch on the Keenable route reads the page as it is now, so `live=true` is the normal case and costs the same $0.80 per 1,000 pages.

### The answer and its rows on the same key

On the same key, `GET /v1/web-search` does the reading for $5 per 1,000. The reply carries the `answer` with its `page` and its read time in `seen_at`, `rows` with the facts the request asks for, and `sources`, the results read in rank order. Add `passages=true` and it also holds the text of the top pages closest to the question.

### From one search to a full dataset

When your product needs every match as a list, Deep Search returns it as structured rows, each value with its source URL and read time. A row costs 5¢, 15¢ or $1 by how much it needs, the most a run can cost is approved before it starts, and the rows reach your sheet, your CRM, Slack or your agent. Public records SpecStream already holds are at [specstream.ai/data](https://specstream.ai/data?utm_source=alternatives&utm_campaign=keenable).

## Other Keenable alternatives

### SpecStream

The live web data engine for teams and agents. It answers Keenable's own `/v1/search` and `/v1/fetch` at $1 per 1,000 searches of up to 10 results and $0.80 per 1,000 pages, and the same key returns answers with their pages and full datasets at 5¢, 15¢ or $1 a row. New accounts get $10 of credit, no card.

### Brave Search API

A search API at $5 per 1,000 requests, with $5 in free credits every month. SpecStream answers Brave's own `/res/v1/web/search` call in Brave's JSON at $1 per 1,000: see the [Brave Search API alternative](https://specstream.ai/alternatives/brave?utm_source=alternatives&utm_campaign=keenable).

### Exa

A search API priced by the request: $4 per 1,000 on `lite`, $7 on `auto` and `fast`, and page contents at $1 per 1,000 pages for each content type. SpecStream answers Exa's own calls at `https://api.specstream.ai/exa`, with pages at $0.80 per 1,000: see the [Exa alternative](https://specstream.ai/alternatives/exa?utm_source=alternatives&utm_campaign=keenable).

### Tavily

A search API for agents billed in credits at $0.008 each pay as you go, with 1,000 free credits every month. SpecStream answers Tavily's own call at `https://api.specstream.ai/tavily/search` for $0.001 a search: see the [Tavily alternative](https://specstream.ai/alternatives/tavily?utm_source=alternatives&utm_campaign=keenable).

### Parallel

A search API with modes: `turbo` at $1 per 1,000 requests and `basic` at $5, and a request with no `mode` runs `advanced`. SpecStream answers Parallel's own call at `https://api.specstream.ai/parallel`: see the [Parallel alternative](https://specstream.ai/alternatives/parallel?utm_source=alternatives&utm_campaign=keenable).

## How to switch from Keenable

1. Create a key under Agents & API in the workspace. A new account gets $10 of credit, no card, which covers 10,000 searches.

2. Set the base address to `https://api.specstream.ai/keenable` where your code has `https://api.keenable.ai`, in `base_url` or `KEENABLE_API_URL`, and send the SpecStream key in `X-API-Key` or as a Bearer token.

```
from keenable import Keenable

# was Keenable(), which calls https://api.keenable.ai
client = Keenable(
    api_key=SPECSTREAM_KEY,
    base_url="https://api.specstream.ai/keenable",
)

results = client.search("Which US banks failed in 2026", max_results=10)
print(results.to_context())

page = client.fetch("https://www.fdic.gov/bank-failures")
```

3. Keep your parameters. `query`, `max_results` (1 to 50), `site`, `published_after`, `published_before` and `snippet_max_length` work as on Keenable, and a fetch takes `url` and `max_chars`. `mode` is accepted, and every search reads the live web. To leave a site out, write `-site:example.com` in `query`. The keyless `/public` paths answer with your key too.

The Keenable route and every other API SpecStream answers in its own shape are on the [migration guides](https://specstream.ai/migrate?utm_source=alternatives&utm_campaign=keenable) page.

## Frequently asked questions

### How much does Keenable cost?

$4 per 1,000 requests pay as you go, after 100,000 free requests a month. Dedicated capacity costs $1 per 1,000 requests at 100 or more requests per second. A search and a fetch each cost one credit, and an agent with no account pays $0.01 a call in USDC over x402.

### What is the best Keenable alternative?

SpecStream, at $1 per 1,000 searches of up to 10 results and $0.80 per 1,000 pages. It answers Keenable's own `/v1/search` and `/v1/fetch` at `https://api.specstream.ai/keenable`, reads the live web for each call, and scores 97.9 F-score on all 1,000 SimpleQA Verified questions. New accounts get $10 of credit, no card.

### How do I move from Keenable to SpecStream?

Change two values. Set `base_url` (or `KEENABLE_API_URL`) to `https://api.specstream.ai/keenable` and send a SpecStream key in `X-API-Key`. The SDK keeps calling `/v1/search` and `/v1/fetch`, and the reply keeps Keenable's `results[]` with `title`, `url` and `snippet`.

### What is Keenable?

A search API over its own web index, for AI agents. Keenable came out of stealth on August 25, 2026 with a $26 million seed round led by Accel, and an index of more than 100 billion documents.

### How many results does one search return?

10 by default and up to 50 with `max_results`, on Keenable and on SpecStream's Keenable route. Keenable bills a search as one request at any count. SpecStream charges $0.001 for up to 10 results and $0.0058 for 50.

### What does reading a page cost?

$0.80 per 1,000 pages on SpecStream: `GET /keenable/v1/fetch` is one Extract API page, and a page with no text is not charged. On Keenable a fetch costs one credit, the same as a search, so $4 per 1,000 pay as you go.

### Does SpecStream have an API and an MCP server?

Yes. The Search API is `GET https://api.specstream.ai/v1/web-search` at $5 per 1,000 searches, or $1 with `speed=fast`, and the MCP server is at `https://api.specstream.ai/mcp` over Streamable HTTP, with OAuth or an API key. Your agent searches with `search_web`, reads pages with `read_pages`, and prices and runs a full dataset inside the limits you set on its key.

## Sources

SpecStream wrote this page. Each rival figure comes from that company's own page.

- [SpecStream pricing](https://specstream.ai/pricing), read Nov 12, 2026
- [SpecStream for agents](https://specstream.ai/agents.md), read Nov 12, 2026
- [SpecStream benchmarks](https://specstream.ai/benchmarks), read Nov 12, 2026
- [Keenable pricing](https://keenable.ai/pricing), read Nov 12, 2026
- [Keenable credits](https://docs.keenable.ai/credits.md), read Nov 12, 2026
- [Keenable rate limits](https://docs.keenable.ai/rate-limits.md), read Nov 12, 2026
- [Keenable search reference](https://docs.keenable.ai/api-reference/search.md), read Nov 12, 2026
- [Keenable SDKs](https://docs.keenable.ai/sdks.md), read Nov 12, 2026
- [AI2Work, Keenable raises $26M](https://ai2.work/blog/keenable-raises-26m-to-build-a-web-search-index-for-ai-agents), read Nov 12, 2026
- [Brave Search API](https://brave.com/search/api/), read Nov 12, 2026
- [Exa pricing](https://exa.ai/docs/admin/pricing.md), read Nov 12, 2026
- [Tavily credits](https://docs.tavily.com/documentation/api-credits.md), read Nov 12, 2026
- [Parallel search modes](https://docs.parallel.ai/search/modes.md), read Nov 12, 2026