> SpecStream is the live web data engine for teams and agents. This is the Markdown copy of https://specstream.ai/blog/dzhng-deep-research-firecrawl-base-url. Every page, with what SpecStream does and costs: https://specstream.ai/llms.txt

# dzhng/deep-research without a Firecrawl key: set FIRECRAWL\_BASE\_URL

SpecStream

[Search API](https://specstream.ai/blog.md) · Nov 12, 2026 · 4 min read

[dzhng/deep-research](https://github.com/dzhng/deep-research) does all of its web work through one call: a Firecrawl search that also returns each result's page as Markdown. The address of that call is a setting, `FIRECRAWL_BASE_URL`. SpecStream answers Firecrawl's v1 search at `https://api.specstream.ai/firecrawl`, so the switch is two lines in `.env.local`:

```bash
FIRECRAWL_KEY="YOUR_SPECSTREAM_API_KEY"
FIRECRAWL_BASE_URL="https://api.specstream.ai/firecrawl"
```

No file in `src` changes, and there is no Firecrawl server to run. The rest of this post shows where the call sits, what comes back, and what a run costs.

## Where Firecrawl sits in the code

`src/deep-research.ts` builds one Firecrawl client from two environment variables:

```ts
const firecrawl = new FirecrawlApp({
  apiKey: process.env.FIRECRAWL_KEY ?? '',
  apiUrl: process.env.FIRECRAWL_BASE_URL,
});
```

Each search query the model writes becomes one call:

```ts
const result = await firecrawl.search(serpQuery.query, {
  timeout: 15000,
  limit: 5,
  scrapeOptions: { formats: ['markdown'] },
});
```

The lock file pins `@mendable/firecrawl-js` 1.16.0. That version of the SDK posts to the address it is given followed by `/v1/search`, and sends the key as `Authorization: Bearer`. With the two lines above, every search goes to `https://api.specstream.ai/firecrawl/v1/search` with your SpecStream key. The code never calls Firecrawl's scrape, map or crawl, so the search is the only call to move.

## Set it up

1.  In your SpecStream workspace, open [Agents & API](https://specstream.ai/workspace/agents?tab=keys&utm_source=blog&utm_campaign=dzhng-deep-research), choose **API keys**, then **Create API key**, and set a total limit. New accounts start with $10 of credit, no card.
2.  Put the two lines in `.env.local` in the repository root, next to `OPENAI_KEY`. `npm start` runs `tsx --env-file=.env.local src/run.ts`, so that is the file it reads. With Docker, `docker-compose.yml` reads the same file through `env_file`.
3.  Run `npm start`, type the question, and answer the breadth and depth prompts. The report lands in `report.md`, with the pages the searches found listed under its sources.

To check the address and the key before a run, send the same call the SDK sends. It makes one search on your key:

```bash
curl -s https://api.specstream.ai/firecrawl/v1/search \
  -H "Authorization: Bearer $SPECSTREAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "open source deep research agents", "limit": 5, "scrapeOptions": {"formats": ["markdown"]}}'
```

## What comes back

The reply is in Firecrawl's v1 shape, so `processSerpResult` reads it as it is:

| Field the code reads | What SpecStream puts there |
| --- | --- |
| `data[].url` | The result's address |
| `data[].markdown` | The part of the page closest to the query, up to about 3,500 characters |
| `data[].title`, `description` | The result's title and snippet |
| `data[].metadata` | `title`, `sourceURL`, and `publishedTime` when the page has a date |

The code keeps each result's `markdown` and trims it to 25,000 tokens before the model reads it. SpecStream sends the passages of the page closest to the query, not the whole page, so the model reads less text for each result.

## How many searches a run makes, and the price

A run searches in levels. The first level writes up to `breadth` queries. Each query then starts a level of its own with half the breadth, rounded up, until `depth` runs out. That gives these counts at most:

| How you start it | Defaults | Searches at most |
| --- | --- | --- |
| `npm start` | breadth 4, depth 2 | 4 + 8 = 12 |
| `npm run api`, `POST /api/research` | breadth 3, depth 3 | 3 + 6 + 6 = 15 |

Each Firecrawl search on the SpecStream address is one Search API call on the fast tier: $0.001 for up to 10 results, $1 per 1,000. The code asks for 5 results, so every call is the base price, and the page text comes with it at no extra charge. A default CLI run costs at most $0.012 in searches and a default API run at most $0.015. A call that returns no results costs nothing. The model calls stay on your OpenAI, Fireworks or other model bill. Every call comes out of your balance with no quote and no approval, and each one is listed on the Search API screen of your workspace.

The same key reaches the [Search API](https://specstream.ai/search-api.md) directly, at $5 per 1,000 searches on the default tier, and the [Extract API](https://specstream.ai/extract-api.md) at $0.80 per 1,000 pages, where a page with no text is not charged. On accuracy, the Search API scores 97.9 F-score on all 1,000 SimpleQA Verified questions and 64.0 item F1 on all 200 WideSearch tasks ([benchmarks](https://specstream.ai/benchmarks.md)).

## Concurrency: the variable the code reads

The README says to raise `CONCURRENCY_LIMIT` on a paid plan. The code reads a different name:

```ts
const ConcurrencyLimit = Number(process.env.FIRECRAWL_CONCURRENCY) || 2;
```

To run more searches at once, set `FIRECRAWL_CONCURRENCY` in `.env.local`. `CONCURRENCY_LIMIT` changes nothing.

## Going back

Delete `FIRECRAWL_BASE_URL` and put your Firecrawl key back in `FIRECRAWL_KEY`. The SDK then calls `https://api.firecrawl.dev` again. To stop the SpecStream key working everywhere, revoke it in **Agents & API**.

If what you need from the run is a list rather than a report, such as every company or paper that meets your conditions with a source on each value, compare [deep research APIs](https://specstream.ai/deep-research-api.md) first.

## More from the blog

[Every post](https://specstream.ai/blog.md)

[![Google's Custom Search API ends January 1, 2027: 16 open-source AI apps still call it](https://specstream.ai/blog/covers/google-custom-search-api-ends-open-source-apps.jpg) ### Google's Custom Search API ends January 1, 2027: 16 open-source AI apps still call it On November 11, 2026, 51 days before Google ends the Custom Search JSON API, all 16 open-source AI apps that call it still hold Google's address in their code Nov 11, 2026 · SpecStream · 6 min read](https://specstream.ai/blog/google-custom-search-api-ends-open-source-apps.md)[### MyVisaJobs H-1B sponsor counts, checked against the Department of Labor files MyVisaJobs ranks its 2026 H-1B sponsors on fiscal 2025 filings Nov 12, 2026 · SpecStream · 5 min read](https://specstream.ai/blog/myvisajobs-h1b-sponsor-counts.md)[![Alabama WARN notices 2026: 31 layoffs, 2,717 workers so far](https://specstream.ai/blog/covers/alabama-warn-layoff-notices-2026.jpg) ### Alabama WARN notices 2026: 31 layoffs, 2,717 workers so far Alabama has 31 WARN notices for 2,717 workers in 2026, the latest filed November 2 Nov 10, 2026 · SpecStream · 3 min read](https://specstream.ai/blog/alabama-warn-layoff-notices-2026.md)