Skip to the page

Render

Give any Render service live web search and page reading. Store your SpecStream API key as an environment variable on the service, and your code calls the Search API and the Extract API over HTTPS, in any language Render runs.

SpecStream for Render, API & cloud platforms

What you need

  • A Render web service, private service, background worker or cron job.
  • A SpecStream account. New accounts start with $10 of credit, no card. Create one.
  • A SpecStream API key with a spending limit, which step 1 creates.
  1. 1. Create an API key

    In your SpecStream workspace, open Agents & API, choose API keys, then Create API key. Turn on Authorize paid work: a key without it can't search or read pages. Set a Total spending limit above $0, because that limit is what caps the spending of everything that uses the key.

    Copy the key when it's shown. It isn't shown again.

  2. 2. Add the key to your service

    In the Render Dashboard (opens in a new tab), select your service and click Environment in the left pane. Under Environment Variables, click + Add Environment Variable. Enter SPECSTREAM_API_KEY as the Key and paste your SpecStream key as the Value.

    Save with Save, rebuild, and deploy or Save and deploy. With Save only, the service reads the key at its next deploy. To share one key across several services, put it in an Environment Group and link the group to each service.

  3. 3. Or declare it in render.yaml

    If you deploy from a Blueprint, declare the variable with sync: false. Render asks for its value in the Dashboard when you create the Blueprint, so the key never goes into your repository:

    render.yaml
    services:
    - type: web
    name: my-app
    runtime: node
    buildCommand: npm install
    startCommand: node server.js
    envVars:
    - key: SPECSTREAM_API_KEY
    sync: false
  4. 4. Search from your code

    Send the question in q, in everyday words, with the key as a Bearer token. The reply's data.answer.value holds a short answer when the pages give one, and data.sources lists each page with its title, url and snippet:

    server.js
    const q = "Which regions does Render offer for web services?";
    const res = await fetch(
    `https://api.specstream.ai/v1/web-search?q=${encodeURIComponent(q)}`,
    { headers: { Authorization: `Bearer ${process.env.SPECSTREAM_API_KEY}` } },
    );
    if (!res.ok) throw new Error(`SpecStream answered ${res.status}`);
    const { data } = await res.json();
    console.log(data.answer?.value);
    for (const source of data.sources) console.log(source.title, source.url);
  5. 5. Read the pages you need

    POST /v1/extract returns the main text of 1 to 20 pages or documents in one call. Each item of data.results has the page's url, a status, and its text when the status is ok. In Python, with requests:

    worker.py
    import os
    import requests
    res = requests.post(
    "https://api.specstream.ai/v1/extract",
    headers={"Authorization": f"Bearer {os.environ['SPECSTREAM_API_KEY']}"},
    json={"urls": ["https://render.com/docs/cronjobs"], "format": "markdown"},
    timeout=60,
    )
    res.raise_for_status()
    for page in res.json()["data"]["results"]:
    if page["status"] == "ok":
    print(page["url"], page["text"][:500])

Run a search on a schedule

Create a Cron Job in the Render Dashboard with a schedule such as 0 12 * * * (every day at noon UTC) and a command that runs your script, then add SPECSTREAM_API_KEY to its Environment as in step 2. Each run spends from the same balance, and the key's spending limit is the ceiling for all of them.

An agent on Render

If your service runs an agent with an MCP client, connect it to https://api.specstream.ai/mcp over Streamable HTTP and send Authorization: Bearer with the value of SPECSTREAM_API_KEY. The agent gets these tools:

ToolWhat it doesCost
search_webSearches the live web with {"q": "<the question>"} and returns up to 10 results, each with its page.$5 per 1,000 searches
read_pagesReturns the main text of 1 to 20 pages or documents (PDF, Word, Excel), read live, or from SpecStream's own dated copy when a page is slow or refuses, with {"urls": [...]}.$0.80 per 1,000 pages
compile, quote_capacity_work, authorize_capacity_workDeep Search: reads a request in plain words, prices it, and starts it after a maximum is approved. Rows come back with list_find_rows.5¢, 15¢ or $1 a delivered row, plus 5¢ for a person's email and 15¢ for a phone

Errors

  • 401: the key is missing or wrong. Send it as Authorization: Bearer <key>.
  • 403: the key has no Authorize paid work, or the call would go over the key's spending limit.
  • 402: the balance is empty, or the call would go over the account's monthly spending limit.
  • 503 with Retry-After: wait that many seconds and send it again.

Cost

A search is $5 per 1,000 searches of up to 10 results, or $1 per 1,000 with speed=fast. A page read is $0.80 per 1,000 pages. Neither needs a quote or an approval, so they come out of your balance up to the key's spending limit. Render bills the service itself as usual. Balance, quotes, and billing has the details.

Remove

Delete SPECSTREAM_API_KEY on the service's Environment page and deploy again. To stop the key working everywhere, revoke it under API keys in Agents & API. Results already delivered stay in your workspace. Questions go to [email protected].

More

SpecStream for Render covers what it does in Render on one page. Every other tool has its guide in Connect your tools. You see the most a request can cost before it starts, and the matches are paid from your balance. Billing has the details. For help, email [email protected].