<!-- twin of https://specstream.ai/web-search/vertex-ai -->
# Vertex AI grounding with your search API: live web at $1 per 1,000

Compared on Nov 12, 2026. The page: https://specstream.ai/web-search/vertex-ai

Grounding with Google Search on Vertex AI, now Gemini Enterprise Agent Platform, costs $14 per 1,000 grounding queries past 5,000 free a month. Grounding with your search API takes any endpoint that answers Google's `SIMPLE_SEARCH` schema.

SpecStream answers that schema at `https://api.specstream.ai/vertex/search`. Set it as the `endpoint` of `externalApi` and your SpecStream key as `apiKeyString`. Gemini grounds in the live web at $1 per 1,000 searches, with no gateway to deploy.

SpecStream is the live web data engine for teams and agents. Its Search API scores 97.9 F-score on all 1,000 SimpleQA Verified questions. A new account gets $10 of credit, no card, which covers 10,000 searches.

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

## Web grounding sources for Gemini on Vertex AI, from each company's own pages on Nov 12, 2026

| | SpecStream | Grounding with Google Search | Web Grounding for Enterprise | Grounding with Parallel | Grounding with Exa |
|---|---|---|---|---|---|
| Price per 1,000 | $1 per 1,000 searches of up to 10 results | $14 per 1,000 grounding queries on Gemini 3 and Gemini 4. $35 per 1,000 grounding prompts on Gemini 2.0 and 2.5 | $14 per 1,000 grounding queries, on the same price line as Google Search | From $1 per 1,000 requests on Parallel's Search API | $7 per 1,000 `auto` searches on Exa's API |
| Free to start | $10 of credit, no card, which covers 10,000 searches | 5,000 grounding queries a month | 5,000 grounding queries a month, counted with Google Search | Up to $80 at sign up and $5 a month on Parallel's own plans | $10 in credits on sign up, up to 2,500 Lite searches |
| Who bills you | SpecStream, from a prepaid balance that never expires | Google, on your Cloud bill | Google, on your Cloud bill | Google Cloud Marketplace, or Parallel on your own Parallel key | Exa, on your own Exa key |
| How you connect | `externalApi` with `api_spec` `SIMPLE_SEARCH`, `https://api.specstream.ai/vertex/search` as `endpoint` and your key as `apiKeyString` | A grounding tool built into the Gemini request | A grounding tool built into the Gemini request | Subscribe on Google Cloud Marketplace, or bring your own Parallel API key | Get an API key from Exa's site and put it in the request |
| What answers the search | The whole live web, read at the moment of the call. 97.9 F-score on all 1,000 SimpleQA Verified questions, 978 correct | Google's web index | A web index for highly regulated industries, with compliance controls | Parallel's search API over billions of web pages | Exa's search API |
| When a search is billed | Each search. A call stopped by a `429` is not charged | Only when a grounding prompt returns at least one source URL | Only when a grounding prompt returns at least one source URL | Per request on Parallel's price list | Per request. The base price covers the first 10 results |

## Why Vertex AI users ground Gemini with SpecStream

### One tool block, and nothing to deploy

Google's guide to grounding with your search API has you build an endpoint and put it behind API Gateway. SpecStream is that endpoint already, for the whole live web. Add one `retrieval` tool to the request and keep the rest of your code.

```
# pip install --upgrade google-genai
# export GOOGLE_CLOUD_PROJECT=your-project GOOGLE_CLOUD_LOCATION=global GOOGLE_GENAI_USE_ENTERPRISE=True
import os
from google import genai
from google.genai.types import ExternalApi, GenerateContentConfig, HttpOptions, Retrieval, Tool

client = genai.Client(http_options=HttpOptions(api_version="v1"))

specstream = Tool(
    retrieval=Retrieval(
        external_api=ExternalApi(
            api_spec="SIMPLE_SEARCH",
            endpoint="https://api.specstream.ai/vertex/search",
            api_auth={"apiKeyConfig": {"apiKeyString": os.environ["SPECSTREAM_API_KEY"]}},
        )
    )
)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Who won the most recent Formula 1 race?",
    config=GenerateContentConfig(tools=[specstream]),
)
print(response.text)
```

The same tool in a REST request to `generateContent`:

```
{
  "contents": [{"role": "user", "parts": [{"text": "Who won the most recent Formula 1 race?"}]}],
  "tools": [{
    "retrieval": {
      "externalApi": {
        "api_spec": "SIMPLE_SEARCH",
        "endpoint": "https://api.specstream.ai/vertex/search",
        "apiAuth": {"apiKeyConfig": {"apiKeyString": "YOUR_SPECSTREAM_KEY"}}
      }
    }
  }]
}
```

### The call Gemini sends, and what comes back

Gemini sends `POST` with the JSON body `{"query": "..."}` and adds your key to the address as `?key=`. SpecStream answers with the JSON array Google's schema asks for: one object per result, each with `snippet` and `uri`, and an empty array when nothing matches. Each call returns up to 10 results. Errors come back in Google's error form.

```
# The call Gemini sends: the query in the body, your key as key= in the address
curl "https://api.specstream.ai/vertex/search?key=$SPECSTREAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "who won the most recent Formula 1 race"}'

# [{"snippet": "...", "uri": "https://..."}, ...]
```

### $1 per 1,000 searches, on every Gemini model

Each search Gemini makes through this endpoint costs $0.001. Grounding with Google Search costs $14 per 1,000 grounding queries on Gemini 3 and Gemini 4 past 5,000 free a month, and $35 per 1,000 grounding prompts on Gemini 2.0 and 2.5. SpecStream bills from a prepaid balance that never expires, and a new account starts with $10 of credit.

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

On SimpleQA Verified the SpecStream Search API scores 97.9 F-score on all 1,000 official questions, 978 of them correct. On WideSearch it scores 64.0 item F1 and 43.4 row F1 on all 200 official tasks. The Extract API scores 0.908 F1 on WCXB. Every score and its method is on the [benchmarks](https://specstream.ai/benchmarks?utm_source=alternatives&utm_campaign=web-search-vertex-ai) page.

### Use it beside Google Search or your own data

A generation request takes up to 10 grounding sources. Keep Grounding with Google Search, Vertex AI Search or Elasticsearch where they serve you, and add SpecStream as one more `retrieval` tool for the live web.

### You decide what is kept, on each key

Give Gemini a key with `zero_retention` and a search made with it keeps no request text and no answer after the reply. It is not in the history and its log lines carry neither. The charge keeps the account, the key, the request ID, the price and the time. `spend_cap_cents` is the most the key can spend.

```
curl -X POST https://api.specstream.ai/v1/account/keys \
  -H "Authorization: Bearer $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"name": "vertex-grounding", "scopes": ["account:read", "finds:spend"], "spend_cap_cents": 500000, "zero_retention": true}'
```

### Search, pages and rows on one key

The same key reads up to 20 pages or documents a call with the [Extract API](https://specstream.ai/extract-api?utm_source=alternatives&utm_campaign=web-search-vertex-ai) at $0.80 per 1,000 pages, and a page with no text is not charged. [Deep Search](https://specstream.ai/deep-search?utm_source=alternatives&utm_campaign=web-search-vertex-ai) takes a request in plain words and returns every match on the live web as structured rows, at 5¢, 15¢ or $1 a row, with a source URL on every value.

## The other web grounding sources on Vertex AI, and what each costs

### Grounding with Google Search

Google's own index, built into Gemini. $14 per 1,000 grounding queries on Gemini 3 and Gemini 4 after 5,000 free a month, billed only when a prompt returns a source. SpecStream grounds the same models at $1 per 1,000 searches. More on the [Grounding with Google Search alternative](https://specstream.ai/grounding-with-google-search-alternative?utm_source=alternatives&utm_campaign=web-search-vertex-ai) page.

### Web Grounding for Enterprise

A web index Google offers to highly regulated industries, with compliance controls, on the same $14 per 1,000 price line as Google Search. SpecStream keeps nothing from a search made with a `zero_retention` key and costs $1 per 1,000.

### Grounding with Parallel

Parallel's search API, sold on Google Cloud Marketplace or on your own Parallel key, from $1 per 1,000 requests. SpecStream costs $1 per 1,000 searches through any project that can call an endpoint, and scores 97.9 F-score on SimpleQA Verified.

### Grounding with Exa

Exa's search API on your own Exa key, at $7 per 1,000 `auto` searches. SpecStream costs $1 per 1,000 searches and reads the live web at the moment of the call.

## How to ground Gemini on Vertex AI with SpecStream

1. Create a key under Agents & API in the SpecStream workspace. A new account gets $10 of credit, no card, which covers 10,000 searches. Turn on `zero_retention` on the key if your searches must leave no trace.

2. Check the key from a terminal with the call Gemini sends. A `200` with a JSON array of `snippet` and `uri` means Gemini will get the same.

```
curl "https://api.specstream.ai/vertex/search?key=$SPECSTREAM_API_KEY" -H "Content-Type: application/json" -d '{"query": "test"}'
```

3. In your Gemini request, add a `retrieval` tool with `externalApi`: `api_spec` set to `SIMPLE_SEARCH`, `endpoint` set to the address below, and your key in `apiAuth.apiKeyConfig.apiKeyString`.

```
https://api.specstream.ai/vertex/search
```

4. Send a question about something that happened today. The answer's `groundingMetadata` lists the `uri` of each result Gemini used.

5. Each search shows up in your SpecStream request log with its price.

## Frequently asked questions

### How do I ground Gemini on Vertex AI with my own search API?

Add a `retrieval` tool with `externalApi`, `api_spec` `SIMPLE_SEARCH`, your endpoint and your key as `apiKeyString`. With `https://api.specstream.ai/vertex/search` as the endpoint, each search costs $0.001.

### How much does Grounding with Google Search cost on Vertex AI?

$14 per 1,000 grounding queries on Gemini 3 and Gemini 4 after 5,000 free a month, and $35 per 1,000 grounding prompts on Gemini 2.0 and 2.5 past the free daily prompts. SpecStream costs $1 per 1,000 searches on every supported model.

### What must a search API return for Vertex AI grounding?

A JSON array of objects, each with `snippet` and `uri`, and an empty array when nothing matches. Gemini sends `POST` with `{"query": "..."}` and the key as `key=` in the address. SpecStream answers in exactly that form.

### Do I need API Gateway or Cloud Run to use grounding with my search API?

No. Google's guide sets up API Gateway for a search you host yourself. SpecStream's endpoint is public and checks the `key` Gemini adds, so there is nothing to deploy.

### Can I use SpecStream and Google Search grounding together?

Yes. A Gemini request takes up to 10 grounding sources, so SpecStream can sit beside Grounding with Google Search, Vertex AI Search or Elasticsearch in the same request.

### Which Gemini models support grounding with your search API?

Google's grounding page lists models from Gemini 2.5 Flash and Gemini 2.5 Pro to Gemini 3.1 Pro, Gemini 3.8 Flash and Gemini 4 Carbon. SpecStream answers every one of them at the same $1 per 1,000 searches.

## Sources

SpecStream wrote this page. The setup comes from Google's grounding docs, and each provider's figure from that company's own page.

- [Google Cloud, Grounding with your search API](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/grounding/grounding-with-your-search-api), read Nov 12, 2026
- [Google Cloud, Grounding overview](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/grounding/overview), read Nov 12, 2026
- [Google Cloud, Agent Platform pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing), read Nov 12, 2026
- [Google Cloud, Grounding with Parallel Web Search](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/grounding/grounding-with-parallel), read Nov 12, 2026
- [Google Cloud, Grounding with Exa web search](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/grounding/grounding-with-exa), read Nov 12, 2026
- [Parallel pricing](https://parallel.ai/pricing), read Nov 12, 2026
- [Exa pricing](https://exa.ai/docs/admin/pricing), read Nov 12, 2026
- [SpecStream benchmarks](https://specstream.ai/benchmarks), read Nov 12, 2026
- [SpecStream pricing](https://specstream.ai/pricing), read Nov 12, 2026
- [SpecStream for agents](https://specstream.ai/agents.md), read Nov 12, 2026