Gemini API
Send the prompt your buyers type and get back what Gemini tells them: the full answer, the URLs it cites and the products it recommends. Same JSON shape as our ChatGPT endpoint, so one parser tracks both.
50 free credits on signup, enough for 10 prompts. No card required.
{ "data": { "platform": "gemini", "prompt": "What are the best running shoes for beginners?", "model": null, "answer": { "markdown": "Choosing your first running shoe is an important step. The best beginner running shoes focus on **balanced cushioning**, **reliable stability**, and **durability** to protect your joints as you build mileage...\n\n### For Daily Versatility & Neutral Support\n\nThe Brooks Ghost 18 is a **fan-favorite daily trainer**..." }, "sources": [ { "url": "https://www.runnersworld.com/gear/a19663621/best-running-shoes/", "title": null, "snippet": null, "source": null, "published_at": null }, { "url": "https://theruntesters.com/", "title": null, "snippet": null, "source": null, "published_at": null } ], "search_queries": [], "shopping": [ { "title": "Brooks Men's Ghost 18", "url": null, "price": null, "image_url": null, "merchant": null }, { "title": "Hoka Men's Clifton 11", "url": null, "price": null, "image_url": null, "merchant": null }, { "title": "Women's On Cloudrunner 3", "url": null, "price": null, "image_url": null, "merchant": null } ] }, "response_time": 36631, "credits_used": 5, "credits_remaining": 4995}Live call against the real endpoint. Answers take 10-40 seconds. 2 free runs, then it's your own key.
What is the Scavio Gemini API?
The Scavio Gemini API is a REST API that sends a prompt to Google Gemini and returns its answer as structured JSON: the answer as Markdown, the URLs it cited, and the products it recommended. It shares one response shape with the Scavio ChatGPT API and is built for tracking AI visibility.
- 1
- endpoint, live in production
- 5
- credits per answered prompt
- 4,000
- characters per prompt
One endpoint, the whole answer
What Gemini says, who it cites, and what it recommends.
Prompt
POST /api/v1/gemini/promptSend the question your buyer would ask. Get back the answer Gemini gives, the URLs it cites and the products it recommends, in the same JSON shape as the ChatGPT endpoint.
The Gemini endpoint
A POST that returns JSON and takes the same API key as every other Scavio platform. 5 credits per answered prompt.
| Endpoint | Returns | Credits |
|---|---|---|
Prompt/api/v1/gemini/prompt | Gemini's answer as Markdown, the URLs it cites and the products it recommended | 5 |
50 free credits on signup covers 10 prompts. See plans
Is your brand in Gemini's answer?
Check the answer, the cited URLs and the recommended products for your brand. The response on the right is a real capture, trimmed.
from scavio import ScavioClient
client = ScavioClient(api_key="sk_live_your_key")
res = client.gemini.prompt("What are the best running shoes for beginners?")
answer = res["data"]
# Is your brand in the answer?
print("Brooks" in answer["answer"]["markdown"])
# Which pages did Gemini cite?
for s in answer["sources"]:
print(s["url"])
# Which products did it recommend?
print([p["title"] for p in answer["shopping"]]){
"data": {
"platform": "gemini",
"prompt": "What are the best running shoes for beginners?",
"model": null,
"answer": {
"markdown": "Choosing your first running shoe is an important step. The best beginner running shoes focus on **balanced cushioning**, **reliable stability**, and **durability** to protect your joints as you build mileage...\n\n### For Daily Versatility & Neutral Support\n\nThe Brooks Ghost 18 is a **fan-favorite daily trainer**..."
},
"sources": [
{
"url": "https://www.runnersworld.com/gear/a19663621/best-running-shoes/",
"title": null,
"snippet": null,
"source": null,
"published_at": null
},
{
"url": "https://theruntesters.com/",
"title": null,
"snippet": null,
"source": null,
"published_at": null
}
],
"search_queries": [],
"shopping": [
{ "title": "Brooks Men's Ghost 18", "url": null, "price": null, "image_url": null, "merchant": null },
{ "title": "Hoka Men's Clifton 11", "url": null, "price": null, "image_url": null, "merchant": null },
{ "title": "Women's On Cloudrunner 3", "url": null, "price": null, "image_url": null, "merchant": null }
]
},
"response_time": 36631,
"credits_used": 5,
"credits_remaining": 4995
}Why not Google's Gemini API?
Google's API answers your request. AI visibility is about the answer Gemini gives everyone else.
Google Gemini API
- Returns a completion from the model and settings you configure, not the answer the Gemini app gives its users
- Grounding and citations only when you enable them, on your terms rather than the app's
- No product recommendations as the Gemini app shows them
- Billed per token, so a long answer costs more than a short one
Scavio Gemini API
- The answer Gemini gives, with the URLs it chose to cite
- The products it recommended, as an array
- A flat 5 credits per answered prompt; failed prompts are free
- Same response shape as the Scavio ChatGPT API, same key as 40+ platforms
What teams build with it
AI visibility tracking
Run the prompts your buyers type, on a schedule, and record whether Gemini names your brand. Gemini sits inside Google's own products, so its recommendations reach buyers who never open a chat app.
promptCitation analysis
Every answer comes with the URLs Gemini cited. Find which sites decide your category in Gemini's eyes, and whether they are the same ones ChatGPT trusts.
promptProduct recommendation monitoring
For commercial prompts Gemini recommends specific products. shopping[] lists them in order, so you can track whether yours is named and which competitors are.
promptChatGPT vs Gemini comparison
Send the same prompt to both endpoints. The response shape is identical, so share of answer across assistants is one loop and one parser.
gemini + chatgptAnswer accuracy checks
Catch a confidently wrong claim about your pricing, features or availability before a prospect repeats it to your sales team.
promptHow to get Gemini answers as JSON
- 1
Get an API key
Sign up for a Scavio account and copy your key from the dashboard. You get 50 credits free on signup, enough for 10 prompts, with no card required.
- 2
POST a prompt
Send {"prompt": "What are the best running shoes for beginners?"} to https://api.scavio.dev/api/v1/gemini/prompt with an Authorization: Bearer header. Prompts can be up to 4,000 characters.
- 3
Read the answer, sources and products
data.answer.markdown is the full answer, data.sources lists the URLs it cited and data.shopping the products it recommended. Check them for your brand.
Gemini API FAQ
What is the Scavio Gemini API?
+
It is a REST API that sends a prompt to Google Gemini and returns the answer Gemini gives as structured JSON: the full answer as Markdown, the URLs it cited and the products it recommended. One POST endpoint, authenticated with a Scavio API key.
How is this different from the Gemini API from Google?
+
Google's Gemini API returns a completion from the model and settings you configure in your own request. It is not the answer the Gemini app gives the people asking it questions, with the sources it chose and the products it recommended. For AI visibility you need to see what your buyers see, and that is what this endpoint returns.
Who is this for?
+
SEO and GEO teams tracking brand mentions in Gemini, agencies reporting AI visibility for clients, ecommerce brands checking whether Gemini recommends their products, and developers building AI visibility tools who need the underlying data.
How do I track brand mentions in Gemini?
+
Build a list of the prompts your buyers ask, call the endpoint for each on a schedule, and record whether your brand appears in answer.markdown, sources and shopping. Over time that is your share of answer in Gemini.
Is this a Gemini scraper API?
+
It returns the same data a Gemini scraper would, without you running or maintaining one: no browsers, accounts or retries on your side. You send a prompt and get clean JSON back.
How much does a prompt cost?
+
5 credits per answered prompt. Failed prompts are not charged. New accounts get 50 free credits on signup, enough for 10 prompts. On the Growth yearly plan that works out to about $10 per 1,000 prompts.
How long does an answer take?
+
Typically 10 to 40 seconds. Set your HTTP client timeout to at least 90 seconds, and if a call returns 503, retry after the Retry-After header (it is never charged).
What does Gemini return compared with ChatGPT?
+
The same response shape, with less filled in. Gemini sources are URLs only, so title, source and published_at are null; search_queries is always empty; and model is usually null. Recommended products come back in shopping[] by title. ChatGPT API
Are answers the same every time?
+
No. Gemini answers vary between runs, so treat visibility as a rate measured across several runs per prompt. Responses are never cached, so every call is a fresh answer.
How long can a prompt be?
+
Up to 4,000 characters. A longer prompt is rejected with a 400 before anything is charged.
Which languages and tools are supported?
+
Official Python (pip install scavio) and JavaScript/TypeScript (npm i scavio) SDKs, a remote MCP server at mcp.scavio.dev for AI agents, and an n8n community node. Any language can call the REST endpoint with an HTTP client.
Explore more of Scavio
ChatGPT API
The same prompt, answered by ChatGPT, in the same shape.
Google AI Mode API
Google's generated search answer and its sources.
Google Search API
The full SERP, including AI Overview.
Gemini API docs
Parameters, response fields and errors.
MCP server
Every platform as a callable tool for agents.
Pricing
Credit packs and plans, no per-platform surcharge.
Find out what Gemini says about your brand
50 free credits on signup, no card. Your first request is a POST with a prompt in it.