<!-- twin of https://specstream.ai/gemini-deep-research-api -->
# Gemini Deep Research API in 2026: $1 to $7 a task, or rows at 5¢

Compared on Nov 12, 2026. The page: https://specstream.ai/gemini-deep-research-api

Google's Gemini Deep Research is an agent on the Interactions API, in preview. Google estimates $1.00 to $3.00 a task, and $3.00 to $7.00 on Deep Research Max. A task runs at most 60 minutes, and the agent does not support structured outputs.

SpecStream is the live web data engine for teams and agents. Deep Search returns every match as a structured row at 5¢, 15¢ or $1, under a maximum you approve first. Gemini's agent can also call SpecStream as an MCP server.

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

## SpecStream and the Gemini Deep Research API side by side

| | SpecStream | Gemini Deep Research |
|---|---|---|
| The product today | Deep Search, with the Search API and the Extract API on the same key | Two agents in preview, `deep-research-preview-04-2026` and `deep-research-max-preview-04-2026`, on the Interactions API only. Not available through `generate_content` |
| What you send | The data you want in plain words, with the conditions every row must meet | A prompt as `input`, with `background=True`, then you poll by `id`. Collaborative planning lets you review the plan before the run |
| What you get back | One structured row per match, with the columns you asked for and facts from many sites joined. Source URL and read time on every value | Detailed reports, long-form analysis and comparative tables, with charts when `visualization` is `auto`. The agent does not support structured outputs |
| The unit you pay for | A delivered row: 5¢, 15¢ or $1 by how much the row needs, plus 5¢ for an email and 15¢ for a phone. A run that finds nothing costs nothing | Tokens at Gemini list rates plus tool fees. Google's typical task: about 80 searches, 250k input tokens and 60k output tokens |
| The price before a run | The most the run can cost, quoted before it starts. Nothing runs until you approve it, and the charge never goes past it | An estimate: $1.00 to $3.00 a task, and $3.00 to $7.00 on Max, at preview rates Google says can change. The agent decides how much to search and read |
| Run length | A run works until it reaches the count, up to four hours on the largest lists. The Search API answers in a few seconds | At most 60 minutes. Google says most tasks finish within 20 minutes |
| Tools and connections | The MCP server at `https://api.specstream.ai/mcp`, the REST API, Python and TypeScript SDKs, the CLI and A2A | Google Search, URL Context and Code Execution by default, plus remote MCP servers and File Search. No custom function calling tools |

## Why teams run their research on SpecStream

### You get rows, ready for your table

A Gemini report answers a question once, and someone still copies its facts into a table. Google's page says the Deep Research agent does not support structured outputs. Deep Search returns each match as a row with the columns you asked for: companies, people, filings, tenders, papers or products. `get_find_decisions` returns each condition's answer with its reason, the value, the source and the time it was read.

Source URL and read time on every value.

### The price is set before the run

Google's figures are estimates: a typical Deep Research task uses about 80 searches, a Max task up to 160, and the agent decides how much to read. SpecStream quotes the most the whole job can cost, good for 30 minutes. `compile` reads your request into conditions and columns you can edit, `quote_capacity_work` prices it, and the run starts only when you approve that maximum as `confirm_max_cents`. The charge never goes past it.

### You pay for rows, and the searches behind them are free

A row costs 5¢ with up to 5 facts, 15¢ with up to 15 facts and one set of related records, and $1 for a deep row with no limit. 10,000 rows with 5 facts cost $500. The searches and pages behind each row are not billed. Duplicates, rows you already own and rows a page contradicts are not charged.

### Keep Gemini, and give it SpecStream's search

Gemini Deep Research takes remote MCP servers as tools, with `headers` for the key and `allowed_tools` to choose the tools. Add SpecStream at `https://api.specstream.ai/mcp` with `search_web` and `read_pages`, and the agent searches and reads the live web through SpecStream. A search costs $5 per 1,000 searches of up to 10 results, and a page costs $0.80 per 1,000 pages. The code is in the next section.

### The Search API on the same key is the most accurate there is

The SpecStream Search API scores 97.9 F-score on all 1,000 official SimpleQA Verified questions (978 correct), and 64.0 item F1 and 43.4 row F1 on all 200 official WideSearch tasks. The Extract API scores 0.908 F1 on WCXB. Scores and method are on the [benchmarks](https://specstream.ai/benchmarks?utm_source=alternatives&utm_campaign=gemini-deep-research-api) page. The [Search API](https://specstream.ai/search-api?utm_source=alternatives&utm_campaign=gemini-deep-research-api) costs from $1 per 1,000 searches of up to 10 results, and the [Extract API](https://specstream.ai/extract-api?utm_source=alternatives&utm_campaign=gemini-deep-research-api) costs $0.80 per 1,000 pages.

### The rows stay up to date and land in your tools

Save the request and it reruns hourly to yearly. Each row comes back labeled changed, unchanged or no longer matching. A changed or new row costs half its rate and an unchanged row costs 1¢, so rechecking 1,000 rows that did not change costs $10. New matches arrive in Slack, email, a sheet, a CRM or a signed webhook.

## Other deep research APIs

### Perplexity Agent API

Sonar Chat Completions support ended on September 27, 2026, and Perplexity maps Sonar Deep Research to the Agent API's `high` effort level. You pay tokens at the model's rates plus tool fees: `web_search` costs $2.50 per 1,000 calls, or $1.00 on Fast Search. On SpecStream the searches and pages behind a row are not billed.

### Parallel Task API

Priced per run by processor, from $5 per 1,000 runs on lite to $2,400 per 1,000 on ultra8x. The ultra processor costs $300 per 1,000, or 30¢ a run, and takes 5 to 25 minutes. SpecStream bills the rows a run delivers, and a run that finds nothing costs nothing.

### Tavily Research

One request takes 4 to 110 credits on mini and 15 to 250 on pro, at $0.008 a credit pay as you go, so 3¢ to $2 a request. The charge lands between the minimum and the maximum. SpecStream names the most a run can cost before it starts.

### OpenAI deep research

OpenAI shut down `o3-deep-research` and `o4-mini-deep-research` on July 23, 2026, and its deprecations page names `gpt-5.6-sol` as the replacement. Web search there costs $10.00 per 1,000 calls plus search content tokens at model rates. SpecStream takes the same research request in plain words and returns rows at 5¢, 15¢ or $1 each.

## How to move a Gemini Deep Research job to SpecStream

Write the data you want in plain words, in place of the research prompt you send today. Sign up and you get $10 of credit, no card. At 5¢ a row, that is up to 200 rows. Over MCP, your agent calls `compile`, `quote_capacity_work` and `authorize_capacity_work`, then reads the rows with `list_find_rows`.

Or send the request from code. This call spends nothing: the `402` reply shows how SpecStream read the request, the columns and the most it can cost.

```
curl -i https://api.specstream.ai/v1/agent/lists \
  -H "Content-Type: application/json" \
  -d '{"request": "AI startups that raised a seed or Series A round in 2026, with the founders, the round size, the lead investor and the product in one line", "count": 25}'
```

To keep Gemini Deep Research and run its searches on SpecStream, pass SpecStream as an `mcp_server` tool. When you pass `tools`, the agent uses the tools in that list in place of its defaults. Set `SPECSTREAM_API_KEY` to your SpecStream API key ([MCP setup](https://specstream.ai/docs/mcp?utm_source=alternatives&utm_campaign=gemini-deep-research-api)).

```
import os
from google import genai

client = genai.Client(http_options={"api_version": "v1beta"})

interaction = client.interactions.create(
    agent="deep-research-preview-04-2026",
    input="Research the history of Google TPUs.",
    tools=[
        {
            "type": "mcp_server",
            "name": "SpecStream",
            "url": "https://api.specstream.ai/mcp",
            "headers": {"Authorization": "Bearer " + os.environ["SPECSTREAM_API_KEY"]},
            "allowed_tools": ["search_web", "read_pages"],
        }
    ],
    background=True,
)
print(interaction.id)
```

## Frequently asked questions

### How much does the Gemini Deep Research API cost?

Google estimates $1.00 to $3.00 a task on Deep Research and $3.00 to $7.00 on Deep Research Max, at preview rates that can change. You pay tokens at Gemini list rates plus tool fees, so the exact price is known after the task. SpecStream bills 5¢, 15¢ or $1 for each delivered row, under a maximum you approve first.

### Is there a Gemini Deep Research API?

Yes, in preview: the agents `deep-research-preview-04-2026` and `deep-research-max-preview-04-2026` run on the Interactions API, not through `generate_content`. A task must run with `background=True`, and you poll it by its `id`.

### Does the Gemini Deep Research API return JSON?

No. Google's page says the Deep Research agent does not support structured outputs; it returns reports, analysis and comparative tables. SpecStream Deep Search returns one structured row per match, with the columns you asked for and a source URL and read time on every value.

### How long does a Gemini Deep Research task take?

At most 60 minutes, and Google says most tasks finish within 20 minutes. A SpecStream Deep Search run works until it reaches the count, up to four hours on the largest lists, and the Search API answers in a few seconds.

### Can Gemini Deep Research use an MCP server?

Yes. Pass a tool of type `mcp_server` with the server's `url`, `headers` for the key and `allowed_tools`. SpecStream's MCP server is at `https://api.specstream.ai/mcp`, and its `search_web` tool costs $5 per 1,000 searches of up to 10 results.

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

Yes, and new accounts get $10 of credit, no card. The MCP server is at `https://api.specstream.ai/mcp` over Streamable HTTP, with OAuth or an API key. There is a REST API, Python and TypeScript SDKs, a CLI and A2A, and an agent can buy one request with no account, by card or in USDC.

## 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
- [Gemini Deep Research agent](https://aistudio.google.com/docs/deep-research), read Nov 12, 2026
- [Gemini API pricing](https://aistudio.google.com/docs/pricing), read Nov 12, 2026
- [Perplexity Sonar migration](https://docs.perplexity.ai/docs/agent-api/migrate-from-sonar/overview), read Nov 12, 2026
- [Perplexity pricing](https://docs.perplexity.ai/docs/getting-started/pricing), read Nov 12, 2026
- [Parallel pricing](https://docs.parallel.ai/getting-started/pricing.md), read Nov 12, 2026
- [Tavily API credits](https://docs.tavily.com/documentation/api-credits), read Nov 12, 2026
- [OpenAI o3-deep-research](https://developers.openai.com/api/docs/models/o3-deep-research), read Nov 12, 2026
- [OpenAI o4-mini-deep-research](https://developers.openai.com/api/docs/models/o4-mini-deep-research), read Nov 12, 2026
- [OpenAI deprecations](https://developers.openai.com/api/docs/deprecations), read Nov 12, 2026
- [OpenAI pricing](https://developers.openai.com/api/docs/pricing), read Nov 12, 2026