# Gemini Enterprise (slim)

> Google Cloud's enterprise assistant, which searches and acts across a company's connected apps and data. Developers call the assistant through the StreamAssist method of the Discovery Engine API, and agents registered in it over A2A.

- Full: https://www.anchorterminal.com/tools/gemini-enterprise.md (~8,100 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/gemini-enterprise.json · canonical https://www.anchorterminal.com/tools/gemini-enterprise
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-11

**B · 68.1/100 · rank #231 of 961 · #2 in Company knowledge & data catalogues · not agent-ready · confidence medium**


Assessment: The assistant is callable through a GA v1 method with a 99.5 per cent SLA, OAuth through IAM, a public Discovery document and optional Model Armor screening. Seat prices weren't found on Google's pages, onboarding needs a billing account and a person, and some Gemini agent capabilities announced on 8 October are early access.

## Facts

- Kind: HTTP API · vendor: Google · category: Company knowledge & data catalogues · legal entity: Google LLC · provenance 99/100
- Local only (HTTP): pypi `google-cloud-discoveryengine`, npm `@google-cloud/discoveryengine`
- Auth: OAuth · pricing: Paid · x402: no · licence: Proprietary service under the Google Cloud terms. The client libraries are Apache-2.0
- Probe metrics: not measured yet (probes haven't run)
- API: StreamAssist at POST https://discoveryengine.googleapis.com/v1/{assistant}:streamAssist, with `global`, `us` and `eu` endpoints. Request fields query, session, userMetadata, agentsSpec, toolsSpec and generationSpec (a Vertex AI modelId)
- A2A: Agents in Agent Registry advertise an A2A URL on LOCATION-discoveryengine.googleapis.com with GET /v1/card, POST /v1/message:send and POST /v1/message:stream, A2A protocol version 0.3.0, HTTP_JSON binding
- Credentials: OAuth 2.0 bearer tokens through IAM. Scopes cloud-platform, discoveryengine.assist.readwrite, discoveryengine.readwrite or discoveryengine.serving.readwrite. Permission discoveryengine.assistants.assist
- Editions: Business (1 to 500 users), Standard, Plus, Frontline (with 150 or more Standard or Plus users) and Pay-as-you-go
- Quotas: Assistant 160 queries a day per Standard licence and 200 per Plus licence, pooled per edition, project and location. 300 search and complete-query requests a minute per project
- SLA: 99.5 per cent monthly uptime for StreamAssist and 99.9 for Search, with credits of 10, 25 or 50 per cent
- Security: VPC Service Controls, CMEK on the US and EU multi-regions, Access Transparency, Model Armor screening (opt-in), Cloud Audit Logs and usage audit logs
- Trains on customer data: No, per the product page
- Client libraries: C#, Go, Java, Node.js, PHP, Python and Ruby
- Prices: Storage and data indexing over quota (per GiB) $5 per GB per month

- Scores: Reliability 85, Performance pending, Schema & documentation 78, Agent ergonomics 48, Security & auth 87, Payments & pricing 10, Task success pending, Maintenance & community 80, Transparency & trust 82 · total over the 7 assessed categories
- Why: Reliability, Hosted reading, scored on the StreamAssist method of the Discovery Engine API. · Schema & documentation, A public Discovery document for v1, revision 20261004, with 278 methods and 990 schemas, StreamAssist and the A2A methods among them (25). · Agent ergonomics, API reading. · Security & auth, OAuth 2.0 bearer tokens from user credentials, service accounts or workforce identity federation, with IAM permissions. · Payments & pricing, Hosted rubric. · Maintenance & community, Read as a closed service with official client libraries. · Transparency & trust, Closed service under the Google Cloud terms, with Apache-2.0 client libraries (15 of 30).
- Sources: 25, open questions: 7, both in the full twin
- Capabilities: knowledge.search, agent.multi-agent, agent.mcp-client, web.search
- JSON: https://www.anchorterminal.com/api/v1/tools/gemini-enterprise.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/gemini-enterprise.svg` or a link to https://www.anchorterminal.com/tools/gemini-enterprise from a page on google.com or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Create a Gemini Enterprise app first. StreamAssist needs its APP_ID, and the caller needs `discoveryengine.assistants.assist`
2. Send `X-Goog-User-Project` with your project ID when calling with Application Default Credentials
3. Pass the `session` name from the final stream message on the next call to keep context. Leaving it empty starts a new session
4. Read `connectorAuthErrors` in the response. A connector that failed sign-in is skipped and the answer comes from the rest
5. Use the A2A URL returned by Agent Registry verbatim. It takes the project number, not the project ID

## Connect

```bash
pip install google-cloud-discoveryengine   # or: npm install @google-cloud/discoveryengine
```

```bash
curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" "https://ENDPOINT_LOCATION-discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/collections/default_collection/engines/APP_ID/assistants/default_assistant:streamAssist" -d '{"query": {"text": "QUERY_TEXT"}}'
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/gemini-enterprise

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Onyx | B | 65 | knowledge.search, web.search, agent.mcp-client | https://www.anchorterminal.com/tools/onyx.min.md |
| Cohere North | C | 55.1 | knowledge.search, agent.mcp-client, web.search | https://www.anchorterminal.com/tools/cohere-north.min.md |
| OpenAI Agents SDK | AA | 86.2 | agent.multi-agent, agent.mcp-client | https://www.anchorterminal.com/tools/openai-agents-sdk.min.md |
| Pydantic AI | A | 83.7 | agent.multi-agent, agent.mcp-client | https://www.anchorterminal.com/tools/pydantic-ai.min.md |
| Microsoft Agent Framework | A | 82.2 | agent.multi-agent, agent.mcp-client | https://www.anchorterminal.com/tools/microsoft-agent-framework.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)