Google Gemini

Google's Gemini models reach Memtro through the Gemini API with a key from Google AI Studio. Add the key once and Gemini answers everywhere Memtro calls a model: chat, agent mode, routing ladders, memory extraction and jobs. The same key can also embed your organisation's memories for retrieval.

Add the key

Memtro calls the Gemini Developer API at generativelanguage.googleapis.com, so the key comes from Google AI Studio, not from Vertex AI. In AI Studio open Dashboard, then Projects (import a Google Cloud project there if you want to use one), then API Keys, and create a key. Accepting the terms creates a default project and key for you. Google's API key page says a project you import may need verifying, and that the paid tier means setting up billing on the project. Read your data at Google before deciding between the two.

On Dashboard → Providers pick Google Gemini, paste the key and choose who it is for: Personal (only you), Shared with your organisation, or one team. Which of these you are offered depends on your permissions. Work done for the organisation or a team, such as its jobs and its connections' syncs, spends only shared and team keys, never a member's personal one; your own personal jobs and personal connections can use your personal key.

Saving does not send a test request. Memtro stores the key encrypted, never shows it again, and asks Google which models it can reach, so a good key comes back as Added google key (personal). with the number of models it found after it. If the listing fails, the key is still saved and the form says Saved. Listing models failed: <reason>. Check the key, then use Refresh models., where a request Google refuses gives google and the HTTP status as the reason, such as google 400. Refresh models beside the key asks again.

Leave the optional base URL empty. Hosted Memtro accepts an override only when it is https:// on one of the three hosts Memtro speaks to, api.anthropic.com, api.openai.com or generativelanguage.googleapis.com, so an override cannot point this key at a proxy or gateway; any other host is refused. A host your organisation approves under Custom model hosts does not count here: that list is for OpenAI-compatible endpoints only.

Model ids

Id	What it is
google/<model>	One model through your key, e.g. google/gemini-3.8-flash or google/gemini-3.1-pro-preview. Bare ids starting gemini or gemma are read the same way.
auto/google	Routed by difficulty within Google, on the default ladder Gemini 3.5 flash-lite → 3.8 flash → 3.1 pro. See model routing.

The model list beside the key shows the models the key can reach that generate content. A named model is used only where an administrator has opened model choice on the Routing page; otherwise it is answered as memtro (see cost control).

What is different about Google in Memtro

• Thinking. Agent mode, and a reasoning_effort of high, xhigh or max (deep) or low or medium (standard), are passed on as Gemini's thinking settings: a thinking budget when the request caps its output, a thinking level otherwise. A request capped below 2,048 output tokens gets no thinking.
• Embeddings. A Google key can embed your organisation's memories with gemini-embedding-001, and Memtro uses an OpenAI or Google key of yours for that in place of its own embedding model. It also serves POST /v1/embeddings, which needs a key of your own.
• More than one key. Your own key is tried first, then your team's, then the organisation's; within each, the order set on the Providers page, or Spread the load. A rate-limited or exhausted key hands over to the next before routing moves down the ladder. See several keys for one provider.
• Usage in tokens. Each request is recorded with the input and output tokens Google reports. Allowances are set in tokens, and Memtro does not price them: your Google Cloud billing is where the bill is.

Your data at Google

Google's Gemini API terms, as of November 2026, treat the two tiers differently. On unpaid services Google uses the content you submit to provide, improve and develop its products, and human reviewers may read it. On paid services Google says it does not use your prompts or responses to improve its products, and logs them for a limited period for abuse monitoring. A request through Memtro usually carries your organisation's memory with it, and each memory's text reaches your embedding provider when it is written, so a key on a project without billing sends that memory to the unpaid tier. Use a key from a project with billing set up. See privacy for what erasure in Memtro cannot reach.

What this is not

This is the Gemini Developer API, billed by Google per token on the project that owns the key. It is not Vertex AI: a Vertex AI credential or endpoint does not work here.