---
title: "Does the Gemini API have memory? State, caching, Memory Bank"
description: "Not by itself. generateContent is stateless; the Interactions API can store a conversation server-side. Memory across sessions is something you add."
image: "https://bombos.ai/assets/og-en-v2.png"
---

# Does the Gemini API remember previous conversations?

Short answer

Not on its own. With the legacy generateContent API, every call is stateless and your code resends the conversation history. The Interactions API can keep that history server-side through previous\_interaction\_id, stored 55 days on the paid tier and 1 day on the free tier. Neither remembers facts across conversations; for that you build memory yourself or use Memory Bank on Google Cloud's Agent Platform.

*Piet Baudoin · published November 17, 2026 · November 17, 2026*

## Three things people call “memory”

When developers ask whether the Gemini API has memory, they usually mean one of three things. Only the first is built in. As of November 2026:

| What you want | What Gemini offers | Built in? |
| --- | --- | --- |
| The model remembers earlier turns in the same conversation | Interactions API with `previous_interaction_id`, or resending history with `generateContent` | Yes, per conversation |
| Cheaper, faster repeated context | Implicit and explicit context caching | Yes, but it is not memory |
| The agent remembers a user or a team across conversations | Memory Bank on Google Cloud’s Agent Platform, or your own store | No, you build or add it |

## Conversation state: generateContent versus Interactions

The original **generateContent** API, which Google now calls legacy but still fully supports, is stateless. A multi-turn chat works by sending the full conversation history with every request. The SDK’s chat helpers do that for you, but the history lives in your application, not at Google.

The **Interactions API**, generally available since June 2026 and now Google’s recommended interface, can keep state on the server:

1.  Make a call. By default the request is stored (`store=true`).
2.  For the next turn, pass the ID of the completed interaction as `previous_interaction_id`. The server retrieves the history; you do not resend it.
3.  Send `tools`, `system_instruction` and `generation_config` again each time. Only the conversation history carries over.

How long Google keeps stored interactions:

| Tier | Retention |
| --- | --- |
| Paid | 55 days by default; you can set 7, 14, 28 or 55 days in AI Studio |
| Free | 1 day |

Set `store=false` to opt out. Then `previous_interaction_id` and background execution no longer work, and you are back to sending history yourself.

## The common mistake: caching is not memory

Context caching sounds like memory, but it is a cost optimization. Google describes it as a way to reuse repeated input tokens. **Implicit caching** is on by default for Gemini 2.5 and newer models, with a minimum of 4,096 input tokens on Gemini 4 models and 2,048 on Gemini 2.5. When a request hits the cache, the savings are passed on, and you can see cached tokens in `usage.total_cached_tokens`. **Explicit caching**, where you create cache objects yourself, is not supported in the Interactions API or for Gemini 4 models.

Neither changes what the model knows. If the information is not in the request or the stored conversation, Gemini does not have it.

## Memory across conversations

For an agent that remembers a user next week, Google offers **Memory Bank** on Gemini Enterprise Agent Platform, the evolution of Vertex AI. It stores long-term user preferences and facts generated from sessions, uses generative models to extract those memories, and lets an agent fetch them later. Otherwise you build it yourself: a database or vector store your code reads before each call and writes to afterwards.

If data retention matters, check the zero data retention settings on Google Cloud: caching, request logging, `store` in the Interactions API and some grounding features each keep data in their own way, and some cannot be switched off.

## What this means for a team

Every call starts from what you send. In a team that builds several agents, or uses Gemini next to Claude Code, Cursor or Copilot, that means every agent has its own history and its own store, if it has one at all. A fact that one agent learned is not available to the next unless someone writes it somewhere they both read. An interaction stored for 55 days does not turn into lasting knowledge either. Related: [what is an MCP memory server](https://bombos.ai/en/questions/mcp/what-is-an-mcp-memory-server/) and [types of AI agent memory](https://bombos.ai/en/questions/ai-memory/types-of-ai-agent-memory/).

## Where Bombos fits

If you are about to build a memory store for your Gemini agents, Bombos can be that layer: a plugin that gives every AI tool and agent your team uses one shared memory, with team knowledge, rules learned from corrections, and what already sits in mail, documents and repos. It is a context graph with retrieval, not a model, so you can see what each answer rests on, in the cloud or on your own server. One developer can try it first with their own agents.

## Related questions

Is context caching a form of memory?

No. Caching reuses repeated input tokens to cut cost and latency. Implicit caching is on by default for Gemini 2.5 and newer models, but the model only sees what you send in the request.

Do tools and system instructions carry over with previous\_interaction\_id?

No. Only the conversation history carries over. Tools, system\_instruction and generation\_config are scoped to one interaction, so you send them again each turn.

Can I stop Google from storing my interactions?

Yes, set store=false. That also means you cannot use previous\_interaction\_id for the next turn, and background execution does not work.

Does the Gemini app's memory work through the API?

No. Memory in the Gemini app belongs to a personal Google account. The API starts from nothing apart from what your code sends or what you have stored in an interaction.

## Sources

1.  [Google AI Studio docs: Interactions API overview](https://aistudio.google.com/docs/interactions-overview)
2.  [Google AI Studio docs: Context caching](https://aistudio.google.com/docs/caching)
3.  [Google Cloud: Memory Bank overview (Agent Platform)](https://docs.cloud.google.com/agent-builder/agent-engine/memory-bank/overview)
4.  [Google Cloud: Agent Platform overview](https://docs.cloud.google.com/gemini-enterprise-agent-platform/overview?hl=en)
5.  [Google Cloud: data governance and zero data retention](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/data-governance)

## What does your AI forget?

1.  01You tell us which AI you use and where it keeps starting over.
2.  02We show what a shared memory changes there, on your own examples.
3.  03You keep the plan, with or without Bombos.

![Piet Baudoin](https://bombos.ai/assets/team/piet-klein.jpg)

**Piet Baudoin**You talk to Piet, from the Bombos teamDutch team from Utrecht and Nijmegen · data in Europe

## More questions about Gemini and NotebookLM

-   [Does Gemini have memory like ChatGPT?](https://bombos.ai/en/questions/gemini/does-gemini-have-memory-like-chatgpt/)
-   [Can you import your ChatGPT or Claude memory into Gemini?](https://bombos.ai/en/questions/gemini/import-chatgpt-memory-into-gemini/)
-   [Where are Gemini's memory settings, and how do you delete what it remembers?](https://bombos.ai/en/questions/gemini/gemini-memory-settings/)
-   [Does NotebookLM have an API?](https://bombos.ai/en/questions/gemini/notebooklm-api/)
-   [Is a Gemini notebook the same as NotebookLM?](https://bombos.ai/en/questions/gemini/is-gemini-notebook-the-same-as-notebooklm/)
-   [Gemini Enterprise vs Gemini in Workspace: what is the difference and what does it cost?](https://bombos.ai/en/questions/gemini/gemini-enterprise-vs-gemini-in-google-workspace/)
-   [What is NotebookLM Enterprise, and how is it different from NotebookLM in Workspace?](https://bombos.ai/en/questions/gemini/notebooklm-enterprise/)
-   [What are NotebookLM's limits and limitations?](https://bombos.ai/en/questions/gemini/notebooklm-limits/)

[All questions about Gemini and NotebookLM →](https://bombos.ai/en/questions/gemini/)


---

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://bombos.ai/#organization","name":"Bombos","url":"https://bombos.ai/","logo":"https://bombos.ai/assets/bombos-bee.png","description":"Bombos is the memory layer under every AI your team uses. One shared memory for Claude, ChatGPT, Copilot, Cursor and your own agents, that learns how you work.","sameAs":["https://www.linkedin.com/company/bombos-ai","https://www.youtube.com/@truebombos","https://www.instagram.com/truebombos/","https://bsky.app/profile/bombostrue.bsky.social","https://www.threads.com/@truebombos","https://mastodon.social/@Bombos","https://www.tiktok.com/@truebombos","https://t.me/truebombos","https://www.pinterest.com/truebombos/","https://github.com/bombos-ai","https://linktr.ee/bombos.ai","https://bombosai.substack.com","https://hashnode.com/@bombosai","https://hackernoon.com/u/bombos","https://dev.to/bombos"],"email":"info@bombos.ai","areaServed":["NL","Europe"],"knowsLanguage":["nl","en"],"contactPoint":{"@type":"ContactPoint","email":"info@bombos.ai","contactType":"sales","url":"https://bombos.ai/en/contact/","availableLanguage":["nl","en"]}},{"@type":"WebSite","@id":"https://bombos.ai/#website","name":"Bombos","url":"https://bombos.ai/","inLanguage":["nl-NL","en"],"publisher":{"@id":"https://bombos.ai/#organization"}}]}

{"@context":"https://schema.org","@type":"Article","headline":"Does the Gemini API remember previous conversations?","description":"Not by itself. generateContent is stateless; the Interactions API can store a conversation server-side. Memory across sessions is something you add.","abstract":"Not on its own. With the legacy generateContent API, every call is stateless and your code resends the conversation history. The Interactions API can keep that history server-side through previous_interaction_id, stored 55 days on the paid tier and 1 day on the free tier. Neither remembers facts across conversations; for that you build memory yourself or use Memory Bank on Google Cloud's Agent Platform.","datePublished":"2026-11-17T00:00:00.000Z","dateModified":"2026-11-17T00:00:00.000Z","author":{"@type":"Person","name":"Piet Baudoin"},"publisher":{"@type":"Organization","@id":"https://bombos.ai/#organization","name":"Bombos","logo":{"@type":"ImageObject","url":"https://bombos.ai/assets/bombos-bee.png"}},"image":"https://bombos.ai/assets/og-en-v2.png","mainEntityOfPage":"https://bombos.ai/en/questions/gemini/does-the-gemini-api-have-memory/","inLanguage":"en-US","isPartOf":{"@type":"CollectionPage","name":"Gemini and NotebookLM","url":"https://bombos.ai/en/questions/gemini/"},"citation":[{"@type":"CreativeWork","name":"Google AI Studio docs: Interactions API overview","url":"https://aistudio.google.com/docs/interactions-overview"},{"@type":"CreativeWork","name":"Google AI Studio docs: Context caching","url":"https://aistudio.google.com/docs/caching"},{"@type":"CreativeWork","name":"Google Cloud: Memory Bank overview (Agent Platform)","url":"https://docs.cloud.google.com/agent-builder/agent-engine/memory-bank/overview"},{"@type":"CreativeWork","name":"Google Cloud: Agent Platform overview","url":"https://docs.cloud.google.com/gemini-enterprise-agent-platform/overview?hl=en"},{"@type":"CreativeWork","name":"Google Cloud: data governance and zero data retention","url":"https://docs.cloud.google.com/vertex-ai/generative-ai/docs/data-governance"}]}

{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Bombos","item":"https://bombos.ai/en/"},{"@type":"ListItem","position":2,"name":"Questions","item":"https://bombos.ai/en/questions/"},{"@type":"ListItem","position":3,"name":"Gemini and NotebookLM","item":"https://bombos.ai/en/questions/gemini/"},{"@type":"ListItem","position":4,"name":"Does the Gemini API remember previous conversations?","item":"https://bombos.ai/en/questions/gemini/does-the-gemini-api-have-memory/"}]}

{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"Is context caching a form of memory?","acceptedAnswer":{"@type":"Answer","text":"No. Caching reuses repeated input tokens to cut cost and latency. Implicit caching is on by default for Gemini 2.5 and newer models, but the model only sees what you send in the request."}},{"@type":"Question","name":"Do tools and system instructions carry over with previous_interaction_id?","acceptedAnswer":{"@type":"Answer","text":"No. Only the conversation history carries over. Tools, system_instruction and generation_config are scoped to one interaction, so you send them again each turn."}},{"@type":"Question","name":"Can I stop Google from storing my interactions?","acceptedAnswer":{"@type":"Answer","text":"Yes, set store=false. That also means you cannot use previous_interaction_id for the next turn, and background execution does not work."}},{"@type":"Question","name":"Does the Gemini app's memory work through the API?","acceptedAnswer":{"@type":"Answer","text":"No. Memory in the Gemini app belongs to a personal Google account. The API starts from nothing apart from what your code sends or what you have stored in an interaction."}}]}
```
