Customer Experience Agent Studio uses quotas and system limits to maintain fair resource
allocation, prevent service overloads, and help you manage resource use.

Quotas and system limits are similar but differ in the following ways:

- *Quotas* have default values, but you can typically request adjustments.
- *System limits* are fixed values that can't be changed.

Google Cloud uses quotas to help maintain fairness and reduce
spikes in resource use and availability. A quota restricts how much of a
Google Cloud resource your Google Cloud project can use. Quotas
apply to a range of resource types, including hardware, software, and network
components. For example, quotas can restrict the number of API calls to a
service, the number of load balancers used concurrently by your project, or the
number of projects that you can create. Quotas protect the community of
Google Cloud users by preventing the overloading of services. Quotas also
help you to manage your own Google Cloud resources.

The Cloud Quotas system does the following:

- Monitors your consumption of Google Cloud products and services
- Restricts your consumption of those resources
- Provides a way to [request changes to the quota value](https://docs.cloud.google.com/docs/quotas/help/request_increase) and [automate quota adjustments](https://docs.cloud.google.com/docs/quotas/quota-adjuster.md.txt)

In most cases, when you attempt to consume more of a resource than its quota
allows, the system blocks access to the resource, and the task that
you're trying to perform fails.

Quotas generally apply at the Google Cloud project
level. Your use of a resource in one project doesn't affect
your available quota in another project. Within a Google Cloud project, quotas
are shared across all applications and IP addresses.


For more information, see the
[Cloud Quotas overview](https://docs.cloud.google.com/docs/quotas/overview.md.txt).

## Important things to know

- **Multi-region quota mapping** : Multi-region and `global` deployments enforce quotas in a mapped single region. Always select the mapped single region when viewing usage or requesting an adjustment.
- **Project and `base_model` pooling** : Quotas apply per Google Cloud project and mapped region. Runtime model quotas are also tracked per `base_model`---any agents, guardrails, or tools in the same project and region that share a model pool into one `base_model` row.
- **Token quotas govern capacity, not billing** : `RunSession` LLM token quotas are throughput guardrails only---CX Agent Studio session pricing includes underlying agent and guardrail token usage, and raising your `ces.googleapis.com` token quota doesn't add per-token charges. For billing details, see [CX Agent Studio pricing](https://cloud.google.com/products/gemini-enterprise-for-customer-experience/cx-agent-studio/pricing).
- **Lead times and alerting** : Small quota adjustments often approve automatically, while large production increases require capacity review and should be requested well ahead of load testing or launch. Configure [quota usage alerts](https://docs.cloud.google.com/docs/quotas/set-up-quota-alerts.md.txt) (for example, at `80%` utilization) to catch traffic growth early.

### Key terms

- **App (agent application)** : The top-level container created when you click **Create agent** in the CX Agent Studio console ([Create an agent application](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/quick/create-agent.md.txt); `projects/*/locations/*/apps/*` in the API). One app holds your root [agent](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/agent.md.txt), sub-agents, [tools](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/tool.md.txt), [guardrails](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/guardrail.md.txt), [evaluations](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/evaluation.md.txt), and [versions](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/version.md.txt).
- **`RunSession` and `StreamRunSession`** : [Runtime API methods](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/deploy/api-access.md.txt) that process turn-by-turn requests, typically used for **text and web chat**.
- **`BidiRunSession`** : [Runtime API method](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/deploy/api-access.md.txt) that opens a persistent two-way stream, typically used for **live voice
  calls** and real-time audio.
- **`base_model`** : The quota dimension identifying the specific foundation or composite [model](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/agent.md.txt#model-support) ID serving an agent, guardrail, or built-in generative tool.

### Multi-region quota mapping

When you deploy an app in a
[multi-region](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/reference/region.md.txt) or call
the `global` endpoint, CX Agent Studio tracks quotas in the following single
regions:

| Application location | Mapped quota `region` |
|---|---|
| `us` (US multi-region) | `us-central1` |
| `eu` (EU multi-region) | `europe-west4` |
| `global` endpoint | `us-central1` |

## Runtime session quotas

The following adjustable quotas govern live customer conversations across chat
and voice.

| Quota | Default | Type and scope | Metric and behavior |
|---|---|---|---|
| `RunSession` LLM tokens per minute | 120,000 | Rate quota (per project, `region`, `base_model`; resets every minute) | `ces.googleapis.com/run_session_llm_token_consumption` Applies to both chat (`RunSession`, `StreamRunSession`) and voice (`BidiRunSession`). Chat sessions have no separate session-rate or concurrency quota. When exceeded, new turns fail with `429 RESOURCE_EXHAUSTED`. See [How tokens and `base_model` quotas are counted](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/resources/quotas.md.txt#tokens-per-minute). |
| Concurrent `BidiRunSession` operations per 30 minutes | 15 | Concurrent quota (per project, `region`, `base_model`) | `ces.googleapis.com/concurrent_bidi_run_session_operations` Maximum simultaneous active voice or bidirectional streaming sessions. Each open stream holds one slot and releases it on disconnect (30 minutes is the maximum slot lease window). When exceeded, new streams fail with `429 RESOURCE_EXHAUSTED`. |

## How tokens and `base_model` quotas are counted

A single conversation turn can trigger multiple LLM calls when an agent invokes
tools or transfers to a sub-agent, and one app can consume quota across
multiple `base_model` rows at the same time.

**Counted toward `RunSession` LLM tokens per minute** (pooled by `base_model`):

- **Root agent, sub-agents, and agent tools** : Input and output tokens across every LLM call in a turn, billed to each agent's configured [model](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/agent.md.txt#model-support). Composite voice models bill only the composite `base_model` ID rather than underlying speech or sub-models.
- **LLM-based guardrails** : **Prompt guard** , natural-language **Rules** , and the **Generate a response** trigger action, billed to a separate default lightweight Gemini `base_model` (unless pinned through API `modelSettings.model` on a [guardrail](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/guardrail.md.txt) policy).
- **Built-in generative tools** : [Data store](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/tool/data-store.md.txt) query rewriting or summarization and [Google Search](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/tool/search.md.txt) grounding, billed to their underlying `base_model`.

**Not counted toward `RunSession` LLM tokens per minute**:

- **Deterministic and supervisor guardrails** : **Blocklist** , code **Rules** , default **Safety** classifiers, and **Supervisor agents** (Preview), unless configured to trigger **Generate a response**.
- **Built-in evaluations (`RunEvaluation`, Preview)** : Enforces only `Concurrent RunEvaluation operations` (custom test scripts that call `RunSession` or `BidiRunSession` directly *do* count as live sessions).
- **Built-in speech and code execution**: Built-in Speech-to-Text, Text-to-Speech, and Python tool or callback execution.

### Identify and size `base_model` rows

Default auxiliary models evolve over time, and some console model names map to
versioned `base_model` IDs. Confirm your active rows in a non-production
project before launch:

1. Run representative test sessions with your agents, guardrails, and tools enabled.
2. After a few minutes, open **IAM \& Admin \> Quotas \& System
   Limits** filtered by `Metric:ces.googleapis.com/run_session_llm_token_consumption` (or check `serviceruntime.googleapis.com/quota/rate/net_usage` on `ces.googleapis.com/Location` in Cloud Monitoring) to see each active `base_model` row and its observed TPM per session.
3. Request adjustments for those same `base_model` IDs (even on `0`-usage rows) in your production project's mapped region.

For example, a voice app in `us` using `AGENT_MODEL` and LLM-based guardrails
on `GUARDRAIL_MODEL` adjusts three rows in `us-central1`:

| Quota | Target dimensions | How to size |
|---|---|---|
| Concurrent `BidiRunSession` operations | `region=us-central1`, `base_model=AGENT_MODEL` | Peak simultaneous voice calls plus headroom |
| `RunSession` LLM tokens per minute | `region=us-central1`, `base_model=AGENT_MODEL` | Peak sessions multiplied by observed `AGENT_MODEL` TPM per test session, plus headroom |
| `RunSession` LLM tokens per minute | `region=us-central1`, `base_model=GUARDRAIL_MODEL` | Peak sessions multiplied by observed `GUARDRAIL_MODEL` TPM per test session, plus headroom |

## Management, authoring, and evaluation quotas

The following adjustable quotas govern app administration, CI/CD, Studio AI
authoring helpers, standalone tool testing, and evaluations. None of these
quotas restrict live customer session traffic.

| Quota | Default | Type and scope | Metric and notes |
|---|---|---|---|
| Apps per project per region | 1,000 | Allocation (per project, `region`) | `ces.googleapis.com/apps` --- Top-level agent applications (`App` containers); restored when an app is deleted. |
| API requests per minute | 10,800 | Rate (per project) | `api-requests` --- Covers management, tool, and evaluation RPCs; excludes runtime sessions. |
| App mutation operations per minute | 200 | Rate (per project, `region`) | `ces.googleapis.com/app_mutation_operations` --- Write actions that create, edit, delete, deploy, import (`ImportApp`), or sync an app or its agents, tools, guardrails, or evaluations. Bulk imports and Git sync count as 1 operation per call. |
| App read operations per minute | 600 | Rate (per project, `region`) | `ces.googleapis.com/app_read_operations` --- Read actions that view, list, or export (`ExportApp`) an app or its agents, tools, guardrails, or evaluations. Bulk exports count as 1 operation per call. |
| App generative operations per minute (Preview) | 100 | Rate (per project, `region`) | `ces.googleapis.com/app_generative_operations` --- AI-assisted authoring actions in the console or API, such as generating instructions, mock tools, test scenarios, or quality fixes. |
| `ExecuteTool` requests per minute | 240 | Rate (per project, `region`) | `ces.googleapis.com/execute_tool_requests` --- Standalone `ToolService` calls only (for example, clicking **Test tool** in the console; excludes tools called inside sessions). |
| `RetrieveTools` requests per minute | 120 | Rate (per project, `region`) | `ces.googleapis.com/retrieve_tools_requests` --- Standalone `ToolService` calls only. |
| `RetrieveToolSchema` requests per minute | 120 | Rate (per project, `region`) | `ces.googleapis.com/retrieve_tool_schema_requests` --- Standalone `ToolService` calls only. |
| Concurrent `RunEvaluation` operations per 10 minutes (Preview) | 20 | Concurrent (per project, `region`) | `ces.googleapis.com/concurrent_run_evaluation_operations` --- Simultaneous active evaluation runs (freed on completion). |

## System limits

CX Agent Studio enforces the following fixed system limits (not adjustable):

| System limit | Value |
|---|---|
| Maximum [agents](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/agent.md.txt) per app (root agent plus sub-agents) | 100 |
| Maximum [tools](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/tool.md.txt) per app | 200 |
| Maximum tools per agent | 100 |
| Maximum toolsets per app (multi-operation [OpenAPI](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/tool/open-api.md.txt), [MCP](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/tool/mcp.md.txt), or [connector](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/tool/connector.md.txt) integrations) | 100 |
| Maximum [guardrails](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/guardrail.md.txt) per app | 100 |
| Maximum few-shot examples per app | 1,000 |
| Maximum [variables](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/variable.md.txt) per app | 100 |
| Maximum [evaluations](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/evaluation.md.txt) per app (Preview) | 1,000 |
| Maximum evaluation datasets per app (Preview) | 100 |
| Maximum turns per evaluation (Preview) | 100 |
| Maximum [callbacks](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/callback.md.txt) per agent | 50 |
| Maximum immutable [app versions](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/version.md.txt) per app | 200 |
| Maximum serialized `App` resource size | 10 MiB |
| Maximum LLM calls (tool or transfer steps) per turn | 10 |
| Unary `RunSession` RPC deadline (default synchronous tool timeout: 30s) | 60 seconds |
| Maximum `BidiRunSession` stream duration | 60 minutes |
| `BidiRunSession` client message idle timeout | 30 seconds |

## Related service quotas

Agent model inference, built-in Speech-to-Text, built-in
Text-to-Speech, `RunEvaluation` judges, and Python execution don't
consume quotas in other APIs in your Google Cloud project. When your
agent integrates with the following services, check their quotas separately:

| Integrated service | When quotas apply in your project |
|---|---|
| [Omnichannel Gateway](https://docs.cloud.google.com/gemini-enterprise-cx/omnichannel-gateway/quotas) and [Dialogflow](https://docs.cloud.google.com/dialogflow/quotas.md.txt) | Native channel and telephony routing (Omnichannel Gateway), or routing through Dialogflow telephony integrations |
| [Agent Search](https://docs.cloud.google.com/generative-ai-app-builder/quotas.md.txt) | Querying or summarizing [data store tools](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/tool/data-store.md.txt) |
| Vertex AI and Vertex AI RAG Engine | Using built-in [Google Search tools](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/tool/search.md.txt) (`aiplatform.googleapis.com`) or connecting an existing corpus to [File Search tools](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/tool/file.md.txt) |
| [Integration Connectors](https://docs.cloud.google.com/integration-connectors/docs/quotas.md.txt) and [Cloud Run](https://docs.cloud.google.com/run/quotas.md.txt) | Invoking [connector tools](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/tool/connector.md.txt) or Cloud Run webhook tools |
| [Model Armor](https://docs.cloud.google.com/model-armor/quotas.md.txt) and [Sensitive Data Protection](https://docs.cloud.google.com/sensitive-data-protection/limits.md.txt) | Scanning [CX Agent Studio MCP server](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/mcp-server.md.txt#model-armor) requests or applying redaction templates |

## Request a quota adjustment

To adjust most quotas, use the Google Cloud console.
For more information, see
[Request a quota adjustment](https://docs.cloud.google.com/docs/quotas/help/request_increase).

In the Google Cloud console, filter by
`Service:Gemini Enterprise for Customer Experience API`, your
[mapped single region](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/resources/quotas.md.txt#multi-region-quota-mapping), and the target runtime
`Metric:` (`ces.googleapis.com/run_session_llm_token_consumption` or
`ces.googleapis.com/concurrent_bidi_run_session_operations`). Include your peak
concurrency and observed TPM per session in the request description.

For CLI commands, alerts, and error diagnosis, see
[Manage quotas using the
gcloud CLI](https://docs.cloud.google.com/docs/quotas/gcloud-cli-examples),
[Set up quota alerts and monitoring](https://docs.cloud.google.com/docs/quotas/set-up-quota-alerts.md.txt), and
[Troubleshoot quota errors](https://docs.cloud.google.com/docs/quotas/troubleshoot.md.txt).