[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC)：2025-08-18。"],[[["\u003cp\u003eDialogflow quotas are constraints applied to projects, varying by agent edition and shared across applications and IP addresses, and can be increased for paid editions.\u003c/p\u003e\n"],["\u003cp\u003eGenerative features in Conversational Agents (Dialogflow CX) have their own quotas per model and region, with the \u003ccode\u003eConversationalAgentLlmTokenConsumption\u003c/code\u003e quota tracking LLM token usage across several features.\u003c/p\u003e\n"],["\u003cp\u003eQuotas are time-bound, with per-month quotas refreshing on the 1st, per-day quotas daily, and per-minute quotas every 60 seconds.\u003c/p\u003e\n"],["\u003cp\u003eLimits are fixed constraints on resources like counts, durations, or lengths, which cannot be increased, and they are detailed in tables for both Conversational Agents (Dialogflow CX) and Dialogflow ES.\u003c/p\u003e\n"],["\u003cp\u003eThe total sum of phone time used per minute is called "phone minutes per minute", which represents the aggregated duration of calls made through the phone system, impacting how many users can simultaneously use the system.\u003c/p\u003e\n"]]],[],null,["# Quotas and limits\n\nThis document contains the commonly encountered quotas and limits\nfor use of Dialogflow.\nInformation on how to find a complete list of quotas and limits\nis provided below.\nWe reserve the right to change these constraints,\nand this page will be updated to reflect any changes.\n\nQuotas\n------\n\n[Quotas](/docs/quotas/overview)\nare default constraints applied to your project.\nWhen using generative features,\neach combination of model and region has its own [generative quota](#generative).\nIf you are using a paid\n[edition](/dialogflow/docs/editions),\nyou can [request a quota increase](#increase).\nThe purpose of quotas is to throttle service load per client,\nwhich protects a service from being overloaded\nand a client from unexpected resource usage.\n\nDialogflow quotas vary, depending on the\n[edition](/dialogflow/docs/editions)\nof your agent.\nQuotas apply to each project\nand are shared across all applications and IP addresses using a project.\n\nQuota time boundary details:\n\n- Per-month quotas are replenished on the 1st of each month at 12:00 AM Pacific Time.\n- Per-day quotas are replenished daily at 12:00 AM Pacific Time. When a Pacific Time daylight savings transition increases the length of a day, a proportional quota bonus will be granted. However, there is no equivalent deduction when a shorter day occurs due to the daylight savings transition.\n- Per-minute quotas are refreshed every 60 seconds on the minute.\n\nThe quotas listed in the [quotas table](#table)\nare the commonly encountered quotas.\nTo review all quotas, see the\n[Google Cloud console Dialogflow quotas](https://console.cloud.google.com/apis/api/dialogflow.googleapis.com/quotas)\npage.\n\n### Generative quotas\n\nWhen your agent uses Conversational Agents (Dialogflow CX)\n[generative features](/dialogflow/cx/docs/generative-deterministic),\neach combination of model and region have unique quotas.\n\n#### Quota identifier\n\nThe `ConversationalAgentLlmTokenConsumption` quota is a regional quota\nthat tracks token usage for large language models (LLMs) in Conversational Agents (Dialogflow CX).\nThis quota is measured across different LLM base models,\nand currently supports the following models:\n\n- gemini-1.5-pro\n- gemini-1.5-pro-002\n- gemini-1.5-flash\n- gemini-1.5-flash-002\n- gemini-2.0-flash-001\n- gemini-2.0-flash-lite-001\n- gemini-2.5-flash\n- gemini-2.5-flash-lite\n\nThe `ConversationalAgentLlmTokenConsumption` quota tracks LLM token usage\nacross the following Conversational Agents (Dialogflow CX) features:\n\n- Generators\n- Generative Fallback\n- Playbook\n- Datastore\n\nThe default limit for the `ConversationalAgentLlmTokenConsumption`\nquota is 600,000 tokens per minute.\n\n#### Multi-region quota increase request\n\nIf you need to request a quota increase for a multi-region,\nsubmit your request for one of the following specific regions:\n\n- For agents in the **US** and **Global** multi-regions, use **us-central1**.\n- For agents in the **EU** multi-region, use **europe-west4**.\n\n#### Visualize token usage by region and model\n\nTo gain insights into your LLM token consumption\nacross different regions and models,\nfollow these steps using\n[Metrics Explorer](/monitoring/charts/metrics-explorer):\n\n1. **Access Metrics Explorer:** Open [Metrics Explorer](https://console.cloud.google.com/monitoring/metrics-explorer).\n2. **Select the Metric:** Choose `Conversational Agent LLM tokens quota usage` as the metric you want to analyze.\n3. **Configure Aggregation and Aligner:**\n - Set the aggregation function to `Sum` to obtain the total token usage.\n - Click `Configure Aligner` to enable the calculation of changes between consecutive data points in your time series. This helps in understanding usage trends over time.\n4. **Define Aggregation Dimensions:** To break down the token usage, select `location` and `base_model` as the dimensions for aggregation. This will allow you to see how token consumption varies across different regions and models.\n5. **Set Aligner Function:** Choose `Sum` as the aligner function to calculate the total change in token usage between consecutive data points.\n\n### Quota increase request\n\nYou can request a\n[quota increase adjustment](/docs/quotas/help/request_increase)\nif necessary.\n\nIf you use different projects for Dialogflow agents and for authenticating\nwith service accounts, request a quota increase for the consumer project.\nFor more information, see [Using multiple projects for Dialogflow ES](/dialogflow/es/docs/multi-project)\nor [Using multiple projects for Conversational Agents (Dialogflow CX)](/dialogflow/cx/docs/concept/multi-project).\n\nFor [Dialogflow ES agents](/dialogflow/docs/editions#agent-types), make sure to\n[upgrade](/dialogflow/es/docs/agents-settings#change-editions) the agent to\nthe Dialogflow Essentials [edition](/dialogflow/docs/editions) before\nrequesting a quota increase.\n\n### Quotas table\n\n\nThe following terms are used to describe pricing and quotas:\n\n- **Request:** A *request* is defined as any API call to the Dialogflow service, whether direct with API usage or indirect with integration or console usage. Depending on the task and design of the agent, the number of requests needed for an end-user to accomplish a task with a Dialogflow agent can vary greatly.\n- **Session:** A *session* is a conversation between an end-user and a Dialogflow agent. A session remains active and its data is stored for 30 minutes after the last request is sent for the session. A session can be either a *chat session* or a *voice session* .\n - **Chat session:** A *chat session* only uses text for both requests and responses.\n - **Voice session:** A *voice session* uses audio for requests, responses, or both.\n- **Consumer projects and resource projects:** If you use multiple projects, it is possible that the project associated with your request authentication (consumer project) is not the same project that is associated with the agent in the request (resource project). In this case, the consumer project is used to determine prices and quotas. For more information, see [Using multiple projects for Dialogflow ES](/dialogflow/es/docs/multi-project) or [Using multiple projects for Conversational Agents (Dialogflow CX)](/dialogflow/cx/docs/concept/multi-project).\n\nThe following tables provide a quota comparison for editions by\n[agent type](/dialogflow/docs/editions#agent-types).\nUnless a feature is indicated as included,\nquotas are cumulative for all features used by a request. \n\n### Conversational Agents (Dialogflow CX) Agent\n\n### Dialogflow ES Agent\n\n### Agent Assist\n\nIf you are using Agent Assist, the quotas listed under the **Conversational Agents (Dialogflow CX) Agent**\nand **Dialogflow ES Agent** tabs also apply, according to which agent type you're using.\n\n\u003cbr /\u003e\n\nLimits\n------\n\n*Limits* are fixed constraints, which cannot be increased.\nMany resources and fields have count, duration, or length limitations,\nwhich are fixed constraints for the service implementation.\n\nThe following tables list commonly encountered limits.\nFeature-specific documentation and API reference documentation\nmay provide additional limits.\n\n### Count limits\n\n**Note:** Some resources are language-specific ([Conversational Agents (Dialogflow CX) documentation](/dialogflow/cx/docs/concept/agent-multilingual#lang-specific), [Dialogflow ES documentation](/dialogflow/es/docs/agents-multilingual#lang-specific)) and these limits are described as \"per *resource* and per language\". This means that you can define the maximum quantity of that resource for each language. For example, if your agent supports English and French, an intent can have at most 2000 English training phrases and 2000 French training phrases. All other language-independent resources have straightforward limits, because these resources are shared across all languages for your agent. \n\n### Conversational Agents (Dialogflow CX) Agent\n\n### Dialogflow ES Agent\n\n### Agent Assist\n\nIf you are using Agent Assist, the limits listed under the **Conversational Agents (Dialogflow CX)\nAgent** and **Dialogflow ES** tabs also apply according to which agent type\nyou're using.\n\n### Duration limits\n\n### Conversational Agents (Dialogflow CX) Agent\n\n### Dialogflow ES Agent\n\n### Length limits\n\n### Conversational Agents (Dialogflow CX) Agent\n\n### Dialogflow ES Agent\n\n### Size limits\n\n### Conversational Agents (Dialogflow CX) Agent\n\n### Dialogflow ES Agent"]]
