This document contains the commonly encountered quotas and limits for use of Dialogflow. Information on how to find a complete list of quotas and limits is provided below. We reserve the right to change these constraints, and this page will be updated to reflect any changes.
Quotas
Quotas are default constraints applied to your project. If you are using a paid edition, you can request a quota increase. The purpose of quotas is to throttle service load per client, which protects a service from being overloaded and a client from unexpected resource usage.
Dialogflow quotas vary, depending on the edition of your agent. Quotas apply to each project and are shared across all applications and IP addresses using a project.
Quota time boundary details:
- Per-month quotas are replenished on the 1st of each month at 12:00 AM Pacific Time.
- 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.
- Per-minute quotas are refreshed every 60 seconds on the minute.
The quotas listed below are the commonly encountered quotas. To review all quotas, see the Google Cloud Console Dialogflow quotas page.
Quota increase request
You can request a quota increase if necessary.
If you use different projects for Dialogflow agents and for authenticating with service accounts, request a quota increase for the consumer project. For more information, see Using multiple projects for Dialogflow ES or Using multiple projects for Conversational Agents (Dialogflow CX).
For Dialogflow ES agents, make sure to upgrade the agent to the Dialogflow Essentials edition before requesting a quota increase.
Quotas table
The following terms are used to describe pricing and quotas:
- 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.
- 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.
- Chat session: A chat session only uses text for both requests and responses.
- Voice session: A voice session uses audio for requests, responses, or both.
- 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 or Using multiple projects for Conversational Agents (Dialogflow CX).
The following tables provide a quota comparison for editions by agent type. Unless a feature is indicated as included, quotas are cumulative for all features used by a request.
Conversational Agents (Dialogflow CX) Agent
Feature | Conversational Agents (Dialogflow CX) Edition |
---|---|
Text (includes all DetectIntent, StreamingDetectIntent, and FulfillIntent requests that do not contain audio) |
1200 requests per minute |
Audio input/output (speech recognition, speech-to-text, STT, speech synthesis, text-to-speech, TTS, telephony) |
600 requests per minute |
Dialogflow CX Phone Gateway Includes audio input and output. |
100 total phone minutes per minute ‡ |
Design-time write requests For example, calls to build or update an agent. |
60 requests per minute |
Design-time read requests For example, calls to list or get agent resources. |
200 requests per minute |
Other session requests For example, setting or getting session entities. |
100 requests per minute |
Symbol | Description |
---|---|
‡ | "Phone minutes per minute" is the total sum of time per minute that is used by all users making calls through the phone system. For example: in one 60-second time period one user is on for 60 seconds, a second for 30 seconds, and a third for 30 seconds. This is calculated as 2 minutes per minute. More minutes per minute allows more users to use the system simultaneously. |
Dialogflow ES Agent
Feature | Trial Edition | Essentials Edition |
---|---|---|
Text (includes all DetectIntent and StreamingDetectIntent requests that do not contain audio) |
180 requests per minute ¶ | 600 requests per minute ¶ |
Audio input (also known as speech recognition, speech-to-text, STT) |
100 requests per minute † 1000 requests per day † 15,000 requests per month † Maximum 60 seconds of audio length per request † |
300 requests per minute † Maximum 60 seconds of audio length per request † |
Audio output (also known as speech synthesis, text-to-speech, TTS) |
Same as audio input | Same as audio input |
Knowledge connectors (Beta) | Maximum 10 MB total document size 1000 requests per month 100 requests per day |
Unlimited # |
Sentiment analysis | Not available | Unlimited # |
Dialogflow ES phone gateway Includes audio input and output. |
Toll-free number: Not available 3 total phone minutes per minute ‡ 30 phone minutes per day 500 phone minutes per month Phone number reserved for 30 days |
100 total phone minutes per minute ‡ |
Mega agent | 1000 requests per day | Unlimited # |
Design-time write requests For example, calls to build or update an agent. |
60 requests per minute | 60 requests per minute |
Design-time read requests For example, calls to list or get agent resources. |
60 requests per minute | 60 requests per minute |
Other session requests For example, setting or getting session entities or updating/querying context. |
100 requests per minute | 100 requests per minute |
Symbol | Description |
---|---|
† | Each StreamingDetectIntent stream is considered a single request, even though the stream might include multiple frames of StreamingDetectIntentRequest audio within the stream. |
‡ | "Phone minutes per minute" is the total sum of time per minute that is used by all users making calls through the phone system. For example: in one 60-second time period one user is on for 60 seconds, a second for 30 seconds, and a third for 30 seconds. This is calculated as 2 minutes per minute. More minutes per minute allows more users to use the system simultaneously. |
# | Features marked as unlimited are still potentially limited by use of other features. For example, if your edition provides unlimited quota for knowledge connectors, a text request that uses knowledge connectors is still limited by the quota for text requests. |
¶ | Google Assistant audio input and output is considered a text request. |
Agent Assist
If you are using Agent Assist, the quotas listed under the Conversational Agents (Dialogflow CX) Agent and Dialogflow ES Agent tabs also apply, according to which agent type you're using.
Feature | Trial Edition | Essentials Edition |
---|---|---|
Agent Assist conversation other operations Includes all requests that manage Conversations and Participants. |
Not available | 300 requests per minute |
Agent Assist analyze text/audio operations Includes all AnalyzeContent or StreamingAnalyzeContent requests for any conversation stage. This includes all such requests involving text, speech synthesis, and/or speech recognition. |
Not available | 300 requests per minute |
Agent Assist conversation summary suggestion polling requests Includes all requests for getting conversation summaries. |
Not available | 300 requests per minute |
Limits
Limits are fixed constraints, which cannot be increased. Many resources and fields have count, duration, or length limitations, which are fixed constraints for the service implementation.
The following tables list commonly encountered limits. Feature-specific documentation and API reference documentation may provide additional limits.
Count limits
Conversational Agents (Dialogflow CX) Agent
Description | Limit |
---|---|
Maximum number of agents per Google Cloud project | 1000 |
Maximum number of flows per agent | 50 |
Maximum number of entity types per agent | 250 |
Maximum number of webhooks per agent | 100 |
Maximum number of environments per agent | 20 |
Maximum number of test cases per agent | 2000 |
Maximum number of changelog per agent | 20,000 |
Maximum number of pages per flow | 250 |
Maximum number of route groups per flow | 100 |
Maximum number of versions per flow | 20 |
Maximum number of intents per agent | 10,000 |
Maximum number of referenced intents per flow | 2000 |
Maximum number of training phrases per intent and per language (except "Default Negative Intent") | 2000 |
Maximum number of training phrases per flow and per language | 100,000 |
Maximum number of parameters per intent | 20 |
Maximum number of entity entries per entity | 30,000 |
Maximum number of entity synonyms per entity entry | 200 |
Maximum number of entity reference values and synonyms per agent and per language | 1,000,000 |
Maximum number of parameters per page | 20 |
Maximum number of routes per page | 2000 |
Maximum number of event handlers per page | 100 |
Maximum number of routes per route group | 2000 |
Maximum number of playbooks per agent | no limit |
Maximum number of playbook invocations in one conversational turn | 3 |
Maximum number of LLM calls per playbook invocation in same conversational turn | 10 |
Maximum number of playbook examples per agent | With the default example retrieval strategy, the system will automatically limit the number of examples to fit in the token limit of the model that is being used, based on the relevance of the examples to the session context. |
Dialogflow ES Agent
Description | Limit |
---|---|
Maximum number of agents per region and per Google Cloud project ¶ | 1 |
Maximum number of intents | 2000 |
Maximum number of entity types | 250 |
Maximum number of training phrases per intent and per language | 2000 |
Maximum number of training phrases per agent and per language | 100,000 |
Maximum number of entity entries | 30000 |
Maximum number of entity synonyms per entity entry | 200 |
Maximum number of entity reference values and synonyms per agent and per language | 1,000,000 |
Maximum number of parameters per intent | 20 |
Maximum number of input contexts per intent | 5 |
Maximum number of output contexts per intent | 30 |
Maximum number of text responses per intent and per language | 30 |
Maximum number of prompts per parameter and per language | 30 |
Maximum number of environments per agent | 10 |
Maximum number of versions per agent | 1000 |
¶ | Maximum number of agents per account depends on the number of Google projects you can create in your account. See how to request more projects. |
Agent Assist
If you are using Agent Assist, the limits listed under the Conversational Agents (Dialogflow CX) Agent and Dialogflow ES tabs also apply according to which agent type you're using.
Description | Limit |
---|---|
Minimum number of conversations required for model training | 30,000 |
Maximum number of models trained concurrently per project | 1 |
Maximum number of training node GPU hours per month | 4200 |
Duration limits
Conversational Agents (Dialogflow CX) Agent
Description | Limit |
---|---|
Maximum timeout per webhook | 30 seconds |
Maximum audio input duration | 120 seconds |
Dialogflow ES Agent
Description | Limit |
---|---|
Maximum webhook timeout | 5 seconds |
Maximum telephony call duration | 3.5 hours |
Length limits
Conversational Agents (Dialogflow CX) Agent
Description | Limit |
---|---|
Maximum training phrase length | 768 characters |
Maximum text response length | 4,000 characters |
Maximum text input length for detect intent matched by non-generative intents or parameters | 256 characters |
Dialogflow ES Agent
Description | Limit |
---|---|
Minimum agent name length | 1 character |
Maximum agent name length | 150 characters |
Maximum agent description length | 500 characters |
Maximum intent name length | 100 characters |
Maximum entity type name length | 30 characters |
Maximum training phrase length | 768 characters |
Maximum action name length | 250 characters |
Maximum context name length | 250 characters |
Maximum entry value length | 512 characters |
Maximum parameter name length | 30 characters |
Maximum text response length | 4000 characters |
Maximum detect intent text input length * | 256 characters |
Maximum event name length | 150 characters |
* | This limit is enforced by the Dialogflow service. If you are using an integration, the integration platform may have a smaller limit. See the details for your integration. |
Size limits
Conversational Agents (Dialogflow CX) Agent
Description | Limit |
---|---|
Maximum agent size for agent export/restore from/to a local file system * | ~10 MB |
Maximum speech synthesis request size | See the TTS API content limits |
Symbol | Description |
---|---|
* | Use the Cloud Storage option to export and restore agents exceeding this limit. |
Dialogflow ES Agent
Description | Limit |
---|---|
Maximum agent size (unzipped content) for agent import/restore | 50 MB |
Maximum speech synthesis request size | See the TTS API content limits |