Dialogflow pricing

Dialogflow is priced monthly based on the edition and the requests made during the month.

Conversational Agents (Dialogflow CX) no charge trial

New customers receive a $600 credit for a no charge trial of Conversational Agents (Dialogflow CX) that can be cancelled at any time. This credit activates automatically upon using Conversational Agents (Dialogflow CX) for the first time and expires after 12 months. This is a Conversational Agents (Dialogflow CX)-specific extension of the Google Cloud no charge trial.

Pricing 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 pricing comparison for editions by agent type. Unless a feature is indicated as included, pricing is cumulative for all features used by a request.

Conversational Agents (Dialogflow CX) has a simpler pricing model than Dialogflow ES. For example, sentiment analysis has no charge for Conversational Agents (Dialogflow CX), but sentiment analysis incurs additional charges for Dialogflow ES.

Conversational Agents (Dialogflow CX) Agent

Feature Conversational Agents (Dialogflow CX) Edition
Text
(includes all DetectIntent, StreamingDetectIntent, and FulfillIntent requests that do not contain audio) 		$0.007 per request
Audio input/output
(speech recognition, speech-to-text, STT, speech synthesis, text-to-speech, TTS, telephony) 		$0.001 per second *
Generative requests
 See generative pricing
Design-time write requests
For example, calls to build or update an agent. 		no charge
Design-time read requests
For example, calls to list or get agent resources. 		no charge
Other session requests
For example, setting or getting session entities. 		no charge
Symbol Description
* Each voice session is charged $0.001 per second of audio, with a minimum of one second. For example, a 15 second voice session is charged at $0.015, while a 61 second voice session is charged at $0.061. The previous minimum billed duration of one minute has been removed effective June 30, 2023. The total audio used for a voice session is the sum of both TTS and STT used by all requests and responses for the voice session. The total billed audio processing duration is independent of any no-charge, non-audio processing (API latency, webhook processing, and so on) which may occur before, during, or after audio processing. Voice session requests that make use of TTS or STT contribute to the total cost for the session, but these requests do not incur a per-request charge. If a voice session has any requests that do not use TTS or STT, these requests are charged per-request as defined above.

Dialogflow ES Agent

Feature Trial Edition Essentials Edition
Text
(includes all DetectIntent and StreamingDetectIntent requests that do not contain audio) 		no charge $0.002 per request ¶
Audio input
(also known as speech recognition, speech-to-text, STT) 		no charge * $0.0065 per 15 seconds of audio †
Audio output
(also known as speech synthesis, text-to-speech, TTS) 		no charge * Standard voices:
$4 per 1 million characters

WaveNet voices:
$16 per 1 million characters
Knowledge connectors (Beta) no charge * no charge
Sentiment analysis Not available 0-1 million requests:
$1.00 per 1,000 requests

1-5 million requests:
$0.50 per 1,000 requests

5-20 million requests:
$0.25 per 1,000 requests
Dialogflow ES phone gateway
Includes audio input and output. 		Tolled number:
no charge *

Toll-free number:
Not available		 Tolled number:
$0.05 per minute of phone call processed ‡

Toll-free number:
$0.06 per minute of phone call processed ‡
Mega agent no charge * <=2k intents:
$0.002 per request §

>2k intents:
$0.006 per request §
Design-time write requests
For example, calls to build or update an agent. 		no charge $0 per request
Design-time read requests
For example, calls to list or get agent resources. 		no charge $0 per request
Other session requests
For example, setting or getting session entities or updating/querying context. 		no charge $0 per request
Symbol Description
* While use of the Dialogflow ES Trial Edition is available at no charge, there are limits on the amount of requests that you can make. For details, see Quotas & Limits.
† Each request is rounded up to the nearest increment of 15 seconds. For example, if you make three separate requests, each containing 7 seconds of audio, you are billed for 45 seconds (3 × 15 seconds) of audio. Fractions of seconds are included when rounding up to the nearest increment of 15 seconds. That is, 15.14 seconds are rounded up and billed as 30 seconds.
‡ Call duration time is rounded up to whole minutes. For example, if your call takes 61 seconds, you are billed for 2 minutes.
§ When a request is made with a potential for any one of N intents as a match, Dialogflow ES searches through all N of those intents. When N is large, the processing cost is increased. The number of intents used for mega agent pricing is determined by the number of intents searched for a request. If a request explicitly specifies sub-agents, this is the sum of all intents for the supplied sub-agents. If a request does not specify sub-agents, this is the sum of all intents for all sub-agents of the mega agent.
All Google Assistant requests, including audio input and output, are not billed. Google Assistant audio input and output is considered a text request.

Agent Assist

Feature Trial Edition Essentials Edition
Agent Assist conversation other operations
Includes all requests that manage Conversations and Participants. 		Not available no charge
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 Charged according to underlying operations described in the Conversational Agents (Dialogflow CX) Agent and Dialogflow ES Agent tabs.

Network

There are no additional data transfer charges associated with Dialogflow. All Dialogflow-specific charges are described in the pricing table.

Google Cloud Platform costs

If you use other Google Cloud resources in tandem with Dialogflow, such as Google App Engine instances, then you will also be billed for the use of those services. See the Google Cloud Pricing Calculator to determine other costs based on current rates.

To view your current billing status in the Cloud console, including usage and your current bill, see the Billing page. For more details about managing your account, see the Cloud Billing Documentation or Billing and Payments Support.

What's next

Request a custom quote

With Google Cloud's pay-as-you-go pricing, you only pay for the services you use. Connect with our sales team to get a custom quote for your organization.
Contact sales