Google Dialogflow · Rate Limits

Google Dialogflow Rate Limits

Published Dialogflow quotas and limits, read from Google's own quotas page on 2026-09-12. This file replaces a 2026-05-04 scaffold whose numbers (10 rpm free / 100 rpm pro / 1000 rpm enterprise, X-RateLimit-* headers) were placeholder defaults and matched nothing Google publishes. Quotas apply per Google Cloud project and are shared across every application and IP using that project. Paid editions can request an increase; fixed limits cannot be raised.

Google Dialogflow Rate Limits is the machine-readable rate-limit profile for Google Dialogflow on the APIs.io network, in the API Commons Rate Limits shape.

It captures 25 rate-limit definitions, across the Dialogflow CX Edition, Dialogflow ES Trial Edition, Dialogflow ES Essentials Edition, Dialogflow ES (both editions), and Agent Assist (Essentials Edition) tiers, measuring requests_per_minute, tokens_per_minute, phone_minutes_per_minute, requests_per_day, and requests_per_month.

Limit state is signalled in the limit, remaining, reset, and retryAfter response headers, and an exhausted limit returns HTTP 429.

The profile also includes 3 backoff/retry policies defined and response codes documented for throttled, quotaExceeded, canonicalStatus, and detailsType.

Tagged areas include Conversational AI, Quotas, and Rate Limiting.

25 Limits Exhausted: HTTP 429 Quota: 429 limitremainingresetretryAfter
Transcribed from the provider's documentation on 2026-09-12 — cloud.google.com/dialogflow/quotas.
View Source
Conversational AIQuotasRate Limiting

Limits

Text requests project
requests_per_minute · minute
1200
All DetectIntent, StreamingDetectIntent and FulfillIntent requests that do not contain audio.
Audio input/output requests project
requests_per_minute · minute
600
Speech-to-text, text-to-speech and telephony.
Audio query operations with Chirp 3 HD voice project
requests_per_minute · minute
25
On exceeding this, Chirp 3 HD voices may fall back to Neural or Standard voices rather than failing the request.
Generative features (ConversationalAgentLlmTokenConsumption) project-and-region-and-model
tokens_per_minute · minute
600000
Regional quota, tracked per combination of base model and region across Generators, Generative Fallback, Playbooks and Data stores. Covers gemini-1.5-pro, -pro-002, -flash, -flash-002, gemini-2.0-flash-001, -flash-lite-001, gemini-2.5-flash and -flash-lite. Multi-region increase requests must be filed against us-central1 (US/Global) or europe-west4 (EU).
Dialogflow CX Phone Gateway project
phone_minutes_per_minute · minute
100
Design-time write requests project
requests_per_minute · minute
60
Calls that build or update an agent. This is the ceiling that constrains any agent doing bulk authoring.
Design-time read requests project
requests_per_minute · minute
300
Other session requests project
requests_per_minute · minute
100
For example setting or getting session entities.
Text requests project
requests_per_minute · minute
180
Audio input requests project
requests_per_minute · minute
100
Also capped at 1000 per day, 15,000 per month, and 60 seconds of audio per request.
Audio input requests (daily) project
requests_per_day · day
1000
Audio input requests (monthly) project
requests_per_month · month
15000
Phone gateway project
phone_minutes_per_minute · minute
3
Also 30 phone minutes per day and 500 per month; number reserved for 30 days; no toll-free number.
Mega agent requests project
requests_per_day · day
1000
Text requests project
requests_per_minute · minute
600
Audio input/output requests project
requests_per_minute · minute
300
Maximum 60 seconds of audio length per request.
Phone gateway project
phone_minutes_per_minute · minute
100
Design-time write requests project
requests_per_minute · minute
60
Design-time read requests project
requests_per_minute · minute
60
Other session requests project
requests_per_minute · minute
100
For example setting or getting session entities, or updating/querying context.
Conversation and participant management operations project
requests_per_minute · minute
300
Not available on the Trial Edition.
AnalyzeContent / StreamingAnalyzeContent operations project
requests_per_minute · minute
300
Concurrent bidi streaming sessions project
concurrent_requests · concurrent
50
Conversation summary suggestion polling project
requests_per_minute · minute
60
SearchKnowledge requests project
requests_per_minute · minute
60

Policies

Back-off
Stated in the SLA itself, not just in guidance: after the first error wait a minimum of 1 second, then increase the interval exponentially up to 32 seconds. Meeting this is a customer obligation for SLA credit eligibility.
Quota increase
Paid editions can request an increase through the Cloud console quotas page. ES agents must be upgraded to the Essentials edition first. If the authenticating project differs from the project holding the agent, the increase must be requested on the consumer project.
Session retention
A session remains active and its data is stored for 30 minutes after the last request.

Work with this as data

Every rate limit here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for rate limits

4 MCP tools reach this
  • find_rate_limitsBrowse and filter every rate limit in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This rate limit 
curl "https://apis.io/api/v1/rate-limits/google-dialogflow-rate-limits"
All rate limits 
curl "https://apis.io/api/v1/rate-limits?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.