---
title: Gemini API
description: Monitor request volume, token usage, and quota consumption for the Gemini API.
breadcrumbs: Docs > Integrations > Gemini API
---

> For the complete documentation index, see [llms.txt](https://docs.datadoghq.com/llms.txt).

# Gemini API
Integration version1.0.0
{% callout %}
# Important note for users on the following Datadog sites: us2.ddog-gov.com

{% alert level="info" %}
To find out if this integration is available in your organization, see your [Datadog Integrations](https://app.datadoghq.com/integrations) page or ask your organization administrator.

To initiate an exception request to enable this integration for your organization, email [support@ddog-gov.com](mailto:support@ddog-gov.com).
{% /alert %}

{% /callout %}

## Overview{% #overview %}

The Gemini API powers generative AI features like text, image, and content generation. Use the Datadog Google Cloud Platform integration to monitor request volume, token usage, and quota consumption for the Gemini API.

## Setup{% #setup %}

### Installation{% #installation %}

If you haven't already, set up the [Google Cloud Platform integration](https://docs.datadoghq.com/integrations/google-cloud-platform.md) first. There are no other installation steps.

## Data Collected{% #data-collected %}

### Metrics{% #metrics %}

|  |
|  |
| **gcp.generativelanguage.generate_content_usage_output_token_count**(count)                                       | Generate content usage output token count.                                                                                                                                                                        |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_batches_paid_tier_1.exceeded**(count)     | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_batches_paid_tier_1. After sampling, data is not visible for up to 150 seconds.    |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_batches_paid_tier_1.limit**(gauge)        | Current limit on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_batches_paid_tier_1.                                                                                        |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_batches_paid_tier_1.usage**(gauge)        | Current usage on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_batches_paid_tier_1. After sampling, data is not visible for up to 150 seconds.                             |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_batches_paid_tier_2.exceeded**(count)     | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_batches_paid_tier_2. After sampling, data is not visible for up to 150 seconds.    |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_batches_paid_tier_2.limit**(gauge)        | Current limit on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_batches_paid_tier_2.                                                                                        |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_batches_paid_tier_2.usage**(gauge)        | Current usage on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_batches_paid_tier_2. After sampling, data is not visible for up to 150 seconds.                             |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_batches_paid_tier_3.exceeded**(count)     | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_batches_paid_tier_3. After sampling, data is not visible for up to 150 seconds.    |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_batches_paid_tier_3.limit**(gauge)        | Current limit on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_batches_paid_tier_3.                                                                                        |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_batches_paid_tier_3.usage**(gauge)        | Current usage on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_batches_paid_tier_3. After sampling, data is not visible for up to 150 seconds.                             |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_tokens_paid_tier_1.exceeded**(count)      | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_tokens_paid_tier_1. After sampling, data is not visible for up to 150 seconds.     |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_tokens_paid_tier_1.limit**(gauge)         | Current limit on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_tokens_paid_tier_1.                                                                                         |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_tokens_paid_tier_1.usage**(gauge)         | Current usage on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_tokens_paid_tier_1. After sampling, data is not visible for up to 150 seconds.                              |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_tokens_paid_tier_2.exceeded**(count)      | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_tokens_paid_tier_2. After sampling, data is not visible for up to 150 seconds.     |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_tokens_paid_tier_2.limit**(gauge)         | Current limit on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_tokens_paid_tier_2.                                                                                         |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_tokens_paid_tier_2.usage**(gauge)         | Current usage on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_tokens_paid_tier_2. After sampling, data is not visible for up to 150 seconds.                              |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_tokens_paid_tier_3.exceeded**(count)      | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_tokens_paid_tier_3. After sampling, data is not visible for up to 150 seconds.     |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_tokens_paid_tier_3.limit**(gauge)         | Current limit on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_tokens_paid_tier_3.                                                                                         |
| **gcp.generativelanguage.quota.embed_content_batch_active_concurrent_tokens_paid_tier_3.usage**(gauge)         | Current usage on quota metric generativelanguage.googleapis.com/embed_content_batch_active_concurrent_tokens_paid_tier_3. After sampling, data is not visible for up to 150 seconds.                              |
| **gcp.generativelanguage.quota.embed_content_free_tier_requests.exceeded**(count)                                  | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_free_tier_requests. After sampling, data is not visible for up to 150 seconds.                             |
| **gcp.generativelanguage.quota.embed_content_free_tier_requests.limit**(gauge)                                     | Current limit on quota metric generativelanguage.googleapis.com/embed_content_free_tier_requests.                                                                                                                 |
| **gcp.generativelanguage.quota.embed_content_free_tier_requests.usage**(count)                                     | Current usage on quota metric generativelanguage.googleapis.com/embed_content_free_tier_requests. After sampling, data is not visible for up to 150 seconds.                                                      |
| **gcp.generativelanguage.quota.embed_content_free_tier_tokens.exceeded**(count)                                    | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_free_tier_tokens. After sampling, data is not visible for up to 150 seconds.                               |
| **gcp.generativelanguage.quota.embed_content_free_tier_tokens.limit**(gauge)                                       | Current limit on quota metric generativelanguage.googleapis.com/embed_content_free_tier_tokens.                                                                                                                   |
| **gcp.generativelanguage.quota.embed_content_free_tier_tokens.usage**(count)                                       | Current usage on quota metric generativelanguage.googleapis.com/embed_content_free_tier_tokens. After sampling, data is not visible for up to 150 seconds.                                                        |
| **gcp.generativelanguage.quota.embed_content_paid_tier_2_requests.exceeded**(count)                               | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_2_requests. After sampling, data is not visible for up to 150 seconds.                           |
| **gcp.generativelanguage.quota.embed_content_paid_tier_2_requests.limit**(gauge)                                  | Current limit on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_2_requests.                                                                                                               |
| **gcp.generativelanguage.quota.embed_content_paid_tier_2_requests.usage**(count)                                  | Current usage on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_2_requests. After sampling, data is not visible for up to 150 seconds.                                                    |
| **gcp.generativelanguage.quota.embed_content_paid_tier_2_tokens.exceeded**(count)                                 | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_2_tokens. After sampling, data is not visible for up to 150 seconds.                             |
| **gcp.generativelanguage.quota.embed_content_paid_tier_2_tokens.limit**(gauge)                                    | Current limit on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_2_tokens.                                                                                                                 |
| **gcp.generativelanguage.quota.embed_content_paid_tier_2_tokens.usage**(count)                                    | Current usage on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_2_tokens. After sampling, data is not visible for up to 150 seconds.                                                      |
| **gcp.generativelanguage.quota.embed_content_paid_tier_3_requests.exceeded**(count)                               | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_3_requests. After sampling, data is not visible for up to 150 seconds.                           |
| **gcp.generativelanguage.quota.embed_content_paid_tier_3_requests.limit**(gauge)                                  | Current limit on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_3_requests.                                                                                                               |
| **gcp.generativelanguage.quota.embed_content_paid_tier_3_requests.usage**(count)                                  | Current usage on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_3_requests. After sampling, data is not visible for up to 150 seconds.                                                    |
| **gcp.generativelanguage.quota.embed_content_paid_tier_3_tokens.exceeded**(count)                                 | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_3_tokens. After sampling, data is not visible for up to 150 seconds.                             |
| **gcp.generativelanguage.quota.embed_content_paid_tier_3_tokens.limit**(gauge)                                    | Current limit on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_3_tokens.                                                                                                                 |
| **gcp.generativelanguage.quota.embed_content_paid_tier_3_tokens.usage**(count)                                    | Current usage on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_3_tokens. After sampling, data is not visible for up to 150 seconds.                                                      |
| **gcp.generativelanguage.quota.embed_content_paid_tier_requests.exceeded**(count)                                  | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_requests. After sampling, data is not visible for up to 150 seconds.                             |
| **gcp.generativelanguage.quota.embed_content_paid_tier_requests.limit**(gauge)                                     | Current limit on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_requests.                                                                                                                 |
| **gcp.generativelanguage.quota.embed_content_paid_tier_requests.usage**(count)                                     | Current usage on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_requests. After sampling, data is not visible for up to 150 seconds.                                                      |
| **gcp.generativelanguage.quota.embed_content_paid_tier_tokens.exceeded**(count)                                    | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_tokens. After sampling, data is not visible for up to 150 seconds.                               |
| **gcp.generativelanguage.quota.embed_content_paid_tier_tokens.limit**(gauge)                                       | Current limit on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_tokens.                                                                                                                   |
| **gcp.generativelanguage.quota.embed_content_paid_tier_tokens.usage**(count)                                       | Current usage on quota metric generativelanguage.googleapis.com/embed_content_paid_tier_tokens. After sampling, data is not visible for up to 150 seconds.                                                        |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_batches_paid_tier_1.exceeded**(count)  | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_batches_paid_tier_1. After sampling, data is not visible for up to 150 seconds. |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_batches_paid_tier_1.limit**(gauge)     | Current limit on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_batches_paid_tier_1.                                                                                     |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_batches_paid_tier_1.usage**(gauge)     | Current usage on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_batches_paid_tier_1. After sampling, data is not visible for up to 150 seconds.                          |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_batches_paid_tier_2.exceeded**(count)  | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_batches_paid_tier_2. After sampling, data is not visible for up to 150 seconds. |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_batches_paid_tier_2.limit**(gauge)     | Current limit on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_batches_paid_tier_2.                                                                                     |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_batches_paid_tier_2.usage**(gauge)     | Current usage on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_batches_paid_tier_2. After sampling, data is not visible for up to 150 seconds.                          |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_batches_paid_tier_3.exceeded**(count)  | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_batches_paid_tier_3. After sampling, data is not visible for up to 150 seconds. |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_batches_paid_tier_3.limit**(gauge)     | Current limit on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_batches_paid_tier_3.                                                                                     |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_batches_paid_tier_3.usage**(gauge)     | Current usage on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_batches_paid_tier_3. After sampling, data is not visible for up to 150 seconds.                          |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_tokens_paid_tier_1.exceeded**(count)   | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_tokens_paid_tier_1. After sampling, data is not visible for up to 150 seconds.  |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_tokens_paid_tier_1.limit**(gauge)      | Current limit on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_tokens_paid_tier_1.                                                                                      |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_tokens_paid_tier_1.usage**(gauge)      | Current usage on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_tokens_paid_tier_1. After sampling, data is not visible for up to 150 seconds.                           |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_tokens_paid_tier_2.exceeded**(count)   | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_tokens_paid_tier_2. After sampling, data is not visible for up to 150 seconds.  |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_tokens_paid_tier_2.limit**(gauge)      | Current limit on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_tokens_paid_tier_2.                                                                                      |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_tokens_paid_tier_2.usage**(gauge)      | Current usage on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_tokens_paid_tier_2. After sampling, data is not visible for up to 150 seconds.                           |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_tokens_paid_tier_3.exceeded**(count)   | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_tokens_paid_tier_3. After sampling, data is not visible for up to 150 seconds.  |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_tokens_paid_tier_3.limit**(gauge)      | Current limit on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_tokens_paid_tier_3.                                                                                      |
| **gcp.generativelanguage.quota.generate_content_batch_active_concurrent_tokens_paid_tier_3.usage**(gauge)      | Current usage on quota metric generativelanguage.googleapis.com/generate_content_batch_active_concurrent_tokens_paid_tier_3. After sampling, data is not visible for up to 150 seconds.                           |
| **gcp.generativelanguage.quota.generate_content_free_tier_input_token_count.exceeded**(count)                    | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_free_tier_input_token_count. After sampling, data is not visible for up to 150 seconds.                 |
| **gcp.generativelanguage.quota.generate_content_free_tier_input_token_count.limit**(gauge)                       | Current limit on quota metric generativelanguage.googleapis.com/generate_content_free_tier_input_token_count.                                                                                                     |
| **gcp.generativelanguage.quota.generate_content_free_tier_input_token_count.usage**(count)                       | Current usage on quota metric generativelanguage.googleapis.com/generate_content_free_tier_input_token_count. After sampling, data is not visible for up to 150 seconds.                                          |
| **gcp.generativelanguage.quota.generate_content_free_tier_input_tokens_internal.usage**(count)                   | Current usage on quota metric generativelanguage.googleapis.com/generate_content_free_tier_input_tokens_internal. After sampling, data is not visible for up to 150 seconds.                                      |
| **gcp.generativelanguage.quota.generate_content_free_tier_requests.exceeded**(count)                               | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_free_tier_requests. After sampling, data is not visible for up to 150 seconds.                          |
| **gcp.generativelanguage.quota.generate_content_free_tier_requests.limit**(gauge)                                  | Current limit on quota metric generativelanguage.googleapis.com/generate_content_free_tier_requests.                                                                                                              |
| **gcp.generativelanguage.quota.generate_content_free_tier_requests.usage**(count)                                  | Current usage on quota metric generativelanguage.googleapis.com/generate_content_free_tier_requests. After sampling, data is not visible for up to 150 seconds.                                                   |
| **gcp.generativelanguage.quota.generate_content_free_tier_requests_internal.usage**(count)                        | Current usage on quota metric generativelanguage.googleapis.com/generate_content_free_tier_requests_internal. After sampling, data is not visible for up to 150 seconds.                                          |
| **gcp.generativelanguage.quota.generate_content_paid_tier_1_input_tokens_internal.usage**(count)                | Current usage on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_1_input_tokens_internal. After sampling, data is not visible for up to 150 seconds.                                    |
| **gcp.generativelanguage.quota.generate_content_paid_tier_1_requests_internal.usage**(count)                     | Current usage on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_1_requests_internal. After sampling, data is not visible for up to 150 seconds.                                        |
| **gcp.generativelanguage.quota.generate_content_paid_tier_2_input_token_count.exceeded**(count)                 | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_2_input_token_count. After sampling, data is not visible for up to 150 seconds.               |
| **gcp.generativelanguage.quota.generate_content_paid_tier_2_input_token_count.limit**(gauge)                    | Current limit on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_2_input_token_count.                                                                                                   |
| **gcp.generativelanguage.quota.generate_content_paid_tier_2_input_token_count.usage**(count)                    | Current usage on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_2_input_token_count. After sampling, data is not visible for up to 150 seconds.                                        |
| **gcp.generativelanguage.quota.generate_content_paid_tier_2_requests.exceeded**(count)                            | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_2_requests. After sampling, data is not visible for up to 150 seconds.                        |
| **gcp.generativelanguage.quota.generate_content_paid_tier_2_requests.limit**(gauge)                               | Current limit on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_2_requests.                                                                                                            |
| **gcp.generativelanguage.quota.generate_content_paid_tier_2_requests.usage**(count)                               | Current usage on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_2_requests. After sampling, data is not visible for up to 150 seconds.                                                 |
| **gcp.generativelanguage.quota.generate_content_paid_tier_2_requests_internal.usage**(count)                     | Current usage on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_2_requests_internal. After sampling, data is not visible for up to 150 seconds.                                        |
| **gcp.generativelanguage.quota.generate_content_paid_tier_3_input_token_count.exceeded**(count)                 | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_3_input_token_count. After sampling, data is not visible for up to 150 seconds.               |
| **gcp.generativelanguage.quota.generate_content_paid_tier_3_input_token_count.limit**(gauge)                    | Current limit on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_3_input_token_count.                                                                                                   |
| **gcp.generativelanguage.quota.generate_content_paid_tier_3_input_token_count.usage**(count)                    | Current usage on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_3_input_token_count. After sampling, data is not visible for up to 150 seconds.                                        |
| **gcp.generativelanguage.quota.generate_content_paid_tier_3_requests.exceeded**(count)                            | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_3_requests. After sampling, data is not visible for up to 150 seconds.                        |
| **gcp.generativelanguage.quota.generate_content_paid_tier_3_requests.limit**(gauge)                               | Current limit on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_3_requests.                                                                                                            |
| **gcp.generativelanguage.quota.generate_content_paid_tier_3_requests.usage**(count)                               | Current usage on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_3_requests. After sampling, data is not visible for up to 150 seconds.                                                 |
| **gcp.generativelanguage.quota.generate_content_paid_tier_3_requests_internal.usage**(count)                     | Current usage on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_3_requests_internal. After sampling, data is not visible for up to 150 seconds.                                        |
| **gcp.generativelanguage.quota.generate_content_paid_tier_input_token_count.exceeded**(count)                    | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_input_token_count. After sampling, data is not visible for up to 150 seconds.                 |
| **gcp.generativelanguage.quota.generate_content_paid_tier_input_token_count.limit**(gauge)                       | Current limit on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_input_token_count.                                                                                                     |
| **gcp.generativelanguage.quota.generate_content_paid_tier_input_token_count.usage**(count)                       | Current usage on quota metric generativelanguage.googleapis.com/generate_content_paid_tier_input_token_count. After sampling, data is not visible for up to 150 seconds.                                          |
| **gcp.generativelanguage.quota.generate_content_search_request_usage.exceeded**(count)                             | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_content_search_request_usage. After sampling, data is not visible for up to 150 seconds.                        |
| **gcp.generativelanguage.quota.generate_content_search_request_usage.limit**(gauge)                                | Current limit on quota metric generativelanguage.googleapis.com/generate_content_search_request_usage.                                                                                                            |
| **gcp.generativelanguage.quota.generate_content_search_request_usage.usage**(count)                                | Current usage on quota metric generativelanguage.googleapis.com/generate_content_search_request_usage. After sampling, data is not visible for up to 150 seconds.                                                 |
| **gcp.generativelanguage.quota.generate_requests_per_model.exceeded**(count)                                        | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/generate_requests_per_model. After sampling, data is not visible for up to 150 seconds.                                  |
| **gcp.generativelanguage.quota.generate_requests_per_model.limit**(gauge)                                           | Current limit on quota metric generativelanguage.googleapis.com/generate_requests_per_model.                                                                                                                      |
| **gcp.generativelanguage.quota.generate_requests_per_model.usage**(count)                                           | Current usage on quota metric generativelanguage.googleapis.com/generate_requests_per_model. After sampling, data is not visible for up to 150 seconds.                                                           |
| **gcp.generativelanguage.quota.generate_requests_per_model_per_day_internal.usage**(count)                       | Current usage on quota metric generativelanguage.googleapis.com/generate_requests_per_model_per_day_internal. After sampling, data is not visible for up to 150 seconds.                                          |
| **gcp.generativelanguage.quota.map_grounding_request_free_tier.exceeded**(count)                                   | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/map_grounding_request_free_tier. After sampling, data is not visible for up to 150 seconds.                              |
| **gcp.generativelanguage.quota.map_grounding_request_free_tier.limit**(gauge)                                      | Current limit on quota metric generativelanguage.googleapis.com/map_grounding_request_free_tier.                                                                                                                  |
| **gcp.generativelanguage.quota.map_grounding_request_free_tier.usage**(count)                                      | Current usage on quota metric generativelanguage.googleapis.com/map_grounding_request_free_tier. After sampling, data is not visible for up to 150 seconds.                                                       |
| **gcp.generativelanguage.quota.map_grounding_request_paid.exceeded**(count)                                         | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/map_grounding_request_paid. After sampling, data is not visible for up to 150 seconds.                                   |
| **gcp.generativelanguage.quota.map_grounding_request_paid.limit**(gauge)                                            | Current limit on quota metric generativelanguage.googleapis.com/map_grounding_request_paid.                                                                                                                       |
| **gcp.generativelanguage.quota.map_grounding_request_paid.usage**(count)                                            | Current usage on quota metric generativelanguage.googleapis.com/map_grounding_request_paid. After sampling, data is not visible for up to 150 seconds.                                                            |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model.exceeded**(count)                          | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model. After sampling, data is not visible for up to 150 seconds.                      |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model.limit**(gauge)                             | Current limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model.                                                                                                          |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model.usage**(count)                             | Current usage on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model. After sampling, data is not visible for up to 150 seconds.                                               |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_free_tier.exceeded**(count)              | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_free_tier. After sampling, data is not visible for up to 150 seconds.            |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_free_tier.limit**(gauge)                 | Current limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_free_tier.                                                                                                |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_free_tier.usage**(count)                 | Current usage on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_free_tier. After sampling, data is not visible for up to 150 seconds.                                     |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_paid_tier_2.exceeded**(count)           | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_paid_tier_2. After sampling, data is not visible for up to 150 seconds.          |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_paid_tier_2.limit**(gauge)              | Current limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_paid_tier_2.                                                                                              |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_paid_tier_2.usage**(count)              | Current usage on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_paid_tier_2. After sampling, data is not visible for up to 150 seconds.                                   |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_paid_tier_3.exceeded**(count)           | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_paid_tier_3. After sampling, data is not visible for up to 150 seconds.          |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_paid_tier_3.limit**(gauge)              | Current limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_paid_tier_3.                                                                                              |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_paid_tier_3.usage**(count)              | Current usage on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_paid_tier_3. After sampling, data is not visible for up to 150 seconds.                                   |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_per_day.exceeded**(count)                | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_per_day. After sampling, data is not visible for up to 150 seconds.              |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_per_day.limit**(gauge)                   | Current limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_per_day.                                                                                                  |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_per_day.usage**(count)                   | Current usage on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_per_day. After sampling, data is not visible for up to 150 seconds.                                       |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_per_day_free_tier.exceeded**(count)    | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_per_day_free_tier. After sampling, data is not visible for up to 150 seconds.    |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_per_day_free_tier.limit**(gauge)       | Current limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_per_day_free_tier.                                                                                        |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_per_day_free_tier.usage**(count)       | Current usage on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_per_day_free_tier. After sampling, data is not visible for up to 150 seconds.                             |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_per_day_paid_tier_2.exceeded**(count) | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_per_day_paid_tier_2. After sampling, data is not visible for up to 150 seconds.  |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_per_day_paid_tier_2.limit**(gauge)    | Current limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_per_day_paid_tier_2.                                                                                      |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_per_day_paid_tier_2.usage**(count)    | Current usage on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_per_day_paid_tier_2. After sampling, data is not visible for up to 150 seconds.                           |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_per_day_paid_tier_3.exceeded**(count) | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_per_day_paid_tier_3. After sampling, data is not visible for up to 150 seconds.  |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_per_day_paid_tier_3.limit**(gauge)    | Current limit on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_per_day_paid_tier_3.                                                                                      |
| **gcp.generativelanguage.quota.predict_long_running_requests_per_model_per_day_paid_tier_3.usage**(count)    | Current usage on quota metric generativelanguage.googleapis.com/predict_long_running_requests_per_model_per_day_paid_tier_3. After sampling, data is not visible for up to 150 seconds.                           |
| **gcp.generativelanguage.quota.predict_requests_free_tier_per_model.exceeded**(count)                             | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_requests_free_tier_per_model. After sampling, data is not visible for up to 150 seconds.                         |
| **gcp.generativelanguage.quota.predict_requests_free_tier_per_model.limit**(gauge)                                | Current limit on quota metric generativelanguage.googleapis.com/predict_requests_free_tier_per_model.                                                                                                             |
| **gcp.generativelanguage.quota.predict_requests_free_tier_per_model.usage**(count)                                | Current usage on quota metric generativelanguage.googleapis.com/predict_requests_free_tier_per_model. After sampling, data is not visible for up to 150 seconds.                                                  |
| **gcp.generativelanguage.quota.predict_requests_per_model.exceeded**(count)                                         | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_requests_per_model. After sampling, data is not visible for up to 150 seconds.                                   |
| **gcp.generativelanguage.quota.predict_requests_per_model.limit**(gauge)                                            | Current limit on quota metric generativelanguage.googleapis.com/predict_requests_per_model.                                                                                                                       |
| **gcp.generativelanguage.quota.predict_requests_per_model.usage**(count)                                            | Current usage on quota metric generativelanguage.googleapis.com/predict_requests_per_model. After sampling, data is not visible for up to 150 seconds.                                                            |
| **gcp.generativelanguage.quota.predict_requests_per_model_paid_tier_2.exceeded**(count)                          | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_requests_per_model_paid_tier_2. After sampling, data is not visible for up to 150 seconds.                       |
| **gcp.generativelanguage.quota.predict_requests_per_model_paid_tier_2.limit**(gauge)                             | Current limit on quota metric generativelanguage.googleapis.com/predict_requests_per_model_paid_tier_2.                                                                                                           |
| **gcp.generativelanguage.quota.predict_requests_per_model_paid_tier_2.usage**(count)                             | Current usage on quota metric generativelanguage.googleapis.com/predict_requests_per_model_paid_tier_2. After sampling, data is not visible for up to 150 seconds.                                                |
| **gcp.generativelanguage.quota.predict_requests_per_model_paid_tier_3.exceeded**(count)                          | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_requests_per_model_paid_tier_3. After sampling, data is not visible for up to 150 seconds.                       |
| **gcp.generativelanguage.quota.predict_requests_per_model_paid_tier_3.limit**(gauge)                             | Current limit on quota metric generativelanguage.googleapis.com/predict_requests_per_model_paid_tier_3.                                                                                                           |
| **gcp.generativelanguage.quota.predict_requests_per_model_paid_tier_3.usage**(count)                             | Current usage on quota metric generativelanguage.googleapis.com/predict_requests_per_model_paid_tier_3. After sampling, data is not visible for up to 150 seconds.                                                |
| **gcp.generativelanguage.quota.predict_requests_per_model_per_day_paid_tier_1.exceeded**(count)                | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_requests_per_model_per_day_paid_tier_1. After sampling, data is not visible for up to 150 seconds.               |
| **gcp.generativelanguage.quota.predict_requests_per_model_per_day_paid_tier_1.limit**(gauge)                   | Current limit on quota metric generativelanguage.googleapis.com/predict_requests_per_model_per_day_paid_tier_1.                                                                                                   |
| **gcp.generativelanguage.quota.predict_requests_per_model_per_day_paid_tier_1.usage**(count)                   | Current usage on quota metric generativelanguage.googleapis.com/predict_requests_per_model_per_day_paid_tier_1. After sampling, data is not visible for up to 150 seconds.                                        |
| **gcp.generativelanguage.quota.predict_requests_per_model_per_day_paid_tier_2.exceeded**(count)                | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_requests_per_model_per_day_paid_tier_2. After sampling, data is not visible for up to 150 seconds.               |
| **gcp.generativelanguage.quota.predict_requests_per_model_per_day_paid_tier_2.limit**(gauge)                   | Current limit on quota metric generativelanguage.googleapis.com/predict_requests_per_model_per_day_paid_tier_2.                                                                                                   |
| **gcp.generativelanguage.quota.predict_requests_per_model_per_day_paid_tier_2.usage**(count)                   | Current usage on quota metric generativelanguage.googleapis.com/predict_requests_per_model_per_day_paid_tier_2. After sampling, data is not visible for up to 150 seconds.                                        |
| **gcp.generativelanguage.quota.predict_requests_per_model_per_day_paid_tier_3.exceeded**(count)                | Number of attempts to exceed the limit on quota metric generativelanguage.googleapis.com/predict_requests_per_model_per_day_paid_tier_3. After sampling, data is not visible for up to 150 seconds.               |
| **gcp.generativelanguage.quota.predict_requests_per_model_per_day_paid_tier_3.limit**(gauge)                   | Current limit on quota metric generativelanguage.googleapis.com/predict_requests_per_model_per_day_paid_tier_3.                                                                                                   |
| **gcp.generativelanguage.quota.predict_requests_per_model_per_day_paid_tier_3.usage**(count)                   | Current usage on quota metric generativelanguage.googleapis.com/predict_requests_per_model_per_day_paid_tier_3. After sampling, data is not visible for up to 150 seconds.                                        |

### Events{% #events %}

google_cloud_generativelanguage does not include any events.

### Service Checks{% #service-checks %}

google_cloud_generativelanguage does not include any service checks.

## Troubleshooting{% #troubleshooting %}

Need help? Contact [Datadog support](https://docs.datadoghq.com/help/).