---
title: "POST /v1/{+parent}/models"
method: POST
path: "/v1/{+parent}/models"
tags: ["projects"]
---

# POST /v1/{+parent}/models

`POST /v1/{+parent}/models`

Creates a model which will later contain one or more versions. You must add at least one version before you can request predictions from the model. Add versions by calling projects.models.versions.create.

## Path parameters

- `parent` string, required

## Request body

- GoogleCloudMlV1Model — Represents a machine learning solution. A model can have multiple versions, each of which is a deployed, trained model ready to receive prediction requests. The model itself is just a container.
  - `description` string — Optional. The description specified for the model when it was created.
  - `name` string — Required. The name specified for the model when it was created. The model name must be unique within the project it is created in.
  - `defaultVersion` GoogleCloudMlV1Version — Represents a version of the model. Each version is a trained model deployed in the cloud, ready to handle prediction requests. A model can have multiple versions. You can get information about all of the versions of a given model by calling projects.models.versions.list.
    - `lastMigrationTime` string, google-datetime — Output only. The last time this version was successfully [migrated to AI Platform (Unified)](https://cloud.google.com/ai-platform-unified/docs/start/migrating-to-ai-platform-unified).
    - `labels` object — Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels. Note that this field is not updatable for mls1* models.
    - `routes` GoogleCloudMlV1RouteMap — Specifies HTTP paths served by a custom container. AI Platform Prediction sends requests to these paths on the container; the custom container must run an HTTP server that responds to these requests with appropriate responses. Read [Custom container requirements](/ai-platform/prediction/docs/custom-container-requirements) for details on how to create your container image to meet these requirements.
      - `predict` string — HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to `/foo`, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the `/foo` path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
      - `health` string — HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about [health checks](/ai-platform/prediction/docs/custom-container-requirements#checks). For example, if you set this field to `/bar`, then AI Platform Prediction intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
    - `deploymentUri` string — The Cloud Storage URI of a directory containing trained model artifacts to be used to create the model version. See the [guide to deploying models](/ai-platform/prediction/docs/deploying-models) for more information. The total number of files under this directory must not exceed 1000. During projects.models.versions.create, AI Platform Prediction copies all files from the specified directory to a location managed by the service. From then on, AI Platform Prediction uses these copies of the model artifacts to serve predictions, not the original files in Cloud Storage, so this location is useful only as a historical record. If you specify container, then this field is optional. Otherwise, it is required. Learn [how to use this field with a custom container](/ai-platform/prediction/docs/custom-container-requirements#artifacts).
    - `pythonVersion` string — Required. The version of Python used in prediction. The following Python versions are available: * Python '3.7' is available when `runtime_version` is set to '1.15' or later. * Python '3.5' is available when `runtime_version` is set to a version from '1.4' to '1.14'. * Python '2.7' is available when `runtime_version` is set to '1.15' or earlier. Read more about the Python versions available for [each runtime version](/ml-engine/docs/runtime-version-list).
    - `createTime` string, google-datetime — Output only. The time the version was created.
    - `runtimeVersion` string — Required. The AI Platform runtime version to use for this deployment. For more information, see the [runtime version list](/ml-engine/docs/runtime-version-list) and [how to manage runtime versions](/ml-engine/docs/versioning).
    - `isDefault` boolean — Output only. If true, this version will be used to handle prediction requests that do not specify a version. You can change the default version by calling projects.methods.versions.setDefault.
    - `autoScaling` GoogleCloudMlV1AutoScaling — Options for automatically scaling a model.
      - `maxNodes` integer — The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
      - `minNodes` integer — Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/*/models/*/versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
      - `metrics` GoogleCloudMlV1MetricSpec[] — MetricSpec contains the specifications to use to calculate the desired nodes count.
        - `name` 'METRIC_NAME_UNSPECIFIED' | 'CPU_USAGE' | 'GPU_DUTY_CYCLE' — metric name.
        - `target` integer — Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
    - `serviceAccount` string — Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the `containerSpec` or the `predictionClass` field. Learn more about [using a custom service account](/ai-platform/prediction/docs/custom-service-account).
    - `lastMigrationModelId` string — Output only. The [AI Platform (Unified) `Model`](https://cloud.google.com/ai-platform-unified/docs/reference/rest/v1beta1/projects.locations.models) ID for the last [model migration](https://cloud.google.com/ai-platform-unified/docs/start/migrating-to-ai-platform-unified).
    - `requestLoggingConfig` GoogleCloudMlV1RequestLoggingConfig — Configuration for logging request-response pairs to a BigQuery table. Online prediction requests to a model version and the responses to these requests are converted to raw strings and saved to the specified BigQuery table. Logging is constrained by [BigQuery quotas and limits](/bigquery/quotas). If your project exceeds BigQuery quotas or limits, AI Platform Prediction does not log request-response pairs, but it continues to serve predictions. If you are using [continuous evaluation](/ml-engine/docs/continuous-evaluation/), you do not need to specify this configuration manually. Setting up continuous evaluation automatically enables logging of request-response pairs.
      - `samplingPercentage` number, double — Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter `0.1`. The sampling window is the lifetime of the model version. Defaults to 0.
      - `bigqueryTableName` string — Required. Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following [schema](/bigquery/docs/schemas): Field name Type Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
    - `state` 'UNKNOWN' | 'READY' | 'CREATING' | 'FAILED' | 'DELETING' | 'UPDATING' — Output only. The state of a version.
    - `framework` 'FRAMEWORK_UNSPECIFIED' | 'TENSORFLOW' | 'SCIKIT_LEARN' | 'XGBOOST' — Optional. The machine learning framework AI Platform uses to train this version of the model. Valid values are `TENSORFLOW`, `SCIKIT_LEARN`, `XGBOOST`. If you do not specify a framework, AI Platform will analyze files in the deployment_uri to determine a framework. If you choose `SCIKIT_LEARN` or `XGBOOST`, you must also set the runtime version of the model to 1.4 or greater. Do **not** specify a framework if you're deploying a [custom prediction routine](/ai-platform/prediction/docs/custom-prediction-routines) or if you're using a [custom container](/ai-platform/prediction/docs/use-custom-container).
    - `packageUris` string[] — Optional. Cloud Storage paths (`gs://…`) of packages for [custom prediction routines](/ml-engine/docs/tensorflow/custom-prediction-routines) or [scikit-learn pipelines with custom code](/ml-engine/docs/scikit/exporting-for-prediction#custom-pipeline-code). For a custom prediction routine, one of these packages must contain your Predictor class (see [`predictionClass`](#Version.FIELDS.prediction_class)). Additionally, include any dependencies used by your Predictor or scikit-learn pipeline uses that are not already included in your selected [runtime version](/ml-engine/docs/tensorflow/runtime-version-list). If you specify this field, you must also set [`runtimeVersion`](#Version.FIELDS.runtime_version) to 1.4 or greater.
    - `errorMessage` string — Output only. The details of a failure or a cancellation.
    - `container` GoogleCloudMlV1ContainerSpec — Specification of a custom container for serving predictions. This message is a subset of the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core).
      - `command` string[] — Immutable. Specifies the command that runs when the container starts. This overrides the container's [`ENTRYPOINT`](https://docs.docker.com/engine/reference/builder/#entrypoint). Specify this field as an array of executable and arguments, similar to a Docker `ENTRYPOINT`'s "exec" form, not its "shell" form. If you do not specify this field, then the container's `ENTRYPOINT` runs, in conjunction with the args field or the container's [`CMD`](https://docs.docker.com/engine/reference/builder/#cmd), if either exists. If this field is not specified and the container does not have an `ENTRYPOINT`, then refer to the [Docker documentation about how `CMD` and `ENTRYPOINT` interact](https://docs.docker.com/engine/reference/builder/#understand-how-cmd-and-entrypoint-interact). If you specify this field, then you can also specify the `args` field to provide additional arguments for this command. However, if you specify this field, then the container's `CMD` is ignored. See the [Kubernetes documentation about how the `command` and `args` fields interact with a container's `ENTRYPOINT` and `CMD`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). In this field, you can reference [environment variables set by AI Platform Prediction](/ai-platform/prediction/docs/custom-container-requirements#aip-variables) and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with `$$`; for example: $$(VARIABLE_NAME) This field corresponds to the `command` field of the [Kubernetes Containers v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core).
      - `image` string — URI of the Docker image to be used as the custom container for serving predictions. This URI must identify [an image in Artifact Registry](/artifact-registry/docs/overview) and begin with the hostname `{REGION}-docker.pkg.dev`, where `{REGION}` is replaced by the region that matches AI Platform Prediction [regional endpoint](/ai-platform/prediction/docs/regional-endpoints) that you are using. For example, if you are using the `us-central1-ml.googleapis.com` endpoint, then this URI must begin with `us-central1-docker.pkg.dev`. To use a custom container, the [AI Platform Google-managed service account](/ai-platform/prediction/docs/custom-service-account#default) must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: `service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com` {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to [grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository](/artifact-registry/docs/access-control#grant-repo) to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read [Custom container requirements](/ai-platform/prediction/docs/custom-container-requirements).
      - `env` GoogleCloudMlV1EnvVar[] — Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable `VAR_2` to have the value `foo bar`: ```json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] ``` If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the `env` field of the [Kubernetes Containers v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core).
        - `value` string — Value of the environment variable. Defaults to an empty string. In this field, you can reference [environment variables set by AI Platform Prediction](/ai-platform/prediction/docs/custom-container-requirements#aip-variables) and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with `$$`; for example: $$(VARIABLE_NAME)
        - `name` string — Name of the environment variable. Must be a [valid C identifier](https://github.com/kubernetes/kubernetes/blob/v1.18.8/staging/src/k8s.io/apimachinery/pkg/util/validation/validation.go#L258) and must not begin with the prefix `AIP_`.
      - `args` string[] — Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's [`CMD`](https://docs.docker.com/engine/reference/builder/#cmd). Specify this field as an array of executable and arguments, similar to a Docker `CMD`'s "default parameters" form. If you don't specify this field but do specify the command field, then the command from the `command` field runs without any additional arguments. See the [Kubernetes documentation about how the `command` and `args` fields interact with a container's `ENTRYPOINT` and `CMD`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). If you don't specify this field and don't specify the `commmand` field, then the container's [`ENTRYPOINT`](https://docs.docker.com/engine/reference/builder/#cmd) and `CMD` determine what runs based on their default behavior. See the [Docker documentation about how `CMD` and `ENTRYPOINT` interact](https://docs.docker.com/engine/reference/builder/#understand-how-cmd-and-entrypoint-interact). In this field, you can reference [environment variables set by AI Platform Prediction](/ai-platform/prediction/docs/custom-container-requirements#aip-variables) and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with `$$`; for example: $$(VARIABLE_NAME) This field corresponds to the `args` field of the [Kubernetes Containers v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core).
      - `ports` GoogleCloudMlV1ContainerPort[] — Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends [liveness and health checks](/ai-platform/prediction/docs/custom-container-requirements#health) to this port. If you do not specify this field, it defaults to following value: ```json [ { "containerPort": 8080 } ] ``` AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the `ports` field of the [Kubernetes Containers v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core).
        - `containerPort` integer — Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.
    - `explanationConfig` GoogleCloudMlV1ExplanationConfig — Message holding configuration options for explaining model predictions. There are three feature attribution methods supported for TensorFlow models: integrated gradients, sampled Shapley, and XRAI. [Learn more about feature attributions.](/ai-platform/prediction/docs/ai-explanations/overview)
      - `xraiAttribution` GoogleCloudMlV1XraiAttribution — Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
        - `numIntegralSteps` integer — Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
      - `sampledShapleyAttribution` GoogleCloudMlV1SampledShapleyAttribution — An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
        - `numPaths` integer — The number of feature permutations to consider when approximating the Shapley values.
      - `integratedGradientsAttribution` GoogleCloudMlV1IntegratedGradientsAttribution — Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
        - `numIntegralSteps` integer — Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
    - `acceleratorConfig` GoogleCloudMlV1AcceleratorConfig — Represents a hardware accelerator request config. Note that the AcceleratorConfig can be used in both Jobs and Versions. Learn more about [accelerators for training](/ml-engine/docs/using-gpus) and [accelerators for online prediction](/ml-engine/docs/machine-types-online-prediction#gpus).
      - `count` string, int64 — The number of accelerators to attach to each machine running the job.
      - `type` 'ACCELERATOR_TYPE_UNSPECIFIED' | 'NVIDIA_TESLA_K80' | 'NVIDIA_TESLA_P100' | 'NVIDIA_TESLA_V100' | 'NVIDIA_TESLA_P4' | 'NVIDIA_TESLA_T4' | 'NVIDIA_TESLA_A100' | 'TPU_V2' | 'TPU_V3' | 'TPU_V2_POD' | 'TPU_V3_POD' | 'TPU_V4_POD' — The type of accelerator to use.
    - `lastUseTime` string, google-datetime — Output only. The time the version was last used for prediction.
    - `name` string — Required. The name specified for the version when it was created. The version name must be unique within the model it is created in.
    - `machineType` string — Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read [Choosing a machine type for online prediction](/ai-platform/prediction/docs/machine-types-online-prediction). If this field is not specified and you are using a [regional endpoint](/ai-platform/prediction/docs/regional-endpoints), then the machine type defaults to `n1-standard-2`. If this field is not specified and you are using the global endpoint (`ml.googleapis.com`), then the machine type defaults to `mls1-c1-m2`.
    - `etag` string, byte — `etag` is used for optimistic concurrency control as a way to help prevent simultaneous updates of a model from overwriting each other. It is strongly suggested that systems make use of the `etag` in the read-modify-write cycle to perform model updates in order to avoid race conditions: An `etag` is returned in the response to `GetVersion`, and systems are expected to put that etag in the request to `UpdateVersion` to ensure that their change will be applied to the model as intended.
    - `predictionClass` string — Optional. The fully qualified name (module_name.class_name) of a class that implements the Predictor interface described in this reference field. The module containing this class should be included in a package provided to the [`packageUris` field](#Version.FIELDS.package_uris). Specify this field if and only if you are deploying a [custom prediction routine (beta)](/ml-engine/docs/tensorflow/custom-prediction-routines). If you specify this field, you must set [`runtimeVersion`](#Version.FIELDS.runtime_version) to 1.4 or greater and you must set `machineType` to a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction). The following code sample provides the Predictor interface: class Predictor(object): """Interface for constructing custom predictors.""" def predict(self, instances, **kwargs): """Performs custom prediction. Instances are the decoded values from the request. They have already been deserialized from JSON. Args: instances: A list of prediction input instances. **kwargs: A dictionary of keyword args provided as additional fields on the predict request body. Returns: A list of outputs containing the prediction results. This list must be JSON serializable. """ raise NotImplementedError() @classmethod def from_path(cls, model_dir): """Creates an instance of Predictor using the given path. Loading of the predictor should be done in this method. Args: model_dir: The local directory that contains the exported model file along with any additional files uploaded when creating the version resource. Returns: An instance implementing this Predictor class. """ raise NotImplementedError() Learn more about [the Predictor interface and custom prediction routines](/ml-engine/docs/tensorflow/custom-prediction-routines).
    - `description` string — Optional. The description specified for the version when it was created.
    - `manualScaling` GoogleCloudMlV1ManualScaling — Options for manually scaling a model.
      - `nodes` integer — The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to `nodes` * number of hours since last billing cycle plus the cost for each prediction performed.
  - `etag` string, byte — `etag` is used for optimistic concurrency control as a way to help prevent simultaneous updates of a model from overwriting each other. It is strongly suggested that systems make use of the `etag` in the read-modify-write cycle to perform model updates in order to avoid race conditions: An `etag` is returned in the response to `GetModel`, and systems are expected to put that etag in the request to `UpdateModel` to ensure that their change will be applied to the model as intended.
  - `labels` object — Optional. One or more labels that you can add, to organize your models. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels. Note that this field is not updatable for mls1* models.
  - `regions` string[] — Optional. The list of regions where the model is going to be deployed. Only one region per model is supported. Defaults to 'us-central1' if nothing is set. See the available regions for AI Platform services. Note: * No matter where a model is deployed, it can always be accessed by users from anywhere, both for online and batch prediction. * The region for a batch prediction job is set by the region field when submitting the batch prediction job and does not take its value from this field.
  - `onlinePredictionConsoleLogging` boolean — Optional. If true, online prediction nodes send `stderr` and `stdout` streams to Cloud Logging. These can be more verbose than the standard access logs (see `onlinePredictionLogging`) and can incur higher cost. However, they are helpful for debugging. Note that [logs may incur a cost](/stackdriver/pricing), especially if your project receives prediction requests at a high QPS. Estimate your costs before enabling this option. Default is false.
  - `onlinePredictionLogging` boolean — Optional. If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each request. Note that [logs may incur a cost](/stackdriver/pricing), especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option. Default is false.

## Response `200`

Successful response

---

[API](https://skmtc.net/google/apis/ml.md) · [All operations](https://skmtc.net/google/apis/ml/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/google/ml/versions/2135f4d5ddf1/schema)