> ## Documentation Index > Fetch the complete documentation index at: https://docs.baseten.co/llms.txt > Use this file to discover all available pages before exploring further. # Get Model API metrics > Gets Model API metrics for a time range, labeled by team. ## OpenAPI ````yaml get /v1/model_apis/{model_api_name}/metrics openapi: 3.1.0 info: description: REST API for management of Baseten resources title: Baseten management API version: 1.0.0 servers: - url: https://api.baseten.co security: - BearerAuth: [] paths: /v1/model_apis/{model_api_name}/metrics: parameters: - $ref: '#/components/parameters/model_api_name' get: summary: Gets the metrics for a Model API description: >- Gets the metrics for a Model API in the given time range for the teams you can manage, with each series labeled by team_id. Organization admins receive organization-wide metrics by default. For a Model API your lab organization lists, other organizations' consumption is included regardless of team_ids. parameters: - name: mode in: query required: false description: >- 'CURRENT': a single instantaneous snapshot at now; start/end must be omitted. 'SUMMARY': a single value set aggregating the whole window. 'SERIES': evenly-spaced value sets across the window, with the step derived from the window duration. schema: $ref: '#/components/schemas/MetricModeV1' default: CURRENT - name: start_epoch_millis in: query required: false description: >- Epoch millis timestamp to start fetching metrics. Defaults to one hour before the end. schema: anyOf: - type: integer - type: 'null' default: null title: Start Epoch Millis - name: end_epoch_millis in: query required: false description: >- Epoch millis timestamp to end fetching metrics. Defaults to the current time. The window between start and end must not exceed 7 days. schema: anyOf: - type: integer - type: 'null' default: null title: End Epoch Millis - name: metrics in: query required: false description: >- Names of the metrics to return; see https://docs.baseten.co/observability/export-metrics/supported-metrics for the available names. When omitted, a default set is returned: baseten_model_api_inference_requests_total, baseten_model_api_incoming_inference_requests_total, and baseten_model_api_tokens_total. Unknown names are rejected; valid names that are not enabled for your organization are omitted from the response. schema: items: type: string title: Metrics type: array - name: team_ids in: query required: false description: >- Return only metrics for these teams, repeated once per team. Defaults to all teams you can manage. Any unauthorized team causes a 403. schema: items: type: string title: Team Ids type: array responses: '200': description: '' content: application/json: schema: $ref: '#/components/schemas/GetMetricsResponseV1' x-codeSamples: - lang: bash source: > curl --request GET \ --url https://api.baseten.co/v1/model_apis/{model_api_name}/metrics \ --header "Authorization: Bearer $BASETEN_API_KEY" - lang: python source: >- import requests import os API_KEY = os.environ.get("BASETEN_API_KEY", "") url = "https://api.baseten.co/v1/model_apis/{model_api_name}/metrics" headers = {"Authorization": f"Bearer {API_KEY}"} response = requests.request( "GET", url, headers=headers, params={'mode': 'CURRENT', 'start_epoch_millis': None, 'end_epoch_millis': None} ) print(response.text) components: parameters: model_api_name: schema: type: string name: model_api_name in: path required: true schemas: MetricModeV1: description: How metric values are aggregated over the request. enum: - CURRENT - SUMMARY - SERIES title: MetricModeV1 type: string GetMetricsResponseV1: description: >- Model metrics over a time window, index-mapped: metric descriptors appear once in ``metric_descriptors``; each value set's ``values`` are aligned to that order. properties: start_epoch_millis: description: Start of the returned window. title: Start Epoch Millis type: integer end_epoch_millis: description: End of the returned window. title: End Epoch Millis type: integer mode: $ref: '#/components/schemas/MetricModeV1' description: The aggregation mode used. step_seconds: anyOf: - type: integer - type: 'null' description: Seconds per step; populated only in SERIES mode, null otherwise. title: Step Seconds metric_descriptors: description: Descriptors for each metric; position defines the values index. items: $ref: '#/components/schemas/MetricDescriptorV1' title: Metric Descriptors type: array metric_values: description: >- Metric values per time step covering the window. In summary mode this always contains exactly one value set spanning the whole window. items: $ref: '#/components/schemas/MetricValueSetV1' title: Metric Values type: array required: - start_epoch_millis - end_epoch_millis - mode - step_seconds - metric_descriptors - metric_values title: GetMetricsResponseV1 type: object MetricDescriptorV1: description: >- Describes one metric. Its position in the response ``metric_descriptors`` list is the index used to read that metric out of each value set's ``values``. A metric may break down into multiple labeled series (e.g. latency quantiles, or volume by status). ``label_sets`` enumerates those series in order; each value set's value for this metric is a list aligned to that order. properties: name: description: Canonical metric name. title: Name type: string unit_hint: $ref: '#/components/schemas/MetricUnitHintV1' description: Advisory unit of the metric's values. kind: $ref: '#/components/schemas/MetricKindV1' description: >- Semantic hint for how the metric behaves (GAUGE, COUNTER, HISTOGRAM). label_sets: description: >- The metric's series, in order. Each entry is the set of labels identifying one series; the value at the same index in each value set's ``values`` is that series' value. A plain metric has a single entry with no labels (`{}`). A histogram has one entry per quantile plus an average, e.g. {'quantile': '0.5'} … {'quantile': '0.99'}, {'stat': 'avg'}. items: additionalProperties: type: string type: object title: Label Sets type: array required: - name - unit_hint - kind - label_sets title: MetricDescriptorV1 type: object MetricValueSetV1: description: >- The metric values for one time step. ``values`` is aligned by index to the response ``metric_descriptors`` list. properties: start_epoch_millis: description: >- Start of the step. The step spans until the next value set's start, or the window end for the last one; a summary has a single value set starting at the window start. title: Start Epoch Millis type: integer values: description: >- Metric values aligned to the ``metric_descriptors`` index. Each entry is a list aligned to that descriptor's ``label_sets`` (a single-element list for a plain metric). A series with no data in this step is null. items: items: anyOf: - type: number - type: 'null' type: array title: Values type: array required: - start_epoch_millis - values title: MetricValueSetV1 type: object MetricUnitHintV1: description: >- Advisory unit of a metric's values. Values are reported as scraped, so the hint describes the raw value (e.g. GPU memory is reported in mebibytes). - ``PER_SECOND``: a rate per second. - ``SECONDS``: a duration in seconds. - ``BYTES``: a size in bytes. - ``MEBIBYTES``: a size in mebibytes (MiB). - ``COUNT``: a dimensionless tally of discrete things. - ``RATIO``: a dimensionless ratio. Usually in ``[0, 1]`` but may exceed 1 (e.g. CPU usage in cores = cpu-seconds/second). - ``CELSIUS``: a temperature in degrees Celsius. - ``WATTS``: power draw in watts. enum: - PER_SECOND - SECONDS - BYTES - MEBIBYTES - COUNT - RATIO - CELSIUS - WATTS title: MetricUnitHintV1 type: string MetricKindV1: description: >- Semantic hint for how a metric behaves, to aid client rendering and aggregation. It does not describe the value's shape (that is carried by the descriptor's ``label_sets``; a metric may break down into multiple series). - ``GAUGE``: an instantaneous value (e.g. queue size, running requests). - ``COUNTER``: a cumulative total over the step (e.g. tokens, restarts). - ``HISTOGRAM``: a distribution, exposed as quantile/average series. enum: - GAUGE - COUNTER - HISTOGRAM title: MetricKindV1 type: string securitySchemes: BearerAuth: type: http scheme: bearer description: >- Send `Authorization: Bearer `. The legacy `Authorization: Api-Key ` scheme is also accepted. ````