> ## Documentation Index > Fetch the complete documentation index at: https://www.latitude.sh/docs/llms.txt > Use this file to discover all available pages before exploring further. # Get inference usage for a project > Returns the project's inference requests, tokens and estimated cost for the window, per model and as a time series. The estimate uses current model prices. ## OpenAPI ````yaml https://spec.speakeasy.com/latitude/latitude/latitude-sh-api-with-code-samples get /inference/usage openapi: 3.0.1 info: title: Latitude.sh API version: '2023-06-01' description: >- The Latitude.sh API is a RESTful API to manage your Latitude.sh account. It allows you to perform the same actions as the Latitude.sh dashboard. servers: - url: https://api.latitude.sh variables: latitude_api_key: default: - url: http://api.latitude.sh variables: latitude_api_key: default: security: [] tags: - name: API keys - name: Baselines (Preview) description: >- Preview. Available to teams with the `baselines_api` feature flag. The shape of these endpoints may change before general availability. - name: Billing - name: Elastic Ips - name: Events - name: Firewalls - name: Inference - name: IP Addresses - name: Managed Databases description: Managed database instances (PostgreSQL, ClickHouse) - name: Kubernetes Clusters - name: LKS - name: Marketplace apps - name: Operating Systems - name: Plans - name: Sandboxes (Preview) description: >- Preview. Available to teams with the `sandboxes_api` feature flag. The shape of these endpoints may change before general availability. - name: Public Networks - name: Private Networks - name: Projects - name: Regions - name: Roles - name: SSH Keys - name: Servers - name: Block Storage - name: Filesystem Storage - name: Object Storage - name: Tags - name: Teams - name: Team members - name: Traffic - name: User data - name: User profile - name: VPN Sessions - name: Virtual machines - name: Virtual machine backups - name: Virtual machine restores paths: /inference/usage: get: tags: - Inference summary: Get inference usage for a project description: > Returns the project's inference requests, tokens and estimated cost for the window, per model and as a time series. The estimate uses current model prices. operationId: get-inference-usage parameters: - name: project_id in: query required: true description: Project ID or Slug examples: Success: value: proj_AoW6vRnwkvLn0 schema: type: string - name: from in: query required: true description: Start of the window (inclusive), truncated to whole seconds examples: Success: value: '2026-10-01T00:00:00Z' schema: type: string format: date-time - name: to in: query required: true description: >- End of the window (exclusive), truncated to whole seconds; at most 31 days after from examples: Success: value: '2026-10-02T00:00:00Z' schema: type: string format: date-time - name: granularity in: query required: true description: Size of each series bucket examples: Success: value: 6h schema: type: string enum: - 1h - 6h - 24h responses: '200': description: Success content: application/vnd.api+json: examples: Success: value: total_estimated_cost: '0.0312' total_requests: 412 total_tokens: 186240 by_model: - model: qwen3-30b-a3b-fp8 requests: 412 input_tokens: 142080 output_tokens: 44160 estimated_cost: '0.0312' series: - timestamp: '2026-10-01T00:00:00Z' models: qwen3-30b-a3b-fp8: requests: 250 estimated_cost: '0.0189' - timestamp: '2026-10-01T06:00:00Z' models: qwen3-30b-a3b-fp8: requests: 162 estimated_cost: '0.0123' schema: $ref: '#/components/schemas/inference_usage' '403': description: >- Forbidden — AI Inference is not enabled for the team (`FEATURE_NOT_ENABLED`) content: application/vnd.api+json: schema: $ref: '#/components/schemas/error_object' '404': description: Not Found — the project doesn't exist or belongs to another team content: application/vnd.api+json: schema: $ref: '#/components/schemas/error_object' '422': description: >- Unprocessable Entity — a parameter is missing, `granularity` is not `1h`, `6h`, or `24h`, or the window is shorter than one second or longer than 31 days content: application/vnd.api+json: schema: $ref: '#/components/schemas/error_object' '503': description: >- Service Unavailable — inference usage is temporarily unavailable (`UPSTREAM_SERVICE_ERROR`) content: application/vnd.api+json: schema: $ref: '#/components/schemas/error_object' security: - Bearer: [] x-codeSamples: - lang: python label: Python (SDK) source: |- import latitudesh_python_sdk from latitudesh_python_sdk import Latitudesh from latitudesh_python_sdk.utils import parse_datetime import os with Latitudesh( bearer=os.getenv("LATITUDESH_BEARER", ""), ) as latitudesh: res = latitudesh.inference.get_inference_usage(project_id="proj_AoW6vRnwkvLn0", from_=parse_datetime("2026-10-01T00:00:00Z"), to=parse_datetime("2026-10-02T00:00:00Z"), granularity=latitudesh_python_sdk.Granularity.SIXH) # Handle response print(res) components: schemas: inference_usage: type: object properties: total_estimated_cost: type: string example: '0.88' description: Estimated USD across priced models total_requests: type: integer total_tokens: type: integer by_model: type: array items: type: object properties: model: type: string example: qwen3-30b-a3b-fp8 requests: type: integer input_tokens: type: integer output_tokens: type: integer estimated_cost: type: string example: '0.000599' nullable: true description: >- Estimated USD at current model prices; null when the model has no price series: type: array items: type: object properties: timestamp: type: string format: date-time description: Start of the bucket (UTC) models: type: object description: Usage in the bucket keyed by model ID additionalProperties: type: object properties: requests: type: integer estimated_cost: type: string example: '0.000599' nullable: true description: >- Estimated USD at current model prices; null when the model has no price error_object: type: object properties: errors: type: array items: type: object properties: code: type: string nullable: true status: type: string title: type: string detail: type: string source: type: object properties: pointer: type: string parameter: type: string meta: type: object securitySchemes: Bearer: type: apiKey name: Authorization in: header ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.