> ## Documentation Index > Fetch the complete documentation index at: https://data.ornn.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Get current utilization for all GPUs > The latest utilization reading for every tracked GPU in one call, with the 7- and 30-day means behind it. Takes no parameters. Use this for a cross-section across GPUs. For one GPU's series over time, use `/api/gpu/{gpuName}/volume-metrics`. `utilization_ratio` is the share of tracked capacity rented, between 0 and 1, and is bounded to the last 48 hours: a GPU whose feed has stopped returns `null` rather than a stale figure. `avg_7d` and `avg_30d` are explicitly windowed and still populate in that case. A GPU with no readings at all in the 30-day window is absent from `data` rather than present with nulls. Pinned to `region: "global"`. ## Overview The latest utilization reading for every tracked GPU in one call, with the 7- and 30-day means behind it. Takes no parameters. Use this for a cross-section across GPUs. For one GPU's series over time, use [Get market utilization](/docs/api-reference/analytics/get-market-utilization). ## Reading the response `utilization_ratio` is the share of tracked capacity rented, between 0 and 1, and is bounded to the last 48 hours — a GPU whose feed has stopped returns `null` rather than a stale figure. `avg_7d` and `avg_30d` are explicitly windowed and still populate in that case, so neither can be misread as current. A GPU with no readings at all in the 30-day window is absent from `data` rather than present with nulls. Results are pinned to `region: "global"`. ## OpenAPI ````yaml openapi.yaml GET /api/gpu-utilization openapi: 3.1.0 info: title: Ornn Data API version: 1.0.0 description: > Read-only REST API for GPU and memory market data. The price index is the going rate of compute in USD per GPU-hour, a weighted average of all verified compute transactions across the market. servers: - url: https://api.ornnai.com security: - bearerAuth: [] tags: - name: Current Prices - name: Historical Prices - name: Analytics - name: Memory - name: Token Prices - name: Workload Cost - name: LLM Coding - name: Forward Curves - name: Token Volume - name: Model Frontier - name: Compute Buyers - name: Power Markets - name: Neo-Cloud Sites - name: Reference paths: /api/gpu-utilization: get: tags: - Analytics summary: Get current utilization for all GPUs description: > The latest utilization reading for every tracked GPU in one call, with the 7- and 30-day means behind it. Takes no parameters. Use this for a cross-section across GPUs. For one GPU's series over time, use `/api/gpu/{gpuName}/volume-metrics`. `utilization_ratio` is the share of tracked capacity rented, between 0 and 1, and is bounded to the last 48 hours: a GPU whose feed has stopped returns `null` rather than a stale figure. `avg_7d` and `avg_30d` are explicitly windowed and still populate in that case. A GPU with no readings at all in the 30-day window is absent from `data` rather than present with nulls. Pinned to `region: "global"`. responses: '200': description: Latest utilization per GPU. content: application/json: example: success: true query: region: global gpu_types: - H100 SXM - H200 - A100 SXM4 - RTX 5090 - B200 - RTX PRO 6000 WS window_days: 30 data: - gpu_name: H100 SXM utilization_ratio: 0.7 recorded_at: '2026-08-31T12:00:00.000Z' avg_7d: 0.68 avg_30d: 0.66 readings_found: 720 - gpu_name: H200 utilization_ratio: 0.81 recorded_at: '2026-08-31T12:00:00.000Z' avg_7d: 0.79 avg_30d: 0.77 readings_found: 720 '401': $ref: '#/components/responses/Unauthorized' x-codeSamples: - lang: bash label: cURL source: | curl "https://api.ornnai.com/api/gpu-utilization" \ -H "Authorization: Bearer YOUR_API_KEY" - lang: python label: Python source: | import requests resp = requests.get( "https://api.ornnai.com/api/gpu-utilization", headers={"Authorization": "Bearer YOUR_API_KEY"}, ) data = resp.json() - lang: javascript label: JavaScript source: > const res = await fetch("https://api.ornnai.com/api/gpu-utilization", { headers: { Authorization: "Bearer YOUR_API_KEY" }, }); const data = await res.json(); - lang: php label: PHP source: | true, CURLOPT_HTTPHEADER => ["Authorization: Bearer YOUR_API_KEY"], ]); $data = json_decode(curl_exec($ch), true); - lang: go label: Go source: "package main\n\nimport (\n\t\"io\"\n\t\"net/http\"\n)\n\nfunc main() {\n\treq, _ := http.NewRequest(\"GET\", \"https://api.ornnai.com/api/gpu-utilization\", nil)\n\treq.Header.Set(\"Authorization\", \"Bearer YOUR_API_KEY\")\n\tresp, _ := http.DefaultClient.Do(req)\n\tdefer resp.Body.Close()\n\tbody, _ := io.ReadAll(resp.Body)\n\t_ = body\n}\n" - lang: java label: Java source: > import java.net.URI; import java.net.http.HttpClient; import java.net.http.HttpRequest; import java.net.http.HttpResponse; HttpClient client = HttpClient.newHttpClient(); HttpRequest request = HttpRequest.newBuilder( URI.create("https://api.ornnai.com/api/gpu-utilization")) .header("Authorization", "Bearer YOUR_API_KEY") .build(); HttpResponse response = client.send(request, HttpResponse.BodyHandlers.ofString()); - lang: ruby label: Ruby source: > require "net/http" require "json" uri = URI("https://api.ornnai.com/api/gpu-utilization") req = Net::HTTP::Get.new(uri) req["Authorization"] = "Bearer YOUR_API_KEY" res = Net::HTTP.start(uri.host, uri.port, use_ssl: true) { |http| http.request(req) } data = JSON.parse(res.body) components: responses: Unauthorized: description: Missing, invalid, or revoked API key. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: Unauthorized message: 'API key required. Use Authorization: Bearer YOUR_API_KEY' schemas: Error: type: object properties: error: type: string example: Bad request message: type: string example: >- Invalid GPU type. Allowed: H100 SXM, H200, A100 SXM4, RTX 5090, B200, RTX PRO 6000 WS securitySchemes: bearerAuth: type: http scheme: bearer description: API key passed as a Bearer token. Create one in the dashboard. ````