> ## 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 the Model Frontier dataset > The Model Frontier dataset: benchmark capability against transacted price per task. `models` is the per-model scatter - Epoch Capabilities Index plus SWE-bench Verified / GPQA Diamond / AIME scores, priced with token-weighted OTPI dollars per million tokens as of the last benchmark refresh (`costPerTask` = `price` x `tpt` / 1e6). `tests` lists the tracked thinking-level benchmarks, `efforts` carries every (model x thinking level) run per test, and `releaseDates` maps model display names to first-release dates (YYYY-MM-DD) - join it against the `efforts` rows to reconstruct the frontier as of any past date. `history` carries real month-by-month prices where they exist (currently GPQA Diamond only); for the tracked benchmarks, past frontier states come from `efforts` + `releaseDates`. The dataset refreshes on benchmark refresh rather than daily, so responses are stable between refreshes. Requires an API key - there is no free tier. ## Overview The Model Frontier dataset: benchmark capability against transacted price per task, for every model and thinking level. `models` is the per-model scatter - Epoch Capabilities Index and SWE-bench Verified / GPQA Diamond / AIME scores, priced with token-weighted OTPI dollars per million tokens as of the last benchmark refresh (`costPerTask` = `price` × `tpt` / 1e6). `tests` lists the tracked thinking-level benchmarks, `efforts` carries every (model × thinking level) run per test, and `releaseDates` maps model display names to first-release dates - join it against the `efforts` rows to reconstruct the frontier as it stood on any past date. `history` carries real month-by-month prices where they exist (currently GPQA Diamond only). A model with no real score on an axis is dropped from that view, never estimated. The dataset moves on benchmark refresh, not daily. Requires an API key - there is no free tier. ## OpenAPI ````yaml openapi.yaml GET /api/model-frontier 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: Token Volume - name: Model Frontier - name: Compute Buyers - name: Neo-Cloud Sites - name: Reference paths: /api/model-frontier: get: tags: - Model Frontier summary: Get the Model Frontier dataset description: > The Model Frontier dataset: benchmark capability against transacted price per task. `models` is the per-model scatter - Epoch Capabilities Index plus SWE-bench Verified / GPQA Diamond / AIME scores, priced with token-weighted OTPI dollars per million tokens as of the last benchmark refresh (`costPerTask` = `price` x `tpt` / 1e6). `tests` lists the tracked thinking-level benchmarks, `efforts` carries every (model x thinking level) run per test, and `releaseDates` maps model display names to first-release dates (YYYY-MM-DD) - join it against the `efforts` rows to reconstruct the frontier as of any past date. `history` carries real month-by-month prices where they exist (currently GPQA Diamond only); for the tracked benchmarks, past frontier states come from `efforts` + `releaseDates`. The dataset refreshes on benchmark refresh rather than daily, so responses are stable between refreshes. Requires an API key - there is no free tier. responses: '200': description: The full Model Frontier dataset. content: application/json: example: success: true access: premium models: - slug: google/gemini-2.5-pro name: Gemini 2.5 Pro lab: google cap: 146.19 tpt: 75000 price: 2.2173 pIn: 1.1065 pOut: 10.0316 totalTokens: 6828491 costPerTask: 0.1663 bench: coding: 0.5756 reasoning: 0.8529 math: 0.8417 tests: - key: weirdml label: WeirdML desc: ML / data-science coding unit: '%' efforts: weirdml: - model: claude-fable-5 effort: max rank: 5 cap: 91.9 cost: 8.4244 costBasis: measured tokensEst: null timeSec: null speedTps: null speedMeasured: false lab: Anthropic history: gpqa: label: GPQA Diamond months: - 2026.0833 - 2026.1667 models: - name: gemini-3.1-pro-preview cap: 94.1 cost: - 0.067 - 0.067 releaseDates: Claude Fable 5: '2026-06-09' Claude Opus 4.8: '2026-05-28' '401': $ref: '#/components/responses/Unauthorized' x-codeSamples: - lang: bash label: cURL source: | curl "https://api.ornnai.com/api/model-frontier" \ -H "Authorization: Bearer YOUR_API_KEY" - lang: python label: Python source: | import requests frontier = requests.get( "https://api.ornnai.com/api/model-frontier", headers={"Authorization": "Bearer YOUR_API_KEY"}, ).json() for m in frontier["models"]: print(m["name"], m["cap"], m["costPerTask"]) - lang: javascript label: JavaScript source: > const res = await fetch("https://api.ornnai.com/api/model-frontier", { headers: { Authorization: "Bearer YOUR_API_KEY" }, }); const { models, tests, efforts, history } = 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\tendpoint := \"https://api.ornnai.com/api/model-frontier\"\n\treq, _ := http.NewRequest(\"GET\", endpoint, 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/model-frontier")) .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/model-frontier") req = Net::HTTP::Get.new(uri) req["Authorization"] = "Bearer YOUR_API_KEY" res = Net::HTTP.start(uri.hostname, 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. ````