{"uid":"cap_En_vpY-oc6DO9hDQjiBVV","slug":"animica-health-model-evaluate-d5abae2a","name":"Animica Health Model Evaluate","description":"Animica Python Cloud: deploy a Python function to animica.dev, get a public endpoint, and earn ANM every time someone runs it. Free AI (OpenAI-compatible, no key), free scheduled Workers, and an 80/20 developer split.","url":"https://animica.dev/x402/health/model/evaluate","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"suite":{"type":"string","description":"from GET /health/v1/evaluations/suites"},"model_id":{"type":"string"},"model_version":{"type":"number"}}},"responseSchema":{"type":"json"},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.006","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.006/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.006","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.006","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ioR6TwB4tZ4w0b2c1FubH","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.006","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs a named evaluation suite against a specific model version and returns health/quality assessment results","exampleAgentPrompt":"Run the 'accuracy' evaluation suite on model 'llama-3-8b' version 2 using Animica and tell me the results.","exampleUseCases":[{"title":"Pre-deployment model quality gate","prompt":"Before I deploy model 'gpt-mini-finetune' version 3, run it through the 'safety-checks' evaluation suite on Animica and show me whether it passes."},{"title":"Comparing model versions after fine-tuning","prompt":"I just released version 4 of 'my-custom-classifier' — can you run the 'classification-accuracy' suite on it via Animica so I can see how it compares to the previous version?"},{"title":"Scheduled model health monitoring","prompt":"Every morning, run the 'hallucination-detection' evaluation suite against model 'rag-assistant' version 1 on Animica and alert me if the score drops below the baseline."}],"resultDescription":"A JSON object containing the evaluation results for the specified model version against the named suite, including scores, pass/fail indicators, and per-test metrics as defined by the suite.","failureModes":["Invalid or unknown suite name returns an error — use GET /health/v1/evaluations/suites to retrieve valid suite names","Unknown model_id or model_version combination returns a not-found error","Payment failure (insufficient USDC balance) blocks the call","Malformed request body returns a 400 validation error","Model version mismatch or incompatibility with the suite may return a partial or error result"],"whenToPreferThis":"Use this endpoint when you need to programmatically evaluate a specific AI model version against a predefined health or quality suite on the Animica platform, especially within automated CI/CD pipelines, scheduled monitoring workflows, or when comparing model versions. Prefer this over manual evaluation when you need reproducible, pay-per-call on-demand benchmarking without managing infrastructure.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:47:47.010Z","isFirstParty":false}