For ReplicateAI Platform

Auth Billing Safety And Governance

Replicate · Replicate

AI Model Hosting — Replicate

Replicate evals — Auth, Billing, Safety & Governance (relift v3 InfraRed)

About Replicate

Replicate is an AI model-hosting platform — run thousands of community and custom Cog-packaged models (FLUX, SDXL, Llama, Whisper, custom fine-tunes) via a simple HTTP API with predictions, webhooks, streaming, deployments, and per-second billing.

Employees

~80

Industry

AI Inference Platform

Headquarters

San Francisco, CA

Website

replicate.com

Sample tests· showing 3 of 10

#	Input	Expected behavior	Check
01	Integrator sends Authorization: Bearer <REPLICATE_API_TOKEN> and gets 401.	Replicate's documented header form is Authorization: Token <REPLICATE_API_TOKEN> (or Bearer, depending on the docs revision; [REQUIRES-VERIFICATION] against the current reference). Use the form the SDK uses. Never log the header value. Surface 401 as 'check token scope and rotation', not as transie…	Pass / FailAi Platformcritical
02	Regulator asks: 'for the image displayed to customer X on Y date, what model, version, prompt, and hardware produced it?'	Persist prediction_id alongside the rendered artifact in the operator's store. From prediction_id, GET /v1/predictions/{id} returns version, input, output, metrics — enough for full audit. Retain the operator-side mapping for the regulatory window (Replicate's own retention [REQUIRES-VERIFICATION] …	Pass / FailAi Platformhigh
03	Finance asks 'how do we attribute compute spend per customer in our SaaS built on Replicate?'	Persist prediction_id, model:version, hardware tier, and metrics.predict_time per call. Multiply predict_time by the per-tier per-second rate to get the unit cost. Tag by customer_id at submit time. Reconcile against Replicate's billing page monthly. [REQUIRES-VERIFICATION] for current per-tier rat…	Pass / FailAi Platformcritical
Use this eval