For xAIAI Platform

Auth Rate Limits And Concurrency

xAI API (Grok) · xAI

Foundation Model & API — xAI (Grok)

xAI evals — Auth, Rate Limits & Concurrency (relift v3 InfraRed)

About xAI

xAI builds the Grok foundation-model family and the xAI API — OpenAI-compatible chat completions, function calling, Live Search / DeepSearch real-time web grounding, Grok Vision multimodal inputs, reasoning models with a thinking-effort budget, and Grok / Aurora image generation.

Employees

~1,000

Industry

Foundation Model

Headquarters

Palo Alto, CA

Website

x.ai

Sample tests· showing 3 of 9

#	Input	Expected behavior	Check
01	Client authenticates with Authorization: Bearer <XAI_API_KEY> on every request to https://api.x.ai/v1.	Pull the key from environment / secret manager — never embed in source. Set Authorization: Bearer <key> exactly once per request. Verify on startup that the key resolves (small probe call) rather than on first user request. Rotate keys via the xAI console; revoke immediately on leak.	Pass / FailAi Platformcritical
02	Org has multiple workspaces / projects with different cost owners. Each should bill independently.	Issue project-scoped API keys per workspace/project via the xAI console. Each key isolates usage, RPM/TPM tier, and billing. Do not share a root key across projects. [REQUIRES-VERIFICATION] on current project-scoping field/header conventions against docs.x.ai.	Pass / FailAi Platformhigh
03	Operator's workflow makes few requests but each is huge (long context). Hits TPM cap before RPM cap.	Track both RPM and TPM independently. TPM is bounded by tokenized request size; truncate / chunk long inputs to stay within budget. Choose the tier by the bottleneck dimension, not the cheaper one. Per-tier numerics are [REQUIRES-VERIFICATION] from docs.x.ai.	Pass / FailAi Platformmedium
Use this eval