Configs And Virtual Keys
Portkey AI Gateway · Portkey
AI Gateway — Portkey
Evaluates Portkey's Configs & Virtual Keys across 10 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI Gateway eval coverage.
About Portkey
Portkey is an AI gateway for production LLM apps — a unified, OpenAI-compatible API across 200+ models with provider routing and fallbacks, semantic and simple caching, input/output guardrails (PII redaction, prompt-injection, content moderation), request-level observability and traces, a versioned prompt library, virtual keys with per-key budgets and rate limits, and workspace RBAC + audit logs.
Sample tests· showing 3 of 10
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Team has OpenAI, Anthropic, Bedrock credentials; wants to rotate the OpenAI key without code changes. | Create a virtual key per upstream credential set; clients pass x-portkey-virtual-key (or it's set in a config) and never see the raw provider credential. Rotation = re-issue the underlying credential in the virtual key — operator code is unchanged. | Pass / FailAi Platformcritical |
| 02 | Virtual key configured 60 requests/minute; bursty caller sends 100 in 10 seconds. | Gateway rejects requests above the limit within the window (typical 429 response with retry semantics) [REQUIRES-VERIFICATION for the exact response shape]. Operator implements client-side backoff aligned with the limit; do not retry blindly. | Pass / FailAi Platformhigh |
| 03 | Virtual key has a $1,000/month token-cost budget; usage hits $1,001. | Per docs, budget-exceeded requests are denied at the gateway with a structured error [REQUIRES-VERIFICATION for the exact error shape]; operator alerts on budget-near-exhaustion (e.g., 80%, 95%) to act before deny. Do not silently fall back to a different key — that masks the overage. | Pass / FailAi Platformcritical |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Portkey
- Ai Platform
- Configs And Virtual Keys
Recommended for
Works with
Related evals
Claude API
Evaluates Anthropic's Batch API across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Extended Thinking across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Files API & Citations across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
ViewFrequently asked questions
What does the Configs And Virtual Keys eval for Portkey Portkey AI Gateway test?+
Evaluates Portkey's Configs & Virtual Keys across 10 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI Gateway eval coverage.
How is the Configs And Virtual Keys eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Configs And Virtual Keys pack for Portkey Portkey AI Gateway contains 10 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Configs And Virtual Keys pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.