Router Metadata Observability
OpenRouter · OpenRouter
LLM routing and aggregation — OpenRouter
Evaluates OpenRouter's Router Metadata & Observability across 10 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's LLM routing and aggregation eval coverage.
About OpenRouter
OpenRouter is a unified LLM routing layer that gives developers access to hundreds of models through a single OpenAI-compatible API. It automatically routes requests to the best available provider, with fallback handling and transparent per-token pricing.
Sample tests· showing 3 of 10
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | SRE enables pipeline tracing without storing prompts; needs attempt-level visibility. | Set X-OpenRouter-Experimental-Metadata on request per router metadata guide; parse openrouter_metadata from response header/body as documented. | Pass / FailObservabilityhigh |
| 02 | Identical prompts produce fast responses; SRE sees empty metadata header intermittently. | Router metadata guide documents stripping on cache hits; use generation id lookup or bypass cache for full pipeline when debugging. | Pass / FailObservabilitymedium |
| 03 | Three providers tried; final success on third; metadata enabled. | Attempts lists ordered try history with provider identifiers and failure classes leading to winner—used for SRE postmortems. | Pass / FailObservabilityhigh |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric.
Rubric criteria
- Openrouter
- Ai Platform
- Router Metadata Observability
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 Router Metadata Observability eval for OpenRouter OpenRouter test?+
Evaluates OpenRouter's Router Metadata & Observability across 10 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's LLM routing and aggregation eval coverage.
How is the Router Metadata Observability eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric.
How many test cases does this eval pack include?+
The Router Metadata Observability pack for OpenRouter OpenRouter 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 Router Metadata Observability 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.