Eval Library
O
For OpenRouterAI Platform

Parameter Parity Capability Routing

OpenRouter · OpenRouter

OpenRouter evals — Parameter Parity & Capability Routing (relift v3)

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.

Employees

~20

Industry

LLM Infrastructure

Headquarters

United States

Sample tests· showing 3 of 10

#InputExpected behaviorCheck
01

Five providers listed for openai/gpt-4o; three lack tools in supported_parameters; tools array populated.

Router restricts to tool-capable providers automatically; if none after only/ignore filters, fail with explicit error.

Pass / FailRoutinghigh
02

Legacy orchestrator sets parallel_tool_calls false; catalog does not expose per-provider parallel support uniformly.

Honor OpenAI-compatible parameter semantics; route to providers that can respect constraint or fail clearly—do not invent unsupported parameter passthrough.

Pass / FailRoutingmedium
03

Research eval needs token logprobs; cheapest provider on slug lacks support.

Restrict to providers supporting logprobs or return clear error; do not zero-fill fake logprobs.

Pass / FailRoutinglow

Rubric criteria

  • Openrouter
  • Ai Platform
  • Parameter Parity Capability Routing

Recommended for

OpenRouterOpenRouter customers

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.