Current context and completion limits for the workload you plan to run.
OpenRouter model comparison
Compare OpenRouter models by the constraints that actually matter.
OpenRouter exposes a broad and fast-moving model market. ModelShortlist helps your AI assistant narrow that market using current context, supported parameters, pricing, provider facts, optional ZDR evidence, and independent Artificial Analysis performance context.
The decision
The answer changes with the workload.
A useful OpenRouter comparison starts with the workload, not with a fixed list of popular models. Decide which requirements are hard constraints, then compare the eligible set on quality, economics, and operational fit.
Supported parameters such as tool use when those capabilities are mandatory.
Current input/output pricing, including tiered pricing where applicable.
Provider and ZDR endpoint facts only when the workload actually requires them.
Independent performance evidence
Artificial Analysis
ModelShortlist uses Artificial Analysis benchmark and performance evidence when the model identity can be reconciled confidently. It does not create, relabel, or pretend ownership of those benchmarks.
How Artificial Analysis contributesCurrent operational facts
OpenRouter
The current catalog supplies model availability, context, supported parameters, pricing, and provider details. ZDR endpoint evidence is applied only when the workload explicitly requires ZDR.
Compare OpenRouter models by workloadModel selection is time-sensitive: new models launch, prices move, benchmark results change, tool support evolves, and providers add or remove endpoints. ModelShortlist surfaces freshness and degraded upstream state instead of silently presenting stale evidence as current.
Ask naturally
Prompts that work.
ModelShortlist sits behind the AI assistant you already use. Describe the job and hard constraints instead of translating them into a fixed ranking formula.
“Compare the best current OpenRouter models for a long-running coding agent with tools and at least 100k context.”
“Which OpenRouter models under $10 per million output tokens are still strong enough for this workload?”
“Compare these OpenRouter model IDs and separate benchmark quality evidence from price, context, and provider facts.”
Why ModelShortlist
Current evidence, not a static leaderboard.
Starts from the current OpenRouter catalog instead of a hand-maintained model list.
Can compare specific OpenRouter model IDs or build a broader shortlist from workload constraints.
Adds Artificial Analysis evidence only when model identity reconciliation is confident.
Treats ZDR as optional by default and checks endpoint-level hard constraints only when you explicitly require it.
Local BYOK architecture. No ModelShortlist account, hosted key vault, or telemetry in the MCP.
Put current model-selection evidence inside your assistant.
Install the local MCP, add your OpenRouter and Artificial Analysis keys, and ask the model-selection question in normal language.
Open the install configurator