AI Agent StoreUnbiased · Native stable composite service
Pareto 26.10 · native stable
Send a request to a service that combines several models into one answer. This is the stable October release; the older OpenRouter preview page is a separate offer.
Released 2026-10-15 · First reviewed 2026-10-16 · Checked 2026-10-16.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact provider API ID: pareto-26.10. The displayed provider evaluations are preliminary October 1 preview runs, not new measurements of the stable release. No independent score is assigned here.
The native pareto alias now selects stable 26.10. Use pareto-26.10 to choose it explicitly, or pareto-26.9 to retain the older version. Accounts are reviewed manually. Data-retention terms depend on your direct plan.
The provider announces a one-million-token context. Exact token boundary and maximum generated output are not verified here.
The provider kept preview pricing at graduation: $0.80 input, $0.03 cached input and $3.20 output per million tokens. Personal subscription allowances doubled; subscriptions and API token prices are different billing plans. Allow for retries and any tool fees. Models that think before answering may also charge for that work.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗