Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Unbiased tiers - Template - OpenSmartRoute
Templatev1.0.0
Unbiased tiers
Unbiased only: Pareto 26.10 for everyday requests, Pareto Latest for moderate work, Pareto 26.9 for hard ones - with complexity rules and a cost-aware objective.
Generated from the reference model catalogue (the OpenRouter listing) - regenerated daily as the line-up and prices change. Import it with registry://<slug>@<version> or osr stack apply; every target answers on https://openrouter.ai/api/v1 with your own key.
Unbiased tiers
Unbiased only: Pareto 26.10 for everyday requests, Pareto Latest for moderate work, Pareto 26.9 for hard ones - with complexity rules and a cost-aware objective.
Targets
Pareto 26.10 (Unbiased) - $0.80 in / $3.20 out per 1M tokens
Pareto Latest (Unbiased) - $0.80 in / $3.20 out per 1M tokens
Pareto 26.9 (Unbiased) - $2.50 in / $7.50 out per 1M tokens
2 routing rule(s); every target answers on https://openrouter.ai/api/v1 (OpenAI-compatible).
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
A declarative stack: models, rules and settings in one file. `osr stack apply` turns it into a running router.
Installed into a catalogue, chosen by a router
Install Unbiased tiers and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
