Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Set model to openrouter/auto to let OpenRouter choose a model for each request. Add a provider object to control which provider can serve the selected model. These are separate decisions: Auto Router chooses which model; provider routing chooses which host.
Let OpenRouter choose a model for each request
Send openrouter/auto as the request’s model. Auto Router evaluates the prompt and selects from its current candidate models; the response’s model field identifies the model that answered. The eligible pool can change, so treat it as dynamic rather than relying on a fixed example list. See OpenRouter’s Auto Router documentation.
As an Amazon Associate I earn from qualifying purchases.
This is useful when your requests vary and different prompts may benefit from different models. A fixed model slug gives you a more predictable choice; Auto Router trades that predictability for delegated selection.
Choose which provider can serve the selected model
Provider routing is configured separately in the request body. For example:
#1 Best Overall
{
"model": "openrouter/auto",
"messages": [{"role": "user", "content": "..."}],
"provider": {
"order": ["preferred-provider"],
"allow_fallbacks": true
}
}This illustrates the structure, not a guarantee that the named provider can serve every model Auto Router might select. The selected provider needs a compatible endpoint for that model. Check the available endpoints and current routing options in OpenRouter’s Provider Routing documentation.
Use the setting that matches your control goal
ordergives an explicit preferred provider sequence.onlyrestricts eligible routing to an allowlist.ignoreexcludes specified providers.allow_fallbackscontrols whether OpenRouter may try other providers if the preferred route fails.
If a provider must be used, define the eligible providers and fallback policy explicitly. Turning fallbacks off tightens the route but can leave the request without a usable endpoint if the permitted provider is unavailable or incompatible with the chosen model.
Understand what happens when you leave provider routing unset
When provider sorting and ordering are not specified, OpenRouter documents a price-oriented balancing strategy that also accounts for recent instability. Providers with significant outages in the previous 30 seconds are moved behind stable endpoints. Among low-cost stable providers, selection uses inverse-square price weighting; remaining providers can serve as fallbacks.
Recommended Free Tools
In OpenRouter’s illustrative example, a provider priced at $1 per million tokens is nine times as likely to be tried first as one priced at $3, all else equal, while a recently unstable $2 provider is tried later. This explains the documented weighting approach; it does not predict or guarantee the route for a particular live request.
Override the default with cost, speed, or endpoint policies
Adding provider.sort or provider.order disables the default load-balancing behavior and directs routing according to the specified sort or sequence.
| Goal | Setting | What it does |
|---|---|---|
| Lower cost | sort: "price" |
Prioritizes lower-priced providers. A max_price ceiling can cause the request to fail if no endpoint is available within the limit. |
| Higher throughput | sort: "throughput" |
Prioritizes throughput. |
| Lower latency | sort: "latency" |
Prioritizes lower latency. |
| Preferred provider sequence | order |
Lists providers to try and their order. |
Minimum-throughput and maximum-latency preferences are soft: endpoints outside the preferred range are moved later, not made impossible to select. They do not guarantee that a threshold will be met.
Other filters can narrow eligible endpoints: data_collection, zdr, and require_parameters, along with only and ignore. For privacy- or compliance-sensitive use, confirm current endpoint metadata and any account-level policies instead of assuming that a routing preference alone establishes compliance.
OpenRouter also documents :nitro and :floor model suffixes as shortcuts: :nitro sorts for throughput and permits priority-tier endpoints; :floor sorts for price and permits flex-tier endpoints. These variants affect service-tier eligibility as well as sorting, so they are not equivalent to setting provider.sort alone.
Distinguish provider fallback from model fallback
Provider fallback keeps the requested model and tries another host for it. Model fallback changes the model: supply a models list in priority order, and OpenRouter can try the next model after documented errors such as context-length validation, moderation flags, rate limits, or downtime. The response identifies the model that ultimately answered, and that model determines the request’s model pricing. Do not confuse models with provider.order.
For the Anthropic Messages API, OpenRouter also documents a fallbacks field. It cannot be combined with models, accepts at most three entries, and is handled by OpenRouter’s routing. See the model fallback guide.
Check current models and verify the route
Use the live Models API rather than a copied catalog. Its filters cover query or name, category, parameter support, modality, context, price, author, hosting provider, ZDR, and region. It can sort by price, context length, throughput, latency, popularity, weekly activity, recency, and benchmark indices. Model slugs, prices, endpoint availability, and supported parameters can change; verify them during implementation and when you need current routing details.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
After a request using openrouter/auto, inspect the response’s model field to learn which model answered. For provider-sensitive requirements, consult current endpoint documentation and the request/response metadata available for the request; the model field alone identifies the model, not necessarily the hosting provider.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
