AnyInt Docs

Smart Routing (Coming Soon)

Smart Routing (Coming Soon) is the coming AnyInt product direction for task-aware model selection, cost control, and fallback policy.

Smart Routing is an upcoming AnyInt product direction for task-aware model selection, cost control, and fallback policy. This section explains the planning model, but it is not a published automatic-routing API contract.

Availability

Smart Routing is not generally available yet. Use this section to understand the product model and integration planning assumptions, and confirm production availability before depending on an automated routing API.

What you can do today

Until an automated Smart Routing API is generally available, production applications should make routing decisions explicitly:

NeedCurrent public pattern
Confirm account-level model accessCall Models API and use returned data[].id values
Pick a route familyChoose OpenAI-compatible, Anthropic-compatible, Gemini-compatible, media, or music APIs based on request shape
Control reliabilityDocument primary and fallback model IDs in application configuration
Control costSeparate high-value workloads from lower-risk batch or extraction workloads
Detect route failuresHandle 401, 403, 429, and temporary upstream errors as described in Errors and Limits

Planning checklist

If you are designing an application that will later benefit from Smart Routing, keep these decisions outside hardcoded prompt logic:

  1. Store primary and fallback model IDs in configuration.
  2. Keep workload labels such as chat, extract, classify, code, image-understanding, or media-generation near the call site.
  3. Record whether the workload optimizes for quality, latency, cost, or reliability.
  4. Make retries and fallback behavior observable in logs or metrics.
  5. Keep provider-native request bodies isolated so they can be changed without rewriting product logic.

What not to assume

Do not assumeUse instead
A hidden /smart-routing endpoint is availableOnly call published routes in API Reference
AnyInt will automatically choose a model for every request todaySend explicit model IDs returned by the Models API
A fallback is safe without testingVerify the fallback model's request shape, latency, and output quality
Cost optimization is only a provider choiceAlso consider prompt size, streaming behavior, caching, retries, and task design

Until Smart Routing (Coming Soon) is generally available, production applications should still choose explicit model IDs, document fallback behavior, and use Models API to confirm account-level model access.

On this page