Skip to content

RouteLLM

Serve and evaluate learned routers that choose between a stronger and a weaker model using a configurable cost-quality threshold.

Model-selection framework

Sources reviewed . Documentation review; not a performance benchmark or runtime test.

What can you do with RouteLLM?

Select between two models

Use a learned router to choose between a stronger and a weaker model.

Tune the cost-quality tradeoff

Calibrate the routing threshold against representative queries and the model pair you intend to serve.

Evaluate before serving

Use the framework to assess routing behavior; it is a model-selection framework rather than a hosted gateway account.

Before you integrate

Calibrate thresholds on representative queries and evaluate the model pair you actually intend to deploy.

Test against your own workload

Compare successful responses, latency and the total bill, including retries and fallbacks. Verify streaming, tool calls and structured output on the routes you plan to use. These are evaluation steps, not claims that every feature is supported.

Check model-provider incidents →

Pricing and model access

Model rates, platform fees, credits and eligibility can change. Check the publisher’s current terms before choosing a route. Our calculator estimates model token costs; it does not quote a negotiated RouteLLM bill.

Check RouteLLM documentation ↗

Package download trends

Compare router package adoption →

Downloads include automated installs and repeat downloads. They do not measure unique users, hosted requests or market share.

routellm

PyPI, excluding mirrors · Model-selection framework

5,706 downloads in 28 days

2026-09-29 to 2026-10-26

-15.3% versus the previous 28 days

Source and comparison period

Previous: 6,740 downloads, 2026-09-01 to 2026-09-28.

Retrieved 2026-10-27. This is a saved snapshot, not a live count.

Download data ↗ · Package identity ↗

Sources and corrections

Suggest an update →

Selected by product type and shared routing capabilities.

TensorZero →

An open-source gateway with routing, observability and evaluation. Its official repository is archived; assess maintenance before adopting it.

LiteLLM →

Run a proxy or use a Python router to distribute requests across model deployments, with load balancing, retries, cooldowns and fallbacks.

Merge Gateway →

Use one inference API with model routing, budgets and data controls. Choose ordered failover, intelligent selection or a custom benchmark-weighted routing policy.

View all LLM routers →

Search API Tracker

Curated starting points