Connect model providers
Use the gateway through an OpenAI-compatible interface or its Python client.
Self-hosted gateway
TensorZero
An open-source gateway with routing, observability and evaluation. Its official repository is archived; assess maintenance before adopting it.
Sources reviewed . Documentation review; not a performance benchmark or runtime test.
What can you do with TensorZero?
Configure reliability
The documented gateway supports retries, fallbacks and load balancing.
Evaluate inference behavior
Use recorded inferences and feedback to compare prompts and model configurations.
Before you integrate
The official repository was archived on June 12, 2026. Review maintenance and dependency risks before deploying. A published Python package does not establish ongoing support.
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 TensorZero bill.
Check TensorZero documentation ↗Package download trends
Downloads include automated installs and repeat downloads. They do not measure unique users, hosted requests or market share.
tensorzero
PyPI, excluding mirrors · Python client and embedded gateway
24,128 downloads in 28 days
2026-09-29 to 2026-10-26
-27.8% versus the previous 28 days
Source and comparison period
Previous: 33,432 downloads, 2026-09-01 to 2026-09-28.
Retrieved 2026-10-27. This is a saved snapshot, not a live count.
Sources and corrections
Suggest an update →Compare related routing products
Selected by product type and shared routing capabilities.
LiteLLM →
Run a proxy or use a Python router to distribute requests across model deployments, with load balancing, retries, cooldowns and fallbacks.
Bifrost →
Run an OpenAI-compatible gateway with provider failover, load balancing and a web interface for configuration.
RouteLLM →
Serve and evaluate learned routers that choose between a stronger and a weaker model using a configurable cost-quality threshold.