Compatibility
Does the endpoint actually follow expected API behavior?
Validate compatibility, capability and reliability of OpenAI-compatible AI APIs.
pip install apiwellsRuns locally. Your API keys stay off this website.
$ apiwells doctor01 / THE PROBLEM
An endpoint URL is a starting point. Understanding its behavior comes next.
Does the endpoint actually follow expected API behavior?
Does it support streaming, tools and structured outputs?
Can developers understand failures before production?
02 / DIAGNOSTIC COVERAGE
Check connectivity in Basic mode.
Opt into Deep for chat, streaming, tools and structured output.
Hostname resolution
Secure connections
Response behavior
Access to the endpoint
Model availability
Expected API behavior
Streaming responses
Token usage reporting
Tool call capability
Structured responses
03 / HOW IT WORKS
A short path from an endpoint to diagnostic evidence.
Start with the Endpoint Doctor CLI.
pip install apiwellsRun diagnostics from your machine.
apiwells doctor --base-url https://YOUR-API-HOST/v1Inspect the evidence before you ship.
Replace https://YOUR-API-HOST/v1 with your exact API base URL and configure APIWELLS_API_KEY locally. Capability checks require --deep --model YOUR-MODEL-ID and may incur API charges. Read the quick start
04 / THE OUTPUT
A real diagnostic run, from connection checks to validated tool calls and structured output.
Endpoint Doctor Report
CLI 0.2.1 / qwen3.8-flash
10 checks passed in this recorded run.
Report complete.
05 / BUILT FOR DEVELOPERS
A focused tool for the work between choosing an API and putting it into production.
06 / FUTURE DIRECTION
Endpoint Doctor is the starting point.
Evaluation and optimization are long-term directions, not available products.
BEFORE THE NEXT DEPLOY
Start with a diagnostic report from your own machine.