ekte — LLM relay reality check

🇬🇧 English · 🇨🇳 中文 · 🇫🇷 Français · 🇪🇸 Español · 🇵🇹 Português · 🇮🇹 Italiano · 🇩🇪 Deutsch · 🇳🇴 Norsk

ekte is a local-first tool that audits whether an API relay (reseller / proxy) actually serves the model it claims to — or quietly substitutes a cheaper one, truncates your context window, fakes streaming, or inflates token billing. In short: do you get what you paid for? It speaks the OpenAI Chat Completions API, the Anthropic Messages API and the OpenAI Responses API (/v1/responses) — auto-detected, or forced with --api openai|anthropic|responses.

You point it at a relay endpoint and the model it claims to serve; ekte runs a battery of black-box probes, compares what it observes with a bundled knowledge base of 130 model profiles from 7 providers, and gives a clear, evidence-backed verdict — on the command line, in a local web UI, or as JSON for another tool or LLM.

ekte reports black-box evidence of divergence and risk, not cryptographic proof of fraud. See Responsible use.

Why

The relay-key market is full of "GPT-4o for 1/10th the price" offers. Many are honest. Some are not — and the dishonest ones are hard to catch by eye:

• You ask for gpt-4o; you're quietly served gpt-4o-mini or an open model.
• The relay advertises a 1M-token context but silently truncates to 32K.
• "Streaming" is the full response buffered and re-chunked, with no latency win.
• Reported usage tokens are inflated, so your balance burns faster than it should.
• A model that should support tool calling / JSON mode quietly doesn't.

ekte turns "this feels off" into a reproducible report.

Install

Requires Python 3.11+ on Linux, macOS or Windows.

pip install 'ekte[web]'          # or: uv tool install 'ekte[web]'

The web extra adds the local web UI; leave it out for the command line only. From source, with uv or in Docker: Install.

Quick start

export EKTE_API_KEY=sk-your-relay-key

# audit a relay against the model it claims to serve
ekte check --base-url https://relay.example.com/v1 --api-key env:EKTE_API_KEY \
  --model gpt-4o --suite standard

# the strongest check: compare against a trusted baseline of the same model
export OPENAI_API_KEY=sk-your-openai-key
ekte compare \
  --target-base-url https://relay.example.com/v1 --target-api-key env:EKTE_API_KEY --target-model gpt-4o \
  --baseline-base-url https://api.openai.com/v1 --baseline-api-key env:OPENAI_API_KEY --baseline-model gpt-4o

# or point and click: the local web UI
ekte serve

More examples, config files and use from scripts or LLM agents: Quick start. The web UI: Web UI.

What it checks

ekte scores ten dimensions. The four core dimensions — model identity, context window, capability claims and billing & usage — most directly reveal a bait-and-switch. The names are the ones the web UI and reports use.

How every check works and how the verdict is reached: Methodology.

Documentation

Contributing: Contributing guide and Developer guide (English). Security issues: Security policy.

License

Apache-2.0