Use Cases + Implementation

How do you build model evaluation with an OpenAI-compatible API?

An OpenAI-compatible API turns model comparison into a configuration exercise: keep one client, change the model parameter, and replay the same prompt suite against every candidate. On Plugsky, 30+ models sit behind the same endpoint with streaming, JSON mode and function calling, so an evaluation harness measures quality, latency and refusal behaviour without per-provider adapters.

Key facts

Evaluation approachOne client, one suite, swap the model parameter
API compatibilityOpenAI-shaped chat completions with streaming, JSON mode and function calling (live)
Models30+ models behind one endpoint for side-by-side runs
Structured scoringJSON mode for rubric scores and pass/fail flags
Deterministic checksTool-based validation of outputs and tool calls
PricingFlat monthly plans with unlimited fair-use usage on self-serve
DeploymentRegion-locked planes, VPC, on-prem and air-gapped options
Free tierplugsky-micro and plugsky-lite on the free plan, no card required

TL;DR

  • Make the model a parameter in your harness, not an assumption in your code.
  • Replay identical prompts and settings so differences come from the model alone.
  • Score quality with a rubric and JSON output; check schema validity in code.
  • Measure latency and refusal behaviour alongside accuracy.
  • Keep the suite small, fast and growing — every incident becomes a case.

How it works, step by step

  1. Build the harness around a single client with the base URL in configuration and the model as a per-run parameter.
  2. Assemble a suite of real prompts with expected answers, plus edge cases and must-refuse inputs.
  3. Add deterministic checks for schema validity, required fields and tool-call correctness.
  4. Add a judge model with a rubric and JSON output for semantic quality, calibrated on human ratings.
  5. Run the suite across candidate models, recording quality, latency and failure categories per model.
  6. Compare arms head to head and pick a primary model plus a fallback for each workload.
  7. Schedule the suite to re-run on prompt changes and periodically against production samples.
1Build the harnessaround a singleclient with the2Assemble a suite ofreal prompts withexpected answers,3Add deterministicchecks for schemavalidity, required4Add a judge modelwith a rubric andJSON output for5Run the suiteacross candidatemodels, recording6Compare arms headto head and pick aprimary model plus

Try it yourself

Open the best AI model picker →

One client, many models

The main cost of model evaluation used to be integration: every vendor had its own SDK, auth and response shape. With an OpenAI-compatible API that overhead disappears. Your harness keeps one client, changes the model value and replays the same prompts — differences in output come from the model rather than the plumbing.

Plugsky exposes 30+ models through that single endpoint with streaming, JSON mode and function calling live, so candidate models can be tested on exactly the behaviours your product depends on: structured output, tool calls, long inputs and refusals.

Designing a trustworthy suite

A useful suite is small, labelled and honest about failure. Include representative real prompts, boundary cases, structured-output tasks, tool-use tasks and inputs the system must refuse. Keep expected outputs human-verified, and version everything — prompts, temperature, max tokens — so a re-run is comparable to the last one.

  • Stratify: score by category, not just overall, so a model strong on writing but weak on extraction is visible.
  • Determinism where possible: set temperature to zero for extraction tests; score creative tasks with a rubric.
  • Cost and latency: record tokens, wall-clock time and error rates per model alongside quality.
  • Adversarial cases: prompt injection attempts and malformed inputs belong in the suite.

From results to a routing decision

Evaluation output should be an operational decision: which model for which workload, and what fallback to use. Many teams land on a tiered arrangement — plugsky-micro or plugsky-lite for cheap, high-volume classification and extraction, a mid-tier model for general chat, and a frontier model for hard reasoning. With everything behind one endpoint, that decision is expressed in configuration rather than architecture.

Keep the suite running. Prompts drift, models get updated and traffic changes shape. Periodic runs against production samples catch regressions early, and each incident becomes a new case. Because the API is OpenAI-compatible, adding or replacing a candidate later is a one-line change to the harness.

Honest comparison

AspectPlugskyMulti-provider adaptersSingle-vendor testing
Candidate coverage30+ models, one clientOne adapter per vendorVendor catalogue only
Setup effortModel parameter changeSDK and auth per providerNone, but narrow
Structured checksJSON mode plus function callingVaries by vendorVendor-specific
Cost shapeFlat monthly with unlimited fair use on self-serveMixed per-provider billsPer-token
ReproducibilityPin model and settings per runGood, with effortLimited alternatives

Frequently asked questions

Do I need different code per model?

No. Change the model parameter on the same client. That is the practical benefit of an OpenAI-compatible endpoint for evaluation and for production routing.

How do we judge quality without humans?

Use a rubric-driven judge model and calibrate it against human ratings on a sample. Keep deterministic checks — schema validity, exact matches, tool-call correctness — in code rather than with a model.

Should temperature be zero?

For extraction and classification tests, yes. For tasks where variation is expected, score multiple samples with a rubric instead of pretending a single deterministic answer exists.

What metrics belong in the report?

Quality by category, schema validity rate, tool-call accuracy, refusal correctness, latency and error rate. Quality alone hides operational regressions.

How do we compare cost fairly?

Self-serve plans are flat monthly with unlimited fair-use usage rather than per-token billing. Check the live pricing page for current plan terms before modelling heavy evaluation runs.

Can evaluation run on private prompts?

Yes. The harness runs in your environment, and Plugsky supports region-locked planes plus VPC, on-prem and air-gapped deployment for sensitive data.

How do we begin?

Start on the free plan with plugsky-micro and plugsky-lite and no card, build a 30–50 case suite, then expand candidates and volume on a paid plan or the 14-day full-access trial.