> ## Documentation Index
> Fetch the complete documentation index at: https://infercrane.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Recipes and Inference Lab

> Capture immutable serving evidence and compare measured candidates without hidden provisioning.

# Recipes and Inference Lab

Recipes turn one real deployment revision into a content-addressed, reproducible record. InferCrane
will only capture a recipe when the active revision has an immutable ModelArtifact, an explicit
runtime version, and a matching persisted AIPerf benchmark.

```bash theme={"theme":{"light":"github-light-default","dark":"vesper"}}
infercrane benchmark qwen-prod --requests 100 --concurrency 10
infercrane recipe create qwen-prod \
  --name qwen3-8b-balanced \
  --version 1.0.0
infercrane recipes qwen3
```

The recipe payload records the immutable model commit, runtime/version/arguments, provider adapter,
region, GPU, compute mode, workload contract, benchmark workload, and benchmark ID. Provenance records
the deployment/revision, artifact, benchmark tool/version, InferCrane version, and evidence class.
The SHA-256 digest covers both canonical objects. Retrying the same name/version is idempotent only
for identical content; different content is rejected.

## Compare evidence

Inference Lab v1 compares existing benchmark history. It does not provision hardware or run another
load generator:

```bash theme={"theme":{"light":"github-light-default","dark":"vesper"}}
infercrane lab 'Qwen/Qwen3-8B@IMMUTABLE_COMMIT' \
  --max-ttft-p95-ms 250
```

Rows are ordered by measured p95 TTFT and include runtime, provider, GPU, error rate, throughput, SLO
result when measurable, and cost metadata exactly as persisted. Current Lab results emit only
`MEASURED` rows.
The schema reserves `modeled` and `heuristic` labels for future evidence sources, but InferCrane never
substitutes them silently. With no comparable benchmark, the result is an empty persisted evaluation.

Use `--workload-digest` to require an exact canonical benchmark workload. Prompt and output content
are not part of recipes, benchmark history, or Lab evaluations.

## Qualification boundary

A captured recipe proves provenance, not universal portability. Provider/runtime support remains
scoped to the integration matrix, and local benchmark fixtures are not real GPU evidence. Cost remains
unavailable unless a trustworthy source and observation timestamp were persisted with the benchmark.