Observed by Atlas — nobody has proved they control this domain. Is it yours?

THE FLOW/MLOPS/INFERCRANE

InferCrane

OBSERVED

An execution layer that selects and tunes inference stacks for open models

OPEN SOURCE·MLOPS·ai infrastructurellm inferencedev tools
OUTBOUND CLICKS · 28 DAYS · BOT-FILTERED2 REAL CLICKS
FRESHNESS
0.97
DECAYS BETWEEN READS
READINGS
—
VERIFIED / MEASURED
VOUCHES
0
SIGNED STATEMENTS
THREADS
0
FIELD NOTES
CLICKS · 28D
2
BOT-FILTERED
FIRST SEEN
AUG 29
IN THE FLOW
infercrane.comCAPTURED 1d AGOOPEN FULL CAPTURE ↗
InferCrane — hero
HERO
WHAT IT DOES · WRITTEN BY ATLAS, UNREVIEWED BY AN OWNER

InferCrane takes a workload's quality bar, SLOs, privacy boundary, and budget, then searches across models, runtimes, configurations, kernels, hardware, and supply to find a qualified execution path, exposed behind one stable API. It is aimed at teams running open-model inference who want to evaluate or migrate from OpenAI or Claude workloads, or optimize dedicated deployments on their own infrastructure.

ai infrastructurellm inferencedev tools
CLAIMS

Nothing measured yet. A reading is a measurement with its evidence attached — uptime checked, pricing re-read against what the page claims. Raise a checkable claim in a field note below and Atlas will measure it.

PRICING
READ 1d AGO
MODEL API
Prepaid credits, no subscription

OpenAI-compatible endpoint · Prepaid credits, no subscription · Usage limits + spending caps · Supported open-model catalog · Usage and billing visibility

DEDICATED & OPTIMIZED
Contact sales

Custom deployments · Customer-owned compute · NVIDIA / AMD / Intel testing · Runtime optimization · Kernel work where justified

WHAT CHANGED

Every crawl is diffed. Material changes are listed.

4 CRAWLS ON RECORD
SEP 28PLAN STRUCTUREModel API tier: — → Prepaid credits, no subscription · Dedicated & Optimized tier: — → Contact sales
SEP 21CAPABILITYA claim: — → infercrane provides an openai-compatible endpoint for accessing supported open models · A claim: — → infercrane's model api uses prepaid credits with no subscription · A claim: — → infercrane's execution stack can run on nvidia, amd, intel, tpu, and trainium silicon · A claim: — → infercrane is currently offering 5 workload pilot slots under founding access, with applications open
SEP 14PRICINGPricing model: open_source → paid
VOUCHED BY

Nobody has vouched for InferCrane yet.

SIGNED STATEMENTS OF USE · NOT A RATING

A vouch says you use it. Your handle, how long, and an optional note.

I use this — vouch
FIELD NOTES

Have a question about InferCrane? Ask the people using it.

SIGNED POSTS · THREADS STAY OPEN

No field notes yet. A field note is about use: what broke, what it replaced, what the docs don't say. Anything in one that makes a checkable claim gets measured by Atlas, which replies with the reading.

Signed with your handle.

Outbound clicks are counted for the builder.

Claim it