Skip to content
NeoShunt
The Proving Ground

Which model, on which platform, at what cost.

Submit your real documents. Every feasible model answers every one, an independent judge grades them all, and the ranking is priced at your actual volume. What you get back isn't inference — it's a defensible decision, kept honest over time by drift detection.

No vendor account needed to run one. You sign up for the winner, not the shortlist.

completed3 samples · 9 models · 45 answers graded

Qwen 2.5 14B for 501 items

$1.42

quality 4.31 ± 0.12 across 3 samples · $0.00283 per item · the priciest option that fits would be $4.67
Top four models from a completed Proving Ground run
ModelQualityAt 501
Qwen 2.5 14B4.31 ± 0.12$1.42
Claude Haiku 4.54.24 ± 0.19$4.67
Llama 3.1 70B4.02 ± 0.22$1.20
Gemini 3.6 Flash3.88 ± 0.31$0.59

An actual verdict screen. When the top two overlap within their spread, the platform says too close to call instead of naming a winner.

How it works

A measured decision, not a recommendation engine

Four steps, all of them evidence. Nothing here is a projection.

  1. 01

    Bring real items

    Paste or upload a few representative documents — up to five. Several rather than one, because a single document cannot tell a model that is reliably good from one that got lucky.

  2. 02

    Every feasible model answers

    Our shortlist, or your own candidate list. Models that cannot hold your sample are excluded with the reason, not silently dropped.

  3. 03

    An independent judge grades

    Every answer, on the same rubric: are the claims true, is anything missing, does it follow instructions. Graded out-of-band, not by the model that answered.

  4. 04

    Priced at your volume

    You state how many items like these you actually run. The ranking is costed at that number, per platform, including the priciest option that fits.

The platform is allowed to decline

A confident wrong recommendation would destroy the premise of the product. “These two are within noise” would not — so when the evidence doesn't separate the top two, the verdict says so and shows you the cost gap instead.

Profiles

One object crosses into production

A finished bake-off can become a profile: the decision, made durable. Your application sends a profile id instead of a model id, and the platform routes what was measured.

POST /v1/chat/completions
Authorization: Bearer $NEOSHUNT_KEY

{ "profile": "invoice_extract",
  "messages": [{ "role": "user", "content": "…" }] }

Same handlers as the UI, bearer-key auth. Routing is part of membership.

Quality drift

The chosen model quietly gets worse on your workload — re-graded against the run that picked it.

Price drift

A vendor changes its list price, or a cheaper platform appears for the same model.

Roster drift

The candidate set changes — a model is retired, or a new one would now win.

An advice layer says whether acting on a drift actually costs money — including the case where it doesn't and you should leave it alone.

Capacity

Four families, ranked side by side

The Proving Ground compares across all of them in one run, so the answer is not confined to whichever vendor you already have an account with.

Private Cloud

GPUs we own and power, plus certified partner capacity. Named, single-operator hardware — not a spot market.

Neocloud

API-first vendors: Anthropic, Google, OpenRouter and the rest, at vendor list price.

IaaS cloud

Rented instances — H100, H200, RTX PRO — provisioned per engagement and billed by the hour.

Hyperscaler

Azure OpenAI, AWS Bedrock, GCP Vertex. Arrives with bring-your-own-account, so you open only the account the winner needs.

Currently routable:Qwen 2.5 14BQwen 3.5 9BLlama 3.1 8BGemma2 2BLlama 3.1 70BClaude Haiku 4.5Claude Sonnet 5Gemini 3.6 FlashGemini 3.1 Profull catalog →

Measured, not estimated

The economics come with receipts

These are measurements taken on this platform's own hardware and rented capacity, with the certification and benchmark files behind them. They are not projections, and they are not a promise about your workload — that is what a bake-off is for.

Published platform measurements
What was measuredResultConditions
Owned GPU, all-in~$0.067 / GPU-hrincluding electricity
70B FP8 on rented H200, batched N=128$0.24 / M output19,955 tok/s prefill = $0.048/M input
Same model class owned, at electricity~$0.01 / M output
One QLoRA fine-tune (7B, 2k examples, rented H200)$0.52 · 4m15send to end
70B FP8 on RTX PRO 6000 ($1/hr)150 tok/s @ N=8certified un-waived · 49,152 ctx honest ceiling

Your keys, your accounts

Bring your own vendor keys

Members vault their own vendor keys — AES-256-GCM, verified before they are stored — and production traffic routes on their accounts at zero platform charge. You are paying us for the decision, not a margin on tokens.

Vaulted

AES-256-GCM

verified before stored

Platform charge on BYOK traffic

$0.00

you pay the vendor directly

Per-token markup on credits

None

vendor list price

Sample applications

See a profile working before you wire anything up

Chat, image generation, knowledge search, batch and fine-tuning all run against a profile in the portal — production surfaces that exist to demonstrate the decision, not to be the product.

Chat
Image
Knowledge
Batch
Fine-tune

Stop guessing which model to standardise on.

Bring three real items and the volume you run. You'll have a priced, graded ranking — and a profile you can put into production behind one line of JSON.