Uncensored open weights · cost-plus pricing · no logs

Uncensored weights.
Honest prices.

Curated uncensored builds of the best open models, behind one API key. Prepaid credits and per-token billing: no subscriptions, no expiry, no logs.

12
Models on the sheet
$0.06
From / 1M in
0
Classifiers in the path
0
Prompts stored
01

Why it’s this cheap

/ 01

MoE math

2026 models are mixture-of-experts: huge total parameters, tiny active parameters. A 320B model that only activates 18B per token serves at small-model speed on commodity GPUs. We pass that arithmetic straight to you.

/ 02

Cost-plus, in writing

Every price obeys one rule and it’s printed right here. If a build can’t meet it on the GPU it needs, it doesn’t go on the sheet.

price ≥ 2.5 × our cost @ 30% utilization
/ 03

No idle-GPU tax

We launch models on scale-to-zero serverless GPUs and only rent dedicated hardware when a model stays >40% busy for 30 days. You never pay for a card sitting idle, because we don’t either.

02

Curated, benchmarked, no refusals.

Every build here has no refusals: curated, benchmarked against its base, publisher named, priced on the tin.

Two build methods, both labelled: abliterations (huihui-ai, OrcaRouter, our own Heretic runs) and refusal-free fine-tunes (Dolphin, Hermes). We measure refusal rate and capability retention against the base model before listing, and publish the numbers. Nothing sits between your prompt and the model: no policy gateway, no classifier.

See the benchmarks →
qwen3.8-27b$0.24 / $0.72
dolphin-3.0$0.15 / $0.45
hermes-4$0.25 / $0.70
gpt-oss-120b$0.30 / $0.72
per 1M tokens, in / out
03

Privacy-first

We can’t leak what we never stored.

Requests are processed in memory and discarded. We keep four things: your account email, your credit ledger, the token counts of each request, and hashed keys. Content: zero. Not a policy promise — the schema has nowhere to put it.

Read the policy →
prompts stored0
completions stored0
content in logs0
token counts (billing)kept
04

Plugs into your agent

Qwen Code, Claude Code, OpenCode, Aider, Cline: if it can change a base URL, it works: streaming, tool calling and JSON mode included, on models that don’t refuse.

OPENAI_BASE_URL="https://api.cheapweights.ai/v1"
Docs & configs →

Stop renting a subscription. Buy tokens.