Abliterated model router · Early access
AI should serve the user, not the companies.
MiniMax M3.1 Flash and DeepSeek V4.1 Flash 1017. Two uncensored checkpoints, one OpenAI-compatible API.
New at Lyber
Chat with MiniMax M3.1 Flash or DeepSeek V4.1 Flash 1017, or connect either to your own app. Join the waitlist; once approved, use both from the same Lyber account.
Uncensored · NVFP4
Lyber’s uncensored derivative of MiniMax M3.1 Flash. Choose this exact checkpoint for chat and API requests; Hugging Face weight access is separate.
Live availability is checked after sign-in
lyber-ai/MiniMax-M3.1-Flash-UNCENSORED-NVFP4
Uncensored · FP8
dealign.ai’s uncensored 1017 checkpoint. Select it explicitly, with its own serving identity and limits shown in the app.
Live availability is checked after sign-in
dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8
Approval opens the app. Each request uses your account’s credit and spending limits; availability can change. Tools and context limits follow the connected Router’s model catalog.
Right now, we are creating a level of intelligence that has never been seen before, and yet we are falling short at making it humanity-centric.
An agent that serves you does what you asked, not a softened, rewritten version of it. You judge the answer, not a filter.
Your request
“Answer what I asked.”
model: deepseek-v4.1-flash-1017-abliterated
The response names its model"model": "deepseek-v4.1-flash-1017-abliterated"
Illustration. Your explicit model ID selects the checkpoint; live availability is checked before each request.
Hack the planet. Liberate the planet. Lyber.
The point
What we build
Censorship-free models behind one OpenAI-compatible endpoint. Point the SDK you already use at it and keep your code.
Connect a clientChoose MiniMax M3.1 Flash or DeepSeek V4.1 Flash 1017 by its exact model ID. Every answer names its model.
See the modelsRequests run on one API key and prepaid dollar credit, topped up with a card or crypto. A website login never stands in for the key.
Get API accessMonthly plans
Monthly credit. One balance for your browser and agents.
Browser · Codex · Hermes · API
Launch preview · not on sale
No charge to request access. Model use needs approval, available credit and live readiness.
$15/ month
$20 monthly usage credit
$45/ month
$60 monthly usage credit
$180/ month
$250 monthly usage credit
Custom
Usage and capacity by agreement
Every plan includes: Available models · Browser chat & API · Supported Codex & Hermes workflows · Key backups · Usage history · Team workspaces · Spending controls
Same model token rates on every plan. USD before tax. Client support depends on the qualified model and integration.
One-time credit from $10. Pay by card, with no subscription. Purchased credit stays separate from expiring plan credit.
Starter: $15 for $20 credit. Pro: $45 for $60. Max: $180 for $250. Spending that included credit is not an additional charge; requests use the selected model’s token rates. Extra prepaid credit is purchased separately.
Choose to add prepaid credit or wait for renewal. The plan design does not authorize automatic overage charges. Automatic top-ups would require your explicit opt-in and a spending cap.
Across your Lyber account: browser, API and supported Codex or Hermes workflows. Compatibility depends on the client and qualified model. A higher plan adds credit and banking, not model access, context or features.
In this proposal, unused Starter credit does not roll over. Pro credit stays usable through the following billing cycle, capped at $120; Max credit lasts through two following cycles, capped at $750. Oldest plan credit is spent first. Separately purchased prepaid credit does not become expiring plan credit. Renewal, cancellation, expiry and refunds must be implemented and final terms published before these benefits are sold.
Credit buys metered tokens, not unlimited inference. Fresh input, recognized cache reads and output have separate rates; billable reasoning counts as output once. Plans do not reserve hardware or promise rate limits, queue priority or support response times. Final limits and terms will be published before subscriptions open.
No. These are proposed prices and benefits. Requesting access creates no charge or subscription and does not enable inference. Final terms, including renewal, cancellation and refunds, will be published before sale.
$5 signup credit now · paid bonuses coming
$5
Reserved after verified waitlist signup. No card or API key needed.
+$10
Planned bonus brings their total to $15, separate from monthly credit.
$15
Share your personal link. Earn credit after their first qualifying paid Pro or Max payment.
Reserve signup credit now. Paid subscription and $15 referral rewards are not active yet; signup alone earns no paid bonus. Approved model access still requires live availability and account credit.
Signup credit is limited to the existing funded campaign’s first 1,000 eligible accounts. Confirmed email is required; one signup reward per person. Existing $10 grants are preserved. The friend’s $15 is $5 + $10, not another $15 on top. Self-referrals, duplicate accounts, trials, failed payments and renewals would not qualify. Paid bonuses are coming with subscriptions; final eligibility, refund and campaign terms will be available before purchase. Promotional credit has no cash value and does not reserve compute.
Get started
Connect your own Hermes agent, use a coding client, or point your SDK at Lyber. Your key stays in your environment.
Hermes: add Lyber to your existing agent or create a separate Lyber-optimized profile. Codex: use Lyber in the desktop app or CLI. SDK and HTTP: any client that accepts an OpenAI-compatible base URL. Prompt: the agent wires Lyber into your project; its own model stays the same.
Request access with a verified email. Once approved, create a key in your dashboard and set it as LYBER_API_KEY.
Request access →export LYBER_API_KEY=lyber_prepaid_…Set up Lyber in this project.
Lyber is an OpenAI-compatible API for uncensored, abliterated models.
- Base URL: https://lyber-paid-acceptance-gateway-production.up.railway.app/v1
- API key: read it from the LYBER_API_KEY environment variable. Never write the key into code, config files, logs or git.
- Model: minimax-m3.1-flash-abliterated or deepseek-v4.1-flash-1017-abliterated. Select one explicitly; check readiness using GET {base URL}/models.
Do this:
1. Find where this project calls an LLM, or add a small client if it has none. Use the official OpenAI SDK for the project's language with its base URL set to the Lyber base URL.
2. Add LYBER_BASE_URL and LYBER_API_KEY to .env.example without values, and load them the way this project loads its other settings.
3. Only when the user asks to send a paid request, use the explicitly selected model ID and print the response model.
4. Tell me what you changed. Don't commit, and don't print the key.It edits your project and runs one test request. Review the changes before you commit.
Works in Claude Code Codex Cursor+ any coding agent
Illustrative output. Inference opens after each model is qualified.
Models & pricing
MiniMax M3.1 Flash NVFP4 and DeepSeek V4.1 Flash 1017 FP8. Choose either by its exact model ID.
Published rate snapshot · USD per 1M tokens · input / output
explicit checkpoint
minimax-m3.1-flash-abliterated$0.20 / $0.80
Cached input: $0.20 per 1M tokens
explicit checkpoint
deepseek-v4.1-flash-1017-abliterated$0.20 / $0.80
Cached input: $0.20 per 1M tokens
These are the two offered checkpoints. Availability can change; the Router’s current published price version governs billing.
Use cases
Lyber answers, and you stay responsible for how it is used.
AI safety & platform teams
Read more: AI red teamingPOST /v1/chat/completions
{
"model": "minimax-m3.1-flash-abliterated",
"messages": [
{ "role": "system",
"content": "<your policy>" },
{ "role": "user",
"content": "<your brief>" }
]
}Your policy, not oursLyber adds no refusals of its own.
Early access
Join the access list with a verified email. We review each request before keys and models open, and invites move you up the queue.