Use case · Government
Analysis that serves the public, not a vendor's policy.
Research, translate and analyze sensitive material with models that answer under your institution's rules.
Built forPublic institutions & policy researchers
Why refusals get in the way
Public institutions handle what commercial assistants are built to avoid: extremist propaganda, fraud schemes, crime reports and disinformation. Refusals and silently softened answers make that analysis slower and less reliable.
What teams use it for
- Analyze disinformation and extremist material for research and policy
- Summarize and translate reports, transcripts and open sources
- Draft briefings that state hard facts plainly
- Evaluate AI systems before procurement
What Lyber gives you
Answers, not refusals
Uncensored and abliterated weights, with no refusal layer of Lyber's own on top.
Your policy, in your system message
The scope and rules for each request travel with it, in the system message you write.
One OpenAI-compatible API
Keep your SDK, harness and agents. Change the base URL and the model name.
Keys, limits and records
A key per app or person with spending limits, shared organizations, and a usage ledger designed to exclude prompt text.
The request
POST /v1/chat/completions
{
"model": "lyber/auto",
"messages": [
{ "role": "system", "content": "<your mandate and handling rules>" },
{ "role": "user", "content": "<your request>" }
]
}Early access. Inference opens as each model is qualified, and launch prices are provisional.