Lyber
Request access
DocsIntroduction

Get started

Markdown

Lyber API documentation

One OpenAI-compatible API for two uncensored checkpoints. Point the SDK you already use at Lyber, choose a model by its exact ID, and pay per token from prepaid credit.

At a glance

Base URLhttps://lyber-paid-acceptance-gateway-production.up.railway.app/v1
AuthenticationAuthorization: Bearer $LYBER_API_KEY
Modelsminimax-m3.1-flash-abliterated and deepseek-v4.1-flash-1017-abliterated
CompatibilityOpenAI Chat Completions, plus a stateless Responses adapter
BillingPrepaid credit, charged per input and output token

How Lyber works

Lyber serves abliterated checkpoints: open-weight models whose refusal behavior has been removed. Both sit behind one endpoint that speaks the OpenAI Chat Completions format, so the official OpenAI SDKs, and the frameworks built on them, work by changing the base URL and the key.

Every request names its model explicitly. Lyber never substitutes another model for your choice, and every response carries the ID of the model that answered, in the model field and the x-lyber-model header.

Endpoints

MethodPathPurpose
POST/v1/chat/completionsGenerate a reply, streamed or whole
POST/v1/responsesThe same models through the Responses format (preview)
POST/v1/workflows/security-reviewPrompt-based audit intake and separate review passes (preview)
GET/v1/modelsModels your key can use, with limits and prices
GET/v1/creditsYour prepaid balance, limits and request history