Learn

Plain explanations of the ideas behind Redline: what abliteration is, how a spend cap can actually hold, what zero prompt retention does and does not promise, and what makes an API OpenAI- or Anthropic-compatible.

AbliterationAbliteration removes the direction in a model’s activations that produces refusals, so it stops declining, without retraining the weights from scratch. Refusal directionA single direction in a model’s residual stream carries its tendency to refuse. Finding it is the basis of abliteration. Uncensored vs abliteratedUncensored usually means a loosely aligned finetune that still refuses sometimes. Abliterated means the refusal direction was removed. They are different claims. LLM gatewayAn LLM gateway is one API in front of many model providers, adding keys, billing, spend limits and logging without changing your code. Per-key spend capsA spend cap that is checked before the call, not after, so a runaway or leaked key stops at the number you set instead of billing past it. max_tokens clampingRedline lowers the outbound max_tokens to whatever the remaining budget covers, so a response cannot cost more than was reserved. Zero prompt retentionRedline stores the model, token counts and cost, never the prompt or completion, and returns a signed receipt so you can verify it. OpenAI-compatible APIAn OpenAI-compatible API accepts the same requests as OpenAI’s chat completions endpoint, so any OpenAI SDK works by changing the base URL. Anthropic-compatible APIAn Anthropic-compatible API accepts the Messages format, so Claude Code and the Anthropic SDKs work by changing the base URL. Signed receiptsRedline returns an HMAC-signed receipt of the prompt hash on every call, so you can prove later what the gateway bound to without it keeping the prompt. Red-teaming LLMsRed-teaming an LLM means attacking your own model on purpose: jailbreaks, prompt injection and abuse generation, to find failures before an attacker does.

Integration guides · Compare Redline · Models