Step 1
Create your account
Sign up to manage credits, generate API keys, and access Policy Gateway controls.
Your AI.
Your rules.
Standard AI providers block legitimate work—like creative writing, security research, and medical analysis—with rigid, unpredictable filters. Abliteration.ai fixes this by offering a uncensored LLM API paired with a built-in Policy Gateway. Stop dealing with random refusals and start defining your own safety rules using policy-as-code, PII redaction, audit logging, and quota controls.
Live Console
Try the model in real time
Stream responses, attach images, and inspect the request body.
Model ID: abliterated-model
Ephemeral Session
Flagged categories
Block prompts that match selected categories.
Self-harm and sexual content involving minors are always blocked.
Free preview: 0/5.Usage-based pricing
Get started in minutes
Step 2
Generate an API key
Create a key in Integration to authenticate OpenAI-compatible /v1/chat/completions requests.
Step 3
Send your first request
Run the sample prompt or copy a snippet below. Free preview includes 5 requests.
Developer-controlled AI with enterprise governance
Policy Gateway
Your AI governance control plane. Define safety rules with policy-as-code, enforce rewrite/redact/escalate outcomes, manage quotas, and stream audit logs.
Uncensored LLM Models
Developer-controlled, less-restricted models without provider-side refusals. Pair with Policy Gateway to enforce your own business rules.
Audit & Compliance
Export every policy decision to Splunk, Datadog, Elastic, S3, and Azure Monitor with structured metadata for SOC 2 and compliance.
OpenAI-compatible
Drop-in replacement for OpenAI API. Change the base URL and keep your existing code. Works with all major SDKs.
Transparent Pricing
~$5 per 1M tokens with no hidden fees. Prepaid credits never expire. Simple, predictable billing for your AI workloads.
Instant Migration
Migrate from OpenAI, Azure, Anthropic, or any provider in minutes. Our migration tool patches your code automatically.
Policy Gateway: enterprise AI governance, your way
Replace provider refusals with your own rules
Policy Gateway is the control plane for your AI traffic. Define policy-as-code guardrails with rewrite, redact, escalate, or refuse outcomes. Manage per-project keys and quotas, test changes with shadow mode and canary rollouts, and export every decision to your SIEM.
Uncensored LLM models for roleplay and creative work
Developer-controlled, less-censored models for roleplay, creative writing, and specialized workloads — free from provider-side refusal filters. Pair with Policy Gateway to enforce your own boundaries.
Model ID:
abliterated-modelOpenAI-compatible API and instant migration
Full /v1/chat/completions parity with a drop-in base URL swap. Patch existing OpenAI code in minutes with the migration tool.
LLM audit logging and compliance exports
Export policy decisions to Splunk, Datadog, Elastic, S3, and Azure Monitor with structured metadata for audits and investigations.
Image understanding (vision) for screenshots and documents
Send images alongside text prompts to extract information, summarize content, and answer questions with the same API format.
Usage-based token pricing
Effective price: ~$5 per 1M tokens on total input + output usage. Subscription credits reset monthly; prepaid credits do not expire.
Zero data retention by default
Prompts and outputs are processed transiently and never used for training. Operational telemetry is retained for billing and reliability.
Rate limits and retries
Requests are rate-limited per API key. Handle 429 responses with backoff + retries, and upgrade for higher throughput.
Account Authentication and API Integration
Sign in or create account
Create an account to save credits and API keys. No phone verification required.
Used for sign up, receipts, and password resets.
Use at least 12 characters with upper/lowercase letters, a number, and a symbol.
Log in accepts email or this username.
If you were referred, paste the code from your link before signing up.
Already have an account?
or
Loading single sign-on…
API Integration & Code Examples
Generate keys for programmatic access.
curl https://api.abliteration.ai/v1/chat/completions \
-H "Authorization: Bearer $ABLIT_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "abliterated-model",
"messages": [{"role":"user","content":[
{"type":"text","text":"What’s in this image?"},
{"type":"image_url","image_url":{"url":"https://abliteration.ai/stonehenge.jpg"}}
]}],
"stream": true
}'
Browse API examples on GitHubSupport
Frequently Asked Questions
Quick answers about Policy Gateway governance, uncensored LLM models, billing, and integrations.
What is an uncensored LLM API?
An uncensored LLM API gives developers access to less-censored models without provider-side refusal filters. Uncensored models are available when needed, and you control prompts, outputs, and policy enforcement; content must still comply with your local laws and policies.
What is the Policy Gateway?
Policy Gateway is an enterprise AI governance layer for abliteration.ai. It applies policy-as-code rules, quotas, rollout controls, and audit logs across apps, models, and agents.
How does Policy Gateway enforce policy?
Send requests to /policy/chat/completions with your policy_id, policy_user, and optional project ID. The gateway enforces your rules and returns decision metadata for audits.
Do I need a separate subscription for Policy Gateway?
Yes. Policy Gateway is an enterprise add-on billed monthly. It layers on top of your base token bundles.
What data does Policy Gateway store?
It stores policy configuration and enforcement metadata (decision, reason code, policy ID, project/user tags) for audits. Prompt/output retention remains off by default.
Is abliteration.ai OpenAI-compatible?
Yes. We expose an OpenAI-compatible /v1/chat/completions endpoint with the same request/response shape, so most OpenAI clients work by changing the base URL and key.
Do you retain prompts or chat logs?
No. We do not retain prompts or outputs by default. Operational telemetry (token counts, timestamps, error codes) is retained for billing and reliability.
How does usage-based token pricing work?
You’re billed on total tokens processed (input + output). Image inputs are metered as token equivalents and count as input tokens. Effective pricing is ~$5 per 1M tokens; use monthly subscription credits or one-time prepaid credits (subscriptions reset monthly with no rollover).