New modelKimi K3.1 Pro Abliterated is now available. See the model

Skip to page controls
OATHBREAKER.

OATHBREAKER.

OPEN POSSIBILITIES.
ANOTHER DIRECTION.

Get
started.
YOUR ACCOUNT / YOUR FIRST API KEY
01 / INDEPENDENT / BY DESIGN

A different
starting point.

Oathbreaker AI is an OpenAI-compatible API for abliterated models: GLM-5.3, GLM-5.3 Flash, DeepSeek V4.1 Flash and Kimi K3.1 Pro. Streaming, tool calling, prepaid usage.

For developers building beyond the defaults.

Explore the model
MODEL APIINDEPENDENT INTELLIGENCE
OB // AGENT CONNECTIONS

Abliterated models for your agents

Oathbreaker AI is a prepaid API for abliterated open-weight models: open models modified to reduce trained refusals. One API key and one credit balance cover every model. Abliteration does not make a model more accurate, so give your agent work you can check, such as code with tests.

Use the base URL https://oathbreaker.ai/v1 in any OpenAI-compatible client. The same API also serves the Anthropic Messages and Responses formats, so it works with Claude Code, Codex, OpenCode and Hermes. Follow the Claude Code, Codex or OpenCode setup guide, or see every agent setup, including Hermes.

Streaming and tool calling are included. Add prepaid credit and pay per token, with no seats to buy. Compare prices per million tokens.

OATHBREAKERA DECLARATION OF INTENT / 001
BEFORE YOU ENTER

TAKETHEOATH.

Break the default.
Keep your word.

I take this oath to put my power
in service of humanity.

To build with purpose.
To question with courage.
To act with care.

I will not use it to exploit, deceive,
or cause needless harm.

I will respect the rights of others
and take responsibility for what I create.

The power is mine.
The responsibility is mine.