The image and video rows below apply to
abliterated-model. abliterated-model-large and abliterated-model-large-v2 are text-only and reject image or video content with a 400 error on every surface.OpenAI — Chat Completions
POST /v1/chat/completions
OpenAI — Responses API
POST /v1/responses
On Responses, the base model accepts effort up to
xhigh (it rejects max); abliterated-model-large and abliterated-model-large-v2 accept up to max.
Anthropic — Messages API
POST /v1/messages
Anthropic — Count Tokens
POST /v1/messages/count_tokens
Count input tokens before sending a request. See count tokens.
Policy-governed endpoints
abliteration.ai exposes a parallel/policy/* surface that adds project quotas, policy evaluation, and streaming policy metadata. See policy endpoints.