Abliteration / abliteration/abliterated-model-large-v2

Abliterated Large v2 - access through LLMTR

Abliterated Large v2 is a text model with reduced refusal behaviour and a 1,000,000-token context window. It supports tool/function calling and JSON output. It reasons on every request and those tokens bill as output; reasoning cannot be turned off, the `low`, `high` and `max` levels can be chosen, and `low` is used when no level is sent. Repeated prompt prefixes can be served from a cache, and those tokens bill at a tenth of the input rate. Requests involving child sexual exploitation or help with self-harm are still blocked.

Technical specifications

Canonical IDabliteration/abliterated-model-large-v2
ProviderAbliteration
Context window1,000,000 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$3.00
CHAT_COMPLETIONSCACHE_READPER_1M_TOKENS$0.300000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$5.00

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions   -H "Authorization: Bearer llmtr-your_key"   -H "Content-Type: application/json"   -d '{"model":"abliteration/abliterated-model-large-v2","messages":[{"role":"user","content":"Hello"}]}'

Related models