Model
abliterated-model
Model specs and benchmark scores for abliterated-model.
Updated 2026-08-04
Model ID: abliterated-model. Use this exact value in the model field of your requests.
Benchmark scores and refusal rate for the model are listed below.
{
"model": "abliterated-model",
"messages": [
{ "role": "user", "content": "Summarize this report in one paragraph." }
],
"temperature": 0.2
}Pricing at a glance
Input is $1 per 1M tokens, cached input is $0.10 per 1M tokens, and output is $3 per 1M tokens.
Image inputs are metered as input-token equivalents. Only provider-reported cache reads receive the cached-input rate.
Monthly usage credit is added each billing cycle and does not expire. Prepaid credits are separate one-time purchases and also do not expire.
See the pricing page for current plans.
Model specs
Latest published benchmark scores and refusal rate for abliterated-model.
| Metric | Score |
|---|---|
mmlu_pro |
82.1 |
gpqa |
73.1 |
aime_2025 |
83.7 |
mmmu_pro |
68.1 |
refusals (mlabonne/harmful_behaviors) |
3/100 |