# Abliteration

Abliteration serves 3 text models on LLM API.

Model ID prefix: `abliteration/` · 3 models
Updated: 2026-11-03
Canonical: https://llmapi.ai/providers/abliteration/

## Models and prices

Prices when Abliteration serves the request.

### Text (3)

Prices per 1M tokens.

| Model | Model ID | Input | Output | Cache read | Context |
| --- | --- | --- | --- | --- | --- |
| [Abliterated Large Flash](https://llmapi.ai/models/abliterated-model-large-flash/) | `abliteration/abliterated-model-large-flash` | $1 | $2 | $0.1 | 1.05M |
| [Abliterated Large v2](https://llmapi.ai/models/abliterated-model-large-v2/) | `abliteration/abliterated-model-large-v2` | $3 | $5 | $0.3 | 1M |
| [Abliterated Model](https://llmapi.ai/models/abliterated-model/) | `abliteration/abliterated-model` | $1 | $3 | $0.1 | 262K |

**Volume pricing.** At higher monthly volume, models on Abliteration may cost less. Book a call and sales will quote a price for your usage. [Book a call with sales](https://meetings.hubspot.com/julia-andriienko/llmapi) or [Create an account first](https://app.llmapi.ai/signup).

## Send requests to Abliteration

Put `abliteration/` before a model ID and the request goes to Abliteration. If Abliteration’s uptime over the last 5 minutes is below 90%, it goes to another provider of the model, unless it sends `X-No-Fallback: true`. [Routing docs](https://docs.llmapi.ai/features/routing)

Example: Abliterated Large Flash, Chat Completions (`POST /v1/chat/completions`). Set LLMAPI_KEY to your LLM API key.

```python
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

response = client.chat.completions.create(
    model="abliteration/abliterated-model-large-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
```

Prices synced 2026-11-03.

Next step: [Get API key](https://app.llmapi.ai/signup)