> ## Documentation Index
> Fetch the complete documentation index at: https://docs.venice.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> The Venice API is OpenAI-compatible: use any OpenAI SDK with the base URL `https://api.venice.ai/api/v1` and a Venice API key, or pay per request from a USDC wallet through x402 with no account.
> Read model IDs from `GET /models` or `GET /models/traits` at runtime instead of hardcoding them from memory or from these pages. Models are added and retired often.
> Every model's price is in https://docs.venice.ai/pricing.md. Quote video and audio jobs with `POST /video/quote` or `POST /audio/quote` before you queue them.
> Search these docs from an MCP client at https://docs.venice.ai/mcp. The full agent guide is https://docs.venice.ai/agents.md.

# Abliterated Large V2 API

> Abliterated Large V2 API on Venice: 1M context, $3.00 input and $5.00 output per 1M tokens. Anonymized access without your identity.



## Abliterated Large V2 API

Abliterated Large V2 is a large language model by Abliteration AI, available on the Venice API as `abliteration-abliterated-model-large-v2`. The provider of this model may retain prompt data (though it is anonymized by Venice). For sensitive content, use a private model.

Abliterated Large V2 is Abliteration AI's unrestricted reasoning model, based on GLM-5.3 and further abliterated and fine-tuned. Text-only with 1M context, for harder reasoning and evaluation workloads. Always reasons; depth can be set to low, high, or max.

### Abliterated Large V2 API pricing

| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `abliteration-abliterated-model-large-v2` | Standard | Anonymized | $3.00 / $5.00 per 1M |

### Abliterated Large V2 specifications

| Spec | Value |
| - | - |
| Provider | Abliteration AI |
| Released | Oct 1, 2026 |
| Privacy | Anonymized |
| Status | Stable |
| Context window | 1M tokens |
| Max output | 32K tokens |
| Reasoning effort | Not adjustable |
| [GPQA Diamond](https://docs.venice.ai/models/methodology.md#benchmarks) | 43.4% ±6.9 (95% interval), run by Venice through the API at its default reasoning on Oct 21, 2026 |

### How to use the Abliterated Large V2 API

Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "abliteration-abliterated-model-large-v2"` and your API key.

```bash theme={"system"}
curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "abliteration-abliterated-model-large-v2",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
  }'
```

### Related models

* [Grok 4.7 API](https://docs.venice.ai/models/grok-4-7.md): $2.27 / $6.80 per 1M
* [Grok 4.6 API](https://docs.venice.ai/models/grok-4-6.md): $2.27 / $6.80 per 1M
* [Gemini 4 Hydrogen API](https://docs.venice.ai/models/gemini-4-hydrogen.md): $1.88 / $9.38 per 1M
* [GPT-6.1 Sol API](https://docs.venice.ai/models/gpt-6-1-sol.md): $2.00 / $10.00 per 1M


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.