# DeepSeek V4.1 Flash 1017 Abliterated

## Best for

Uncensored coding and reasoning with a long context

## When not to use

Workloads that rely on the model refusing unsafe requests; keep your own guardrails in front of it.

## Overview

DeepSeek V4.1 Flash 1017 Abliterated is DeepSeek V4.1 Flash 1017 with its refusal behaviour removed by abliteration, designed to answer requests the original model declines. It keeps the base model's coding, reasoning, and tool use, with a 1,048,576-token context window.

| | |
| --- | --- |
| API identifier | `boundless/deepseek-v4.1-flash-1017-abliterated` |
| Developer | DeepSeek |
| Context window | 1,048,576 tokens |
| Supports | text, reasoning, tool-use, abliterated |
| Status | Serving — access by application |

## Rates

USD per 1M tokens, on-demand tier.

| Input | Cached input | Output |
| --- | --- | --- |
| $0.24 | $0.01 | $0.96 |

## Call it

Access by application only: a key can call it once the Team is approved. [Apply for access](https://boundless.network/defensive-access#apply); until then the gateway answers 403 `model_access_required`.

Put `boundless/deepseek-v4.1-flash-1017-abliterated` in the `model` field. The same request works against the Anthropic Messages API — see [API Compatibility](https://inference.boundless.network/docs/api-compatibility).

```bash
curl https://api.inference.boundless.network/v1/chat/completions \
  -H "Authorization: Bearer $BOUNDLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "boundless/deepseek-v4.1-flash-1017-abliterated",
    "messages": [{
      "content": "Say hello",
      "role": "user"
    }]
  }'
```

Every model we serve is listed at [Models](https://inference.boundless.network/models); the rate card in full is on [Pricing](https://inference.boundless.network/docs/pricing).
