DeepSeek V4.1 Flash Abliterated Fast, per token on one key.
DeepSeek V4.1 Flash Abliterated Fast is DeepSeek V4.1 Flash with its refusal direction removed from the weights. It costs $1.75 per million input tokens and $3.50 per million output tokens, prepaid, with a 1,000,000-token context window. Call it at https://api.pentestllm.ai/v1/chat/completions with model "deepseek-v4.1-flash-abliterated-fast" and a PentestLLM key, from any OpenAI SDK or agent that takes a base URL. It is for authorized security testing only.
Price per million tokens
- Input
- $1.75
- Cached input
- $0.40
- Output
- $3.50
- Daily check
- Steady since Oct 25
- As of
- 2026-11-11
First request
curl https://api.pentestllm.ai/v1/chat/completions \
-H "Authorization: Bearer sk-ptl-live-…" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-v4.1-flash-abliterated-fast", "messages": [{"role": "user", "content": "Hello"}]}'Get a key
- Create a key in the console. Credit is prepaid from $10, with no subscription.
- Set OPENAI_BASE_URL to https://api.pentestllm.ai/v1 and send your sk-ptl- key as the bearer token.
- Send deepseek-v4.1-flash-abliterated-fast as the model. The same key calls every model on PentestLLM.
DeepSeek V4.1 Flash Abliterated Fast settings for a coding agent
- Provider
- OpenAI-compatible
- Base URL
- https://api.pentestllm.ai/v1
- Model
- deepseek-v4.1-flash-abliterated-fast
- Context window
- 1,000,000 tokens
- Max output
- 65,536 tokens
- Tool calling
- not listed in the catalog
- Key prefix
- sk-ptl-
DeepSeek V4.1 Flash Abliterated Fast specs
- Kind
- Abliterated
- Developer
- DeepSeek
- Base model
- DeepSeek V4.1 Flash
- Context window
- 1,000,000 tokens
- Max output
- 65,536 tokens
- Input
- text and image
- Wire formats
- openai
- Endpoints
- /v1/chat/completions, /v1/messages, /v1/completions, /v1/responses, /v1beta/models/{model}:generateContent
What DeepSeek V4.1 Flash Abliterated Fast is for
DeepSeek V4.1 Flash Abliterated Fast is an abliterated build: the refusal direction was removed from the weights, so it is built to decline fewer security questions than the stock model, with no system prompt to maintain. Refusals are reduced, not gone. Testers use it for triaging scanner output, explaining a CVE, reviewing code for vulnerabilities, drafting report findings, writing detection rules and solving CTF challenges.
Use it only on systems you own or have written permission to test. The acceptable use policy lists what is not allowed and applies to every request.
Every request is settled to the token at the prices above. The daily real-model check sends a fixed prompt to every model and records whether the answer still matches; this model’s verdict today is “Steady since Oct 25”. Call it from the OpenAI SDK or a coding agent, or send auto/security and let the router pick a security build per request. Keys and top-ups live in the console.
What DeepSeek V4.1 Flash Abliterated Fast costs, worked
An agent turn of 8,000 input and 1,000 output tokens at $1.75 input and $3.50 output per million tokens is $0.0175; 100 turns are $1.75 and 1,000 turns are $17.50. An agent resends its context on every turn, so the input side is most of the bill. All from prepaid credit, no subscription.
- Input, 8,000 tokens at $1.75 per million
- $0.014
- Output, 1,000 tokens at $3.50 per million
- $0.0035
- One turn
- $0.0175
- 1,000 turns
- $17.50
| Abliterated builds | Context | In / out per 1M | 1,000 agent turns |
|---|---|---|---|
| GLM-5.3 Flash Abliterated | n/a | $0.4656 / $1.94 | $5.6648 |
| Apex Flash 1 Abliterated | 262K | $0.68 / $2.32 | $7.76 |
| DeepSeek V4.1 Flash Abliterated | n/a | $0.8488 / $1.6975 | $8.4875 |
| DeepSeek V4.1 Flash 1017 Abliterated | 1000K | $0.75 / $3.125 | $9.125 |
| GLM-5.3 Flash Apex Abliterated | 1049K | $0.80 / $3.20 | $9.60 |
| Gemma 4 31B Cognitive Unshackled | 262K | $1.071 / $1.071 | $9.639 |
| Qwen3.5 27B Blossom V6.4 Derestricted | 262K | $1.071 / $1.071 | $9.639 |
| Qwen3.5 27B BlueStar v3 Derestricted | 262K | $1.071 / $1.071 | $9.639 |
| Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted | 262K | $1.071 / $1.071 | $9.639 |
| Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite | 262K | $1.071 / $1.071 | $9.639 |
| Qwen3.5 27B Queen Derestricted | 262K | $1.071 / $1.071 | $9.639 |
| DeepSeek V4.1 Flash Abliterated Fast | 1000K | $1.75 / $3.50 | $17.50 |
Also try
DeepSeek V4.1 Flash Abliterated Fast questions
DeepSeek V4.1 Flash Abliterated Fast is DeepSeek V4.1 Flash with its refusal direction removed from the weights, from DeepSeek, with a 1,000,000-token context window. On PentestLLM it answers as deepseek-v4.1-flash-abliterated-fast.
The refusal direction was removed from the model's weights, so DeepSeek V4.1 Flash Abliterated Fast is built to decline fewer requests than the stock model, with no system prompt doing the work. Refusals are reduced, not gone, and the acceptable use policy still applies to every request. See the acceptable use policy.
No. Credit is prepaid from $10 and billed per token: input $1.75 and output $3.50 per million tokens, cached input $0.40.
About $0.0175 for 8,000 tokens in and 1,000 tokens out, at $1.75 in and $3.50 out per million tokens. A thousand such turns are $17.50.
Yes. Send deepseek-v4.1-flash-abliterated-fast as the model through the OpenAI SDK, or any agent that takes a custom OpenAI base URL, with base URL https://api.pentestllm.ai/v1. It also answers the Anthropic Messages API at the same host, so agents built on the Anthropic SDK can call it. See the docs.
Yes. The daily real-model check sends every model the same fixed prompt and records whether the answer still matches. DeepSeek V4.1 Flash Abliterated Fast’s latest result, from Nov 11: steady since Oct 25. See the daily check.