DeepSeek: DeepSeek V4.1 Flash 1017 Abliterated

deepseek/deepseek-v4.1-flash-1017-abliterated

DeepSeek V4.1 Flash 1017 Abliterated is a derivative of the October 17 DeepSeek checkpoint with weight-level refusal-direction removal. It is intended for authorized cybersecurity research, AI red teaming and agent testing. Its long text context supports reviewing code, technical evidence and multi-step task histories. The endpoint provides configurable reasoning for analysis and text generation through an OpenAI-compatible chat interface. Abliteration describes the published modification method, not a guarantee of zero refusals or preserved benchmark performance.

Model specifications

Input
text
Output
text
Context
1,048,576 tokens
Input price
$1 / 1M tokens
Output price
$3 / 1M tokens
Released
2026-10-24

Capabilities

  • Streaming
  • Function calling
  • Vision
  • JSON mode

Provider pricing, discounts and data privacy

Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.

Standard service tier

2 available providers · tier input average $1 / 1M tokens · tier output average $3 / 1M tokens

Refuseless

Tier: Standard · Quantization: fp8

Pricing
Input
$1 / 1M tokens
Output
$3 / 1M tokens
Cache read
$0.25 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Zero data retention
No
Used for training
No
Data collection
Moderated
No
GDPR compliant
No
HIPAA compliant
No
SOC 2 certified
No
BYOK supported
No

Silk Compute

Tier: Standard · Region: US · Quantization: fp4

Pricing
Input
$1 / 1M tokens
Output
$3 / 1M tokens
Cache read
$0.25 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
US
Zero data retention
No
Used for training
No
Data collection
Moderated
No
GDPR compliant
No
HIPAA compliant
No
SOC 2 certified
No
BYOK supported
No

Frequently asked questions

What is DeepSeek: DeepSeek V4.1 Flash 1017 Abliterated?
DeepSeek V4.1 Flash 1017 Abliterated is a derivative of the October 17 DeepSeek checkpoint with weight-level refusal-direction removal. It is intended for authorized cybersecurity research, AI red teaming and agent testing. Its long text context supports reviewing code, technical evidence and multi-step task histories. The endpoint provides configurable reasoning for analysis and text generation through an OpenAI-compatible chat interface. Abliteration describes the published modification method, not a guarantee of zero refusals or preserved benchmark performance.
How much does DeepSeek: DeepSeek V4.1 Flash 1017 Abliterated cost?
Input costs start at $1 / 1M tokens and output costs start at $3 / 1M tokens. Provider-level prices vary by service tier.
What is the context length of DeepSeek: DeepSeek V4.1 Flash 1017 Abliterated?
DeepSeek: DeepSeek V4.1 Flash 1017 Abliterated supports a 1,048,576 token context window.
What capabilities does DeepSeek: DeepSeek V4.1 Flash 1017 Abliterated support?
DeepSeek: DeepSeek V4.1 Flash 1017 Abliterated supports Streaming, Function calling, Vision, JSON mode.
Which providers offer DeepSeek: DeepSeek V4.1 Flash 1017 Abliterated?
DeepSeek: DeepSeek V4.1 Flash 1017 Abliterated is available from Refuseless, Silk Compute.
How do providers handle data privacy for DeepSeek: DeepSeek V4.1 Flash 1017 Abliterated?
2 of 2 providers report that customer data is not used for training, and 0 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.

Browse all AI models