DeepSeek V4.1 Flash 1017 Abliterated API

DeepSeek V4.1 Flash 1017 Abliterated is a large language model by DeepSeek, available on the Venice API as e2ee-deepseek-v4-1-flash-1017-abliterated. It is end-to-end encrypted.DeepSeek V4.1 Flash 1017 Abliterated running in a Trusted Execution Environment (TEE). A text-only reasoning and coding model with refusal behavior removed and a 1M-token context window. Hardware attestation evidence is available for independent verification of enclave identity and configuration.

DeepSeek V4.1 Flash 1017 Abliterated API pricing

Model ID	Variant	Privacy	Price
`e2ee-deepseek-v4-1-flash-1017-abliterated`	E2EE	E2EE	$0.375 / $1.50 per 1M

DeepSeek V4.1 Flash 1017 Abliterated specifications

Spec	Value
Provider	DeepSeek
Released	Nov 5, 2026
Privacy	E2EE
Status	Stable
Open weights	Yes
Context window	1M tokens
Max output	128K tokens
Reasoning effort	Not adjustable
Served precision	FP8

How to use the DeepSeek V4.1 Flash 1017 Abliterated API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "e2ee-deepseek-v4-1-flash-1017-abliterated" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "e2ee-deepseek-v4-1-flash-1017-abliterated",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
  }'

Related models

MiniMax M2.7 API: $0.375 / $1.50 per 1M
MiMo-V2.5 API: $0.40 / $2.00 per 1M
Qwen 3 Coder 480B Turbo API: $0.35 / $1.50 per 1M
MiniMax M3 Preview API: $0.30 / $1.20 per 1M

Explore

By modality