Skip to content
Updates & support on Telegram

DeepSeek V4.1 Flash 1017 Abliterated

Abliterated

Use DeepSeek V4.1 Flash 1017 Abliterated through the UncensoredAI OpenAI-compatible API with a single key and per-token billing. Point any compatible SDK at the endpoint, set the model to the id below, and stream or batch as you like. deepseek-v4.1-flash-1017-abliterated

Specifications

Model ID
deepseek-v4.1-flash-1017-abliterated
Provider
DeepSeek
Context window
1M
Max output
66K
Input / 1M
$0.30
Cached / 1M
$0.16
Output / 1M
$0.30

Example request

curl https://uncensoredai.dev/v1/chat/completions \
  -H "Authorization: Bearer sk-***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash-1017-abliterated",
    "messages": [{ "role": "user", "content": "Hello" }],
    "stream": true
  }'

DeepSeek V4.1 Flash 1017 Abliterated vs the rest of the DeepSeek family

Same request body, same endpoint — pick by price and context. Sorted cheapest input first.

ModelInput /1MOutput /1MContext
DeepSeek V4.1 Flash$0.04$0.041M
DeepSeek V4.1 Flash 1017$0.04$0.041M
DeepSeek V4 Flash$0.06$0.061M
DeepSeek V4.1 Flash 1017 Abliterated ←$0.30$0.301M
DeepSeek V4.1 Flash Abliterated$0.30$0.301M
DeepSeek V4 Pro$0.50$0.501M
DeepSeek V4 Pro Uncensored$0.50$0.501M
DeepSeek V4.1 Flash Abliterated Fast$1.00$1.001M
DeepSeek V4.1 Flash 1017 Abliterated API — $0.30/1M In, $0.30/1M Out, 1M Context · UncensoredAI