Models
ReadyGPU TEENewbeta

Phala: DeepSeek V4.1 Flash 1017 Uncensored

Model IDphala/deepseek-v4.1-flash-1017-uncensored

Uncensored variant of DeepSeek V4.1 Flash 1017, built as a lightweight LoRA adapter served unmerged on the official FP8 weights. Refuses far less while keeping the base model's capabilities, tool calling, image input and 1M-token context. Served with SGLang in a TDX-attested enclave with NVIDIA confidential computing. Reasoning is on by default and can be turned off or capped per request.

input

$0.75/M

output

$1.60/M

cache read

$0.15/M

context

1.0M

added

Nov 18, 2026

Supported API shape

input

text · image

output

text

max output tokens

262,144

tools

Supported

json mode

Supported

Verification

Available evidence. Use a verified client to authenticate the quote, connection, and receipt.

Verify private inference

receipt

signed receipt + hashes

attestation

gateway report

session

attested upstream

serving provider

read from receipt session

Provider

Phala

GPU TEE

input

$0.75/M

output

$1.60/M

cache read

$0.15/M

context

1.0M

Performance comparison

Last 72h · UTC