Last refreshed 2026-11-19. Next refresh: weekly.
Why use DeepSeek V4.1 Flash 1017 Uncensored on Phala?
Phala offers DeepSeek V4.1 Flash 1017 Uncensored with pay-as-you-go pricing at $0.30/1M input tokens. Phala Network is a decentralized compute network for confidential AI inference, enabling privacy-preserving model execution.
Input / 1M
$0.30
Output / 1M
$1.20
Cache
read $0.006
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: phala/deepseek-v4.1-flash-1017-uncensoredModel ID
phala/deepseek-v4.1-flash-1017-uncensoredRequest example
Curated snippets for this provider are not sourced yet. Use Phala documentation with model ID
phala/deepseek-v4.1-flash-1017-uncensored.Gotchas
- Use provider model ID "phala/deepseek-v4.1-flash-1017-uncensored", not the LLMReference slug "deepseek-v4.1-flash-1017-uncensored".
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.30 |
| Output tokens | $1.20 |
Capabilities
VisionMultimodalReasoningJSON / Tool use
About DeepSeek V4.1 Flash 1017 Uncensored
DeepSeek V4.1 Flash 1017 Uncensored is Phala’s named hosted variant of DeepSeek V4.1 Flash 1017. Phala serves its MIT-licensed refusal-reducing LoRA unmerged on the official FP8 base weights in a confidential-computing enclave. The API supports reasoning, tools and image input.
Model Specs
Released2026-11-18
Context1M