DeepSeek V4.1 Flash 1017 Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash 1017, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.
by deepseek|Private|Nov 7, 2026|512K context|$0.173/M input tokens|$0.69/M output tokens
About Sable
Access 1 model served through Sable on AnonRouter's privacy-first gateway, including DeepSeek V4.1 Flash 1017 Uncensored. Each route lists its own pricing, capabilities, and privacy level.
On AnonRouter, the Sable route for DeepSeek V4.1 Flash 1017 Uncensored lists $0.173 per million input tokens and $0.69 per million output tokens at standard pay-as-you-go rates. See the catalog for model-specific prices.
Set your client’s base URL to https://api.anonrouter.ai/v1 and use an AnonRouter API key with compatibility mode enabled. In the chat completion body, send the model ID (for example, deepseek/deepseek-v4.1-flash-1017-uncensored) and {"provider":"sable"} to pin the request to Sable. See the provider routing guide for examples.
The current Sable catalog includes routes labelled Private. Open a model and check the Sable row for the privacy details of that specific route. The models and privacy labels guide explains what the labels mean.
