DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic
DeepSeek · deepseek-v4-pro-qwen3-5-9b-uncensored-heretic
xtools-at's uncensored Heretic version of Jackrong's DeepSeek V4 Pro Qwen3.5 9B, a Qwen3.5 9B model distilled from DeepSeek V4 Pro on about 250,000 math and STEM samples. It answers directly without a thinking phase. It accepts and returns text, with a 32,768-token context window shared by input and output and up to 8,192 output tokens.
Specification
most-agreed values
Context
33K
Max output
8K
Released
2026-11-07
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.28
Output
$0.28
Cache read
$0.14
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nano-gpt · xtools-at | $0.28 | $0.28 | $0.14 | — | 33K | 8K | — |
More from DeepSeek
most-hosted first