Abliterated Large Flash
abliterated-model-large-flash
Abliterated Large Flash is an uncensored reasoning model based on DeepSeek V4.1-Flash-1017. It accepts text and images and returns text, with tool calling, JSON mode, JSON Schema output, and automatic prompt caching. Its shared input/output context is 1,048,576 tokens, with up to 262,144 output tokens when space permits. Reasoning defaults to high and can be turned off or set to low, high, or max. Supports up to four images across the request history.
Specification
most-agreed values
Context
1M
Max output
262K
Released
2026-10-23
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$1.00
Output
$2.00
Cache read
$0.10
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| abliteration · abliteration | $1.00 | $2.00 | $0.10 | — | 1M | 262K | — |
| nano-gpt · abliteration-ai | $1.00 | $2.00 | $0.10 | — | 1M | 262K | — |
Other listings of this model
same model, different key