DeepSeek V4.1 Flash Abliterated
DeepSeek V4.1 Flash Abliterated is DeepSeek V4.1 Flash with refusal behavior removed by abliteration.ai (abliteration.ai lists it as Abliterated Large Flash). It takes text and image input, supports tool calling, structured outputs and configurable reasoning that can be turned off, and has a context window of about 1M tokens.
Modalities
In / out price
$1.00 / $2.00per 1M
Cached price
$0.10per 1M
Context
1M
Max output
131K
Providers
1 routeCompare providers by price, privacy, and speed.
abliteration.ai | Private | $1.00 | $2.00 | $0.10 | 1M | 131K | — | — |
Privacy
2 / 4Private routing
Private tier
- Anonymous
- Private
- TEE
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more
Features
6Streaming
Tool calling
Vision
Reasoning
JSON/schema
Prompt caching
Uptime
FAQ
Common questions about DeepSeek V4.1 Flash Abliterated.