NotHoly Vector Flash 1017
Built on a coding-focused base model.
NotHoly Vector Flash 1017 runs DeepSeek V4.1 Flash 1017 Abliterated with refusal behavior reduced by abliteration.
Price per 1M tokens
- Input
- $0.27
- Output
- $0.97
Cached input$0.068
Billed per token from your prepaid balance, at the price in effect when the request runs.
Specifications
- Model ID
notholy-vector- Base model
- DeepSeek V4.1 Flash 1017 Abliterated
- Context
- 1,048,576 tokens
- Max output
- 131,072 tokens
- Input types
- Text, Images
- Tool calling
- Yes
- Reasoning effort
- off, low (default), high, max
Use it for
Coding agents and terminal work.
What it doesn't do
- A request fits in 1,048,576 tokens of context, and one answer stops at 131,072 tokens.
- Abliteration lowers refusals. It doesn't add knowledge the base model lacks, and answers can be wrong, so check findings before you report or act on them.
Example request
curl https://api.notholy.com/v1/chat/completions \ -H "Authorization: Bearer $NOTHOLY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "notholy-vector", "messages": [ { "role": "user", "content": "Explain CVE-2024-3094 in two sentences." } ] }'Questions
Is the base model shown on purpose?
Yes. People who buy for security work ask what is running, so each model page names its base model.
Do benchmarks of the base model apply?
They describe the original model. NotHoly does not publish benchmarks of its own.
Ask anything your scope allows.
Create an account, add credits from $10 and ask the first question in the chat or the terminal.
- 1/3
Create the account
Individual or company. You can switch to a company later without losing balance or keys.
IndividualCompany - 2/3
Add credits
By card, from $10. Pay per token, no subscription.
$10.00minimum deposit - 3/3
Ask
In the chat, or install the CLI and run notholy login in your terminal.
$ notholy login