Skip to content
New

DeepSeek V4.1 Flash free for 7 days: 10M tokens a day after any top-up. Until Nov 30.

How it works

NotHoly Wisp Flash

A reasoning model at a low price per token.

NotHoly Wisp Flash runs DeepSeek V4.1 Flash with refusal behavior reduced by abliteration.

Price per 1M tokens

Launch promotionUntil Nov 30, 2026
Input
$0.20$0
Output
$0.80$0

Cached input$0.05$0

Free: 10M tokens a day for 7 days after any top-up, until Nov 30, 2026.

$0 for the first 10M tokens of each day while your free days run. Up to 2M of them can be output.

Specifications

Model ID
notholy-wisp
Base model
DeepSeek V4.1 Flash
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

High-volume triage and quick questions.

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

The same call works with any OpenAI client. Change only the base URL and the key.
curl https://api.notholy.com/v1/chat/completions \  -H "Authorization: Bearer $NOTHOLY_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "notholy-wisp",    "messages": [      { "role": "user", "content": "Explain CVE-2024-3094 in two sentences." }    ]  }'

NotHoly Wisp Flash: Launch promotion

Free usage
Top up any amount and use NotHoly Wisp Flash free for 7 days, up to 10M tokens a day. The top-up has to be made by Nov 30, 2026. The 7 days count from that payment, so they can run past that date. Up to 2M of the daily tokens can be output, and cached input counts as input. Unused tokens don't carry over: the count resets at 00:00 UTC. You need a verified email.
More days
Each new qualifying top-up starts 7 new days from that payment. A refund that brings a top-up below $10, or a chargeback, ends the days it started.
Limits
While a request uses free usage or promo credit, the limits are 20 requests per minute and 2 at a time. If the promotion's daily budget runs out, free usage pauses for everyone until 00:00 UTC. Promo credit and paid balance keep working.
What pays first
Each request is paid by free usage first, then promo credit, then your balance. Usage is always priced at the list price.

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. 1/3

    Create the account

    Individual or company. You can switch to a company later without losing balance or keys.

    IndividualCompany
  2. 2/3

    Add credits

    By card, from $10. Pay per token, no subscription.

    $10.00minimum deposit
  3. 3/3

    Ask

    In the chat, or install the CLI and run notholy login in your terminal.

    $ notholy login