Primeiros passos

NotHoly Vector Flash 1017

NotHoly Vector Flash 1017 na API da NotHoly, chamado como notholy-vector. Modelo base: DeepSeek V4.1 Flash 1017 Abliterated.

Especificações

ID do modelo	`notholy-vector`
Modelo base	DeepSeek V4.1 Flash 1017 Abliterated
Contexto	1,048,576
Saída máxima	131,072
Entrada	Texto, Imagens
Chamada de ferramentas	Sim
Raciocínio	Sim
Níveis de raciocínio	`off`, `low`, `high`, `max`

Preços

Entrada	$0.27
Saída	$0.97
Entrada em cache	$0.068

USD por 1M de tokens. Os preços vêm da versão de preço em vigor, os mesmos valores que GET /v1/models retorna.

Exemplos de requisição

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 IDOR in two sentences."}]
  }'

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.notholy.com/v1", api_key=os.environ["NOTHOLY_API_KEY"])

r = client.chat.completions.create(
    model="notholy-vector",
    messages=[{"role": "user", "content": "Explain IDOR in two sentences."}],
)
print(r.choices[0].message.content)

curl https://api.notholy.com/v1/messages \
  -H "x-api-key: $NOTHOLY_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "notholy-vector",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Explain IDOR in two sentences."}]
  }'

import os
from anthropic import Anthropic

client = Anthropic(base_url="https://api.notholy.com", api_key=os.environ["NOTHOLY_API_KEY"])

r = client.messages.create(
    model="notholy-vector",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain IDOR in two sentences."}],
)
print(r.content[-1].text)

Abrir no playground