DeepSeek V4 Pro Abliterated pricing

RouterHub token prices · USD per million tokens
Model / exact API IDVariantInputCached inputOutputContextAvailability
DeepSeek V4 Pro Abliterated
deepseek-v4-pro-abliterated
abliterated$0.4$0.04$1.61,000,000 tokenspreview

Cache-write rate: $0.4 per million tokens.

Prices are USD per million tokens. Cached input uses the cache-read rate when a cache hit is reported.

Compare variants

RouterHub token prices · USD per million tokens
Model / exact API IDVariantInputCached inputOutputContextAvailability
DeepSeek V4 Pro Abliterated
deepseek-v4-pro-abliterated
abliterated$0.4$0.04$1.61,000,000 tokenspreview
DeepSeek V4 Pro
deepseek-v4-pro
standard$0.15$0.0016$0.3Not publishedpreview
DeepSeek V4 Pro Uncensored
deepseek-v4-pro-uncensored
uncensored$0.2$0.0016$0.4Not publishedpreview

API compatibility and context

Exact model ID
deepseek-v4-pro-abliterated
Variant
abliterated
Supported API
OpenAI-compatible Chat Completions
Availability
preview
Context window
1,000,000 tokens
Maximum input
Not published
Maximum output
128,000 tokens

Use DeepSeek V4 Pro Abliterated through the API

Create a RouterHub account, add prepaid credits and create an API key. Set ROUTERHUB_API_KEY locally, then send a first request with the exact model ID below.

cURL

curl --connect-timeout 30 --max-time 600 https://routerhub.si/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4-pro-abliterated","messages":[{"role":"user","content":"Write a short noir scene set in a lighthouse."}],"max_tokens":256}'

Python

Install openai with pip. The examples request 256 output tokens and disable automatic retries. Check Usage after completion or a timeout before resending a paid request.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["ROUTERHUB_API_KEY"],
    base_url="https://routerhub.si/v1",
    timeout=600.0,
    max_retries=0,
)
response = client.chat.completions.create(
    model="deepseek-v4-pro-abliterated",
    messages=[{"role": "user", "content": "Write a short noir scene set in a lighthouse."}],
    max_tokens=256,
)
print(response.choices[0].message.content)

DeepSeek V4 Pro Abliterated FAQ

What is DeepSeek V4 Pro Abliterated?

DeepSeek V4 Pro Abliterated is the abliterated variant of DeepSeek’s DeepSeek V4 Pro, with weight-level refusal reduction.

How much does DeepSeek V4 Pro Abliterated cost?

RouterHub charges $0.4 input / $0.04 cached / $1.6 output per million tokens. Usage is billed against your prepaid balance.

What is the DeepSeek V4 Pro Abliterated context window?

Context window: 1,000,000 tokens. Maximum input: Not published. Maximum output: 128,000 tokens.

Which API does DeepSeek V4 Pro Abliterated support?

Use OpenAI-compatible Chat Completions with the exact model ID deepseek-v4-pro-abliterated and your RouterHub API key.

Which variants can I compare with DeepSeek V4 Pro Abliterated?

Compare DeepSeek V4 Pro Abliterated with DeepSeek V4 Pro, DeepSeek V4 Pro Uncensored. The comparison table includes their input, cached input, output and context.

Explore models and setup