Abliterated
GLM 5.3 Flash
Everyday development, chat and fast workflows.
- Input / 1M
- $0.3
- Output / 1M
- $0.96
ABLITERATED MODELS · API + CHAT
Ask whatever
you want.
Bring GLM, Qwen and DeepSeek into your apps through one API. Or open the chat and explore your ideas.
One account. Shared credit for API and chat.
FOR BUILDERS
Your next idea
starts here.
An assistant in your app. An agent that writes code. The automation you’ve been meaning to build.
Connect abliterated models with the OpenAI SDK you already use. Pick a starting point and make it your own.
Create your first keyA key for each projectCreate and revoke it from the console.
Top up. Use. Track.Prepaid credit with usage you can track.
example.pySDK OpenAI
from openai import OpenAI
import os
client = OpenAI(
base_url="https://uncensuredai.com/v1",
api_key=os.environ["UNCENSURED_API_KEY"]
)
response = client.chat.completions.create(
model="glm-5.3-flash-abliterated",
messages=[{
"role": "user",
"content": "Let’s build this idea."
}],
max_tokens=512
)
print(response.choices[0].message.content)Python · ready to adapt
Per 1M tokensInput $0.3 · Output $0.96
Set UNCENSURED_API_KEY to a key from your console.
Just want
to chat?
The same models, in a chat. Write, attach a file, adjust reasoning and search the web.
Open chatSign in with your account. Chat shares your API credit.
Choose your
model.
Per 1M tokens
Abliterated
GLM 5.3
Complex tasks, analysis and structured reasoning.
- Input / 1M
- $2.4
- Output / 1M
- $3.6
Abliterated
Qwen 3.8 Flash Next
Code, agents and cost-conscious experiments.
- Input / 1M
- $0.216
- Output / 1M
- $0.72
Abliterated
DeepSeek V4.1 Flash
Another approach to code, analysis and conversation.
- Input / 1M
- $0.72
- Output / 1M
- $1.92
See the model catalog for cache rates and details.
This page refreshes prices from the catalog. Your final charge depends on tokens actually used.
Ready
to build?
Create an account, add credit and generate a key. Choose a model and bring it into your projects.
Create an API keyOr start with chat