Abliterated

GLM 5.3 Flash

Built for your everyday ideas.

Fast responses for everyday creation. Draft, explore, and iterate with an efficient model built for your daily workflow.

Try in playground Get API key

Proposed launch pricing

Input

$0.25/ 1M tokens

Output

$1.00/ 1M tokens

Reasoning

Explore complex problems and develop a thoughtful approach.

Code generation

Write, review, and refactor code across your projects.

Tool calling

Connect your applications with function-calling workflows.

A familiar API.

Read the quickstart →

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.unrefused.com/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="glm-5.3-flash-uncensored",
    messages=[{"role": "user", "content": "Help me shape an idea."}],
    stream=True,
)
for chunk in response:
    print(chunk.choices[0].delta.content or "", end="")

Example configuration. Use GET /v1/models to check which models your API key can access.

Have a harder question?

Try GLM 5.3

Deep reasoning. Complex builds.