Docs

Connect

The API follows the OpenAI Chat Completions format. Use these settings in any compatible client. Setup guides

Base URL
https://95-211-44-204.sslip.io/v1
API key
a key from the API keys page
Model
glm-5.3-flash-uncensored

Endpoints

POST /v1/chat/completionschat completions, streaming and non-streaming
GET /v1/modelsavailable models
GET /v1/balanceyour balance and total spend

Reasoning models stream their thinking in delta.reasoning before the answer in delta.content.

Examples

curl
curl https://95-211-44-204.sslip.io/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model": "glm-5.3-flash-uncensored",
       "messages": [{"role": "user", "content": "Hello"}]}'
Python
from openai import OpenAI

client = OpenAI(base_url="https://95-211-44-204.sslip.io/v1", api_key="sk-...")

stream = client.chat.completions.create(
    model="glm-5.3-flash-uncensored",
    messages=[{"role": "user", "content": "Hello"}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
JavaScript
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://95-211-44-204.sslip.io/v1", apiKey: "sk-..." });

const res = await client.chat.completions.create({
  model: "glm-5.3-flash-uncensored",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(res.choices[0].message.content);

Clients

Setup guides: OpenCode, Cursor, VS Code (Cline, Roo Code, Continue), ZCode, Zed, JetBrains, Aider, SillyTavern and chat apps

Models and prices

Model Context Input Output Cached
glm-5.3-flash-uncensored
GLM 5.3 Flash Uncensored
1M $0.16 $0.63 $0.063
LargeV2Uncensored Coming soon
vs GPT-5.6 Sol on par
vs Fable 5.1 high on par
vs Kimi K3 ahead on benchmarks

USD per 1M tokens

Billing

Each request is billed by its actual token usage, reasoning tokens included; cached prompt tokens are cheaper. A request is accepted while the balance is at least $0.01, so the last one may take it slightly below zero.

Errors

401the key is missing, wrong or revoked
402the balance is empty, top up
404unknown model name
429more than 4 requests at once, or a temporary rate limit
5xxa temporary problem, retry in a moment