An uncensored LLM APIthat speaks both formats
7 models behind one key. The endpoint takes requests in the OpenAI chat format, which is what opencode, Codex and most SDKs send, and in the Anthropic messages format, which is what Claude Code sends. Change the base URL and the model id in code you already have.
The endpoint
- Base URL, OpenAI format
https://uncensoredopencode.com/v1- Base URL, Anthropic format
https://uncensoredopencode.com- Auth
Authorization: Bearer sk-nc-...- Model list
GET /v1/models
With the OpenAI SDK
import os
from openai import OpenAI
client = OpenAI(base_url="https://uncensoredopencode.com/v1", api_key=os.environ["UNCENSORED_OPENCODE_API_KEY"])
reply = client.chat.completions.create(
model="glm-5.3-flash-uncensored",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://uncensoredopencode.com/v1", apiKey: process.env.UNCENSORED_OPENCODE_API_KEY });
const reply = await client.chat.completions.create({
model: "glm-5.3-flash-uncensored",
messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);What the model list tells you
/v1/models returns more than ids. Each entry says how much context the model has, whether it calls tools, whether it reasons, whether it takes images, whether it is an uncensored build and whether it is abliterated, along with its price per token. An agent or a script can read that and choose a model without a table being copied by hand.
| Model | Build | Context | Tools | Images | Per million tokens |
|---|---|---|---|---|---|
GLM 5.3 Flashglm-5.3-flash-uncensored | Uncensored | 1M tokens | Yes | Yes | $0.30 in / $1.00 out |
Kimi K3.1 Prokimi-k3.1-pro-uncensored | Abliterated | 1M tokens | Yes | Yes | $7.50 in / $37.50 out |
GLM 5.3glm-5.3-uncensored | Uncensored | 1M tokens | Yes | No | $2.00 in / $5.00 out |
DeepSeek V4.1 Flash 1017deepseek-v4.1-flash-1017-uncensored | Abliterated | 1M tokens | Yes | Yes | $1.25 in / $2.50 out |
MiMo V2.6 Flashmimo-v2.6-flash-uncensored | Abliterated | 1M tokens | Yes | Yes | $1.00 in / $2.00 out |
Qwen3.8 27Bqwen3.8-27b-uncensored | Uncensored | 1M tokens | Yes | Yes | $1.50 in / $5.00 out |
GLM 5.3 Flash Cyberglm-5.3-flash-cyber | Security-tuned | 1M tokens | Yes | Yes | On the models page |
In an agent harness
Questions
Is it a drop-in for the OpenAI API?
For chat completions, streaming and tool calling, yes: set the base URL and use one of the model ids on this page.
How do I pay?
Add credit in the dashboard and it is spent by the token. There is no monthly plan.
Is there a chat I can try first?
Yes, there is a chat page on the same models.