uncensored opencode

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

Python
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)
Node
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.

ModelBuildContextToolsImagesPer million tokens
GLM 5.3 Flash
glm-5.3-flash-uncensored
Uncensored1M tokensYesYes$0.30 in / $1.00 out
Kimi K3.1 Pro
kimi-k3.1-pro-uncensored
Abliterated1M tokensYesYes$7.50 in / $37.50 out
GLM 5.3
glm-5.3-uncensored
Uncensored1M tokensYesNo$2.00 in / $5.00 out
DeepSeek V4.1 Flash 1017
deepseek-v4.1-flash-1017-uncensored
Abliterated1M tokensYesYes$1.25 in / $2.50 out
MiMo V2.6 Flash
mimo-v2.6-flash-uncensored
Abliterated1M tokensYesYes$1.00 in / $2.00 out
Qwen3.8 27B
qwen3.8-27b-uncensored
Uncensored1M tokensYesYes$1.50 in / $5.00 out
GLM 5.3 Flash Cyber
glm-5.3-flash-cyber
Security-tuned1M tokensYesYesOn 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.

Bring your agent.