1. 7API
  2. Uncensored AI API

Uncensored AI API

7API is an uncensored AI API: one key for 5 uncensored and abliterated language models, alongside 35 standard models from Claude, GPT, GLM, DeepSeek and Kimi. They use the same base URL and the same OpenAI- and Anthropic-compatible request formats, so any SDK, agent or chat app that speaks the OpenAI API can use them. Billing is per token from a prepaid balance, with no subscription and no content-filter layer added by the gateway.

Uncensored and abliterated models

ModelIDContextMax outputInput / 1MOutput / 1MCached / 1M
DeepSeek V4.1 Flash 1017 Abliterateddeepseek-v4.1-flash-1017-abliterated1M66K$0.15$0.15$0.05
DeepSeek V4.1 Flash 1017 Abliterated Fastdeepseek-v4.1-flash-1017-abliterated-fast1M66K$0.70$0.70$0.16
GLM 5.3 Uncensoredglm-5.3-uncensored1M66K$0.05$0.05$0.01
GLM 5.3 Flash Uncensoredglm-5.3-flash-uncensored1M66K$0.025$0.025$0.0025
GLM 5.3 Abliteratedglm-5.3-abliterated1M130K$0.80$0.80$0.25

Which uncensored model should I use?

ModelTypeBased onInput / 1MOutput / 1MCached / 1MMax outputReasoning effort
DeepSeek V4.1 Flash 1017 AbliteratedAbliteratedDeepSeek V4.1 Flash 1017$0.15$0.15$0.0566Knone low high max
DeepSeek V4.1 Flash 1017 Abliterated FastAbliteratedDeepSeek V4.1 Flash 1017$0.70$0.70$0.1666Kmodel default
GLM 5.3 UncensoredUncensoredGLM 5.3$0.05$0.05$0.0166Klow high xhigh max
GLM 5.3 Flash UncensoredUncensoredGLM 5.3 Flash$0.025$0.025$0.002566Klow high xhigh max
GLM 5.3 AbliteratedAbliteratedGLM 5.3$0.80$0.80$0.25130Khigh xhigh max

Abliterated vs. uncensored

Neither label guarantees zero refusals. Behavior varies by prompt and model version, so test with your own prompts before you rely on one.

Call the uncensored AI API

curl
curl https://7api.st/v1/chat/completions \
  -H "Authorization: Bearer $SEVENAPI_API_KEY" -H "Content-Type: application/json" \
  -d '{"model": "glm-5.3-abliterated", "messages": [{"role": "user", "content": "…"}]}'
Python
from openai import OpenAI

client = OpenAI(base_url="https://7api.st/v1", api_key="YOUR_7API_KEY")
r = client.chat.completions.create(
    model="glm-5.3-uncensored",
    messages=[{"role": "user", "content": "…"}],
)
print(r.choices[0].message.content)
Node.js
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://7api.st/v1", apiKey: process.env.SEVENAPI_API_KEY });
const r = await client.chat.completions.create({
  model: "deepseek-v4.1-flash-1017-abliterated",
  messages: [{ role: "user", content: "…" }],
});
console.log(r.choices[0].message.content);

Every model above also works on /v1/messages, so it runs in Claude Code as claude-glm-5.3-abliterated, and on /v1/responses. Ready-made OpenCode and Oh My Pi configs include them with the right effort settings. Any chat app or agent that lets you set an OpenAI base URL and key works too.

Why use an uncensored LLM API

Responsible use

Using a model with fewer refusals doesn't change what's legal. Typical uses are security research, red-teaming and evaluating refusal behavior, fiction, and research on sensitive topics where standard models refuse too often. You're responsible for how you use the output.

Is there a free uncensored AI API?

No. 7API is pay per token with a $5 minimum top-up. Rates start at $0.025 per million tokens, so a small top-up covers a lot of testing.

Is the uncensored AI API OpenAI-compatible?

Yes. Set the base URL to https://7api.st/v1 and use your 7API key with the OpenAI SDK or any OpenAI-compatible tool. Anthropic-format clients use https://7api.st.

Do uncensored models still refuse?

Sometimes. Abliterated models refuse least, but no model is guaranteed to answer every prompt. Results vary by prompt, model and reasoning effort.

How do uncensored models compare on benchmarks?

Independent leaderboards don't test uncensored builds. The benchmarks page lists scores for the base models (GLM-5.3, DeepSeek V4 Pro) they're derived from.

More