Use an uncensored model in Cline
Cline is an OpenAI-compatible coding agent. You can point it at Obscurify.ai and code with an uncensored model that won’t refuse security research, odd file formats or blunt language. You get 200+ models through one key, and an account that’s a 16-digit number instead of an email.
Tested on 2026-11-08 with the Cline CLI 3.0.74 against the live API, including an agent run that wrote a file through a tool. The VS Code extension uses the same provider settings; those fields are noted below and match Cline’s current docs.
Before you start
- Cline. The VS Code extension from the marketplace, or the CLI:
npm install -g cline. - An Obscurify.ai API key. Create an account —
it’s a random 16-digit number, no email. Add a little credit on the
account page, then click Show API Key. The
key starts with
sk-obs1_and is derived from your account number, so you can always fetch it again. New accounts may get $1 of starter credit while this month’s promo budget lasts.
Pick a model
Browse /v1/models (prices on the
model list). Keep the whole id, prefix
included. All of these do tool calling, which an agent needs:
- Uncensored, needs the Pro plan:
z-ai/glm-5.3-flash-uncensored(the cheapest uncensored model, 1M context) ordeepseek/deepseek-v4.1-flash-uncensored. - Decensored, works on any funded account (Pay As You Go):
pqhaz/deepseek-v4.1-flash-1017-heretic. This is the model the test below ran on.
CLI setup (tested)
Configure the OpenAI-compatible provider once, then run a task:
cline auth -p openai \
-b "https://obscurify.ai/v1" \
-k "sk-obs1_..." \
-m "pqhaz/deepseek-v4.1-flash-1017-heretic"
cline -P openai -m "pqhaz/deepseek-v4.1-flash-1017-heretic" \
"Create a file named hello.txt containing exactly: obscurify works. Then reply DONE."
Cline stores this as an openai-compatible provider. cline -y auto-approves
tools for unattended runs — use it only in a sandbox.
VS Code extension setup
In the Cline panel, open the settings gear and set:
- API Provider: OpenAI Compatible
- Base URL:
https://obscurify.ai/v1 - API Key: your
sk-obs1_...key - Model ID:
pqhaz/deepseek-v4.1-flash-1017-heretic(or an uncensored id on Pro)
Save, and Cline uses Obscurify.ai for every task.
What it costs
Each request is billed from your balance at the model’s price. Agents use far more tokens than chat, because every step resends the system prompt, tools and history: small tasks in our tests averaged about 20,000 tokens. Paid models have no monthly token limit on any plan. See pricing.
If something fails
- 402: no balance. Add credit on the account page.
- 403
model_not_on_plan: your plan doesn’t include that model. Uncensored models need Pro; frontier models need Casual or Pro. Decensored models likepqhaz/deepseek-v4.1-flash-1017-hereticwork on any funded account. - 404
model_not_found: check the id against/v1/models, and keep its prefix. - 429: you’re going too fast, or you’ve used this month’s free-model tokens.
What stays private
Prompts and responses aren’t stored on Obscurify.ai’s servers, and models with the ZDR tag run only on zero-data-retention routes. Providers don’t see who sent a prompt, but they do see its text, including any files your agent reads and sends. Details are in the privacy policy.
More agents: Obscurify.ai for agents.