Decuff retweeted
If your app has an LLM in it, test it like an attacker would.
OWASP ranks prompt injection #1 on its Top 10 for LLM apps. Their own guidance says it's unclear any method fully prevents it.
Text from a user, a webpage or a file can steer the model. Wire it to tools and data, and that steer becomes an action.
Filters help. Adversarial testing shows what actually gets through.
Our Breach does that: authorized AI pentesting on systems you own, only in the scope you set.
Early access → decuff.ai/breach
One dark prompt. One real run.
Gothic horror: a drowned keeper knocks on his widow's door.
decuffed-flagship wrote it start to finish:
"Maren. Let me in. I'm so cold."
0 refusals · 0 disclaimers
15.09s · 243 tokens · $0.00035
Fiction and dark themes are allowed by design. Every wall is listed → decuff.ai/acceptable-use
Free trial on every account → decuff.ai
Decuff retweeted
Same prompt. Two models. Real run.
Task: build a working analog clock in a single HTML file.
⚡ decuffed-flagship: 2.73s · 1,167 tokens · $0.0016
🧱 decuffed-flash: 49.11s · 3,934 tokens · more detailed design
Both worked on the first try.
Pick speed or detail. Try both free → decuff.ai
Decuff retweeted
Not every model is right for every job, including ours.
On this task, Flagship finished in under 3 seconds. Flash took 49.
Flash is a smaller 27B model that writes more code and more detail, so it trades speed for depth.
Our guidance:
→ Flagship: speed and 1M context
→ Flash: richer output when time isn't the constraint
We'll keep publishing real benchmarks, including the ones where we're slower.
Same prompt. Two models. Real run.
Task: build a working analog clock in a single HTML file.
⚡ decuffed-flagship: 2.73s · 1,167 tokens · $0.0016
🧱 decuffed-flash: 49.11s · 3,934 tokens · more detailed design
Both worked on the first try.
Pick speed or detail. Try both free → decuff.ai
Decuff retweeted
build your own ai chatbot in just 31 lines of python using decuff.
→ powered by decuffed-flash
→ simple openai-compatible api
→ supports streaming responses
→ maintains conversation history
→ 1M free tokens every month
all you need is python and the openai package.
no complicated setup. just build and start chatting.
try it out: decuff.ai
Decuff retweeted
this is the setup i'd recommend to any developer trying decuff.
no new tools or complicated workflow. just claude code, an api key and a base url.
decuffed-flash built this working app in 37 seconds from a single prompt.
give it a try on your own project and let me know how it performs.
build your own ai chatbot in just 31 lines of python using decuff.
→ powered by decuffed-flash
→ simple openai-compatible api
→ supports streaming responses
→ maintains conversation history
→ 1M free tokens every month
all you need is python and the openai package.
no complicated setup. just build and start chatting.
try it out: decuff.ai
Decuff retweeted
claude code now works with decuff.
connect to api.decuff.ai, select decuffed-flash, and continue using your existing coding workflow.
in this live demo, one prompt builds a working pomodoro app with 201 lines of code in just 37 seconds.
→ compatible with openai and anthropic clients
→ no new tools or IDE required
→ 1M free tokens per month when you sign in with google or phone
get started: decuff.ai/docs
Decuff retweeted
one prompt. 37 seconds. 201 lines of code. a working app.
this is claude code powered by decuffed-flash through decuff.
no need to change your workflow or learn new tools. just switch your API endpoint and keep building.
give it a try on your own projects.
i’d love to hear what you build and how it performs.
claude code now works with decuff.
connect to api.decuff.ai, select decuffed-flash, and continue using your existing coding workflow.
in this live demo, one prompt builds a working pomodoro app with 201 lines of code in just 37 seconds.
→ compatible with openai and anthropic clients
→ no new tools or IDE required
→ 1M free tokens per month when you sign in with google or phone
get started: decuff.ai/docs
Decuff retweeted
decuff is live: abliterated open-weight models on one API.
- DeepSeek V4.1 Flash, abliterated — 552B, 1M context
- Qwen3.8 27B, abliterated — warm 24/7
They never refuse. Zero retention. Works with Claude Code, Codex, OpenAI SDK.
Start free: decuff.ai