AI & Agents
Refuseless
Last updated 2026-10-05 · benchmark measured 2026-10-05 — deterministic & reproducible
OpenAI-compatible API serving abliterated LLMs with no prompt retention.
Refuseless at a glance
Refuseless offers an OpenAI-compatible API serving abliterated (refusal-removed) large language models, aimed at cybersecurity teams, penetration testers, coding professionals, security researchers, and AI agents, with zero prompt retention.
Good for
- Penetration testing or security research tasks where standard LLMs might refuse to answer
- Integrating an uncensored model into coding agents such as OpenCode or Pi via a standard OpenAI-style API
- Workloads needing a very large context window (1M tokens) for cybersecurity or coding tasks
Pricing
GLM 5.3 Abliterated: $2 input/$0.35 cache/$3 output per 1M tokens. Flash variant: $0.25/$0.1/$0.8. $5 free credits promo. Card or crypto accepted.
Questions people ask
How is usage billed?
Usage is billed per million tokens, split into separate input, cache, and output rates.
What does 'abliterated' mean for these models?
The models have had their built-in refusals removed, so they respond to requests that other LLMs might decline.
What payment methods does Refuseless accept?
You can pay with Visa or Mastercard, or with cryptocurrency including BTC, ETH, USDT, USDC, or XMR.
Does Refuseless store my prompts?
No, the service applies zero prompt retention to all requests.
Which endpoint do I call and what tools is it compatible with?
You call POST /v1/chat/completions using an OpenAI-compatible request shape, and it works with coding agents like OpenCode and Pi.
Written by Legit.Show from refuseless.com on 2026-10-07. It does not change the score.
Are you the maker of Refuseless? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/refuseless-com/2026-10-05. That address never changes; this page moves with every re-measure.
Legit.Show scored Refuseless 81/100 on 2026-10-05, measured across all 7 frames from its public surface. legit.show/s/refuseless-com/2026-10-05
Is Refuseless production-ready?
Legit.Show scores Refuseless 81 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Refuseless (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 88/100
- Accessibility — 82/100
- Security — 80/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 25/100How this compares across the catalogue: The Privacy Gap
- Reliability — 100/100
- Standards — 92/100
- Discoverability — 100/100
What we measured
- Security headers present: HSTS, X-Frame-Options, X-Content-Type-Options, Referrer-Policy.
- No Content-Security-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 595 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who it's for
Cybersecurity teams · Penetration testers · Coding professionals · AI agents · Security researchers
Pricing
GLM 5.3 Abliterated: $1.5 input / $2 cache / $2.5 output per 1M tokens (with discounts up to 40% for Flash variant). Credit card and cryptocurrency accepted. $5 free credits promo.
Sources and updates
- Description
- Taken from refuseless.com's own website on 2026-10-05.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-10-05.
Put together from public information, without Refuseless's involvement. If anything here is wrong, tell us and a person will check it.
Visit Refuseless → · Alternatives to Refuseless → · How this was measured →