Community fine-tunes of GLM and DeepSeek that refuse less, for fiction, research, security testing and unfiltered brainstorming. Same key as the mainstream models.
glm-5.3-flash-uncensoredglm-5.3-flash-abliterated
deepseek-v4-pro-uncensoredglm-5.3-uncensoredStruck-through = the provider's official API price. Prices in USD, live from our billing.
These are open-weight models fine-tuned (or "abliterated") to remove most of the default refusal behaviour. They answer creative, mature and edgy prompts that mainstream models often decline.
They are not lawless: our terms still forbid breaking the law, malware and any sexual content involving minors, and abuse leads to account closure.
Prices start at a few cents per million tokens. Top up from $1 in crypto, or try them with the welcome gift when a round is open.
curl https://api.apixoai.online/v1/chat/completions \
-H "Authorization: Bearer sk-...your-key" \
-H "Content-Type: application/json" \
-d '{"model":"glm-5.3-flash-uncensored",
"messages":[{"role":"user","content":"Hello"}]}'That's about 111K tokens on Claude Fable 5. Valid 72h, for Google and Telegram sign-ups. Works on 13 models, including GPT-6.1 Sol, GPT-6 Luna, Claude Fable 5.
Sign up with Google, email or Telegram. Your API key is ready instantly ($0.10 free to test for Google and Telegram sign-ups).
Paste our base URL and your key into your SDK or tool. The docs have the exact config for each one.
Top up with crypto from $1. Every request shows its tokens and exact cost.
More answers in the docs, or contact us.
They refuse far less than the original models. Results vary by prompt; the abliterated variants are the most permissive.
No. We only store token counts and cost for billing.
Yes, any client with a custom OpenAI-compatible base URL works.