RisuAI
RisuAI talks to OpenAI-compatible chat completions endpoints through its Custom API model. Give it the full chat completions URL under https://api.abliteratedllm.dev/v1.
Placeholders:
$API_BASEishttps://api.abliteratedllm.dev/v1,$API_ORIGINishttps://api.abliteratedllm.dev, and$YOUR_KEYis your API key.
Configure
- Open RisuAI's settings and go to Chat Bot.
- Set Model to Custom API.
- Fill in the fields that appear:
| Field | Value |
|---|---|
| URL | $API_BASE/chat/completions |
| Key/Password | $YOUR_KEY |
| Request Model | glm-5.3-flash-abliterated, deepseek-v4.1-flash or deepseek-v4-pro |
- Start a chat to test it.
Good to know
- Use the full URL. RisuAI sends requests to the URL exactly as entered, so include
/chat/completions. - Max response size. Trial accounts are capped at 4096 output tokens per response; paid accounts can use up to the model's
max_output_tokensfrom GET /v1/models (65536 for our abliterated models). - Text only. Images in a request fail with 400
unsupported_content. - 18+ only. See our Acceptable use policy.
- Pick an abliterated model for adult roleplay. Models labelled Official DeepSeek API are DeepSeek's stock models and keep DeepSeek's own refusals. See Models.
Verified against RisuAI docs on 2026-11-03. The official RisuAI wiki has no Custom API page yet, so the field names come from RisuAI's official source: BotSettings.svelte and openAI/requests.ts.