RisuAI
RisuAI connects to UberLLM through its Custom API model.
Before you start
- An UberLLM account with credit, and an API key from
Dashboard → Keys (
ull_...).
Setup
- Open Settings → Chat Bot, on the Model tab.
- Set the model to Custom API.
- Fill in:
- URL:
https://api.uberllm.dev/v1/chat/completions - Key/Password: your
ull_...key - Request Model: a model id, for example
deepseek/deepseek-v4.1-flash - Format: OpenAI Compatible
- URL:
- Send a message to test it.
The full URL works whatever your settings. (With Autofill Request URL on, the
default, https://api.uberllm.dev/v1 also works: RisuAI adds /chat/completions.)
On the web version, RisuAI sends the request through its own server, so nothing else is needed. The desktop and self-hosted versions call UberLLM directly.
Recommended models
Checked on 2026-10-30 through UberLLM.
| Request Model | Context | Notes |
|---|---|---|
deepseek/deepseek-v4.1-flash |
1,048,576 | Fast and cheap |
z-ai/glm-5.2 |
1,048,576 | Good at long stories |
venice/uncensored-1.2 |
128,000 | Uncensored |
deepseek/deepseek-v4.1-flash-uncensored |
1,048,576 | Uncensored; fewer providers serve it, so it can be busy |
Uncensored text models are listed for every account.
Common errors
| What you see | Cause and fix |
|---|---|
| "Failed to fetch … This can be a CORS error" | On the web version this appears with Force Plain Fetch on. Turn it off. |
401 |
Key missing or mistyped in Key/Password. |
404 "page not found" |
URL typo. Use https://api.uberllm.dev/v1/chat/completions. |
404 model_not_found |
Request Model mistyped. Copy the id from the catalog. |
402 insufficient_credits |
Balance empty. Add credit under Dashboard → Credits. |