How to connect Wanmo Test to Nevika
Nevika takes any OpenAI-compatible endpoint as a custom proxy. Here is the one minute setup, which model to pick, and the two errors people hit.

Nevika is an AI roleplay platform with long-term memory and thousands of community characters. It does not host models, so it needs an endpoint to send prompts to. Nevika built a setup page for Wanmo Test with the base URL already filled in, so this takes about a minute.
The setup
Open the setup page, paste your Wanmo Test API key, and the model list loads straight from us. Pick a model, save, then message any character to test. The base URL is prefilled as https://api.unorouter.com/v1. The same key works in SillyTavern, RisuAI, Janitor.AI, and Chub.
Which model
glm-5.2 is a strong default for roleplay: it reasons without any special suffix, holds long scenes together, and costs little. Free models are fine for a first test, but they are shared and rate limited, so switch to a paid one once a story matters.
If something breaks
Empty model list means the key has a stray space from copying. A 401 means the key is wrong or revoked, so generate a new one. A 404 on a model means it was typed by hand instead of picked from the list. The SillyTavern setup guide covers the same errors in more detail.
Ready to try it? Create a free account or browse the models.
Trending models this week
Chat, image, embedding and speech models you can call for free through one OpenAI compatible API, what the limits are, and how to start in two minutes.
What a proxy does in Janitor AI, what makes one good for roleplay, and how the free and paid options compare, including where Wanmo Test fits and where it does not.
DeepSeek's own API is paid. Here is how to call DeepSeek models for free through an OpenAI compatible key, what the limits are, and how to use it in your code, Janitor AI or SillyTavern.
Comments
Loading comments