# Connect RisuAI to Unrestricted AI

Use Unrestricted AI in RisuAI through the Custom API model: URL, Key/Password, Request Model and the OpenAI Compatible format.

## What you need

An Unrestricted AI API key from https://tryunrestrictedai.com/api/console#keys, plus these values. RisuAI works with any OpenAI-compatible chat completions endpoint; this is not an official RisuAI integration.



| Setting | Value |
| --- | --- |
| URL | https://tryunrestrictedai.com/v1/chat/completions |
| Model | venice-uncensored-1-2 |
| API key | Your key from the console (starts with ua_) |

## Set up RisuAI



- 1. Open Settings (the gear icon), then “Chat Bot”
- 2. Set Model to “Custom API” It is the OpenAI-compatible custom endpoint option in the model list.
- 3. Paste the full URL into “URL”: https://tryunrestrictedai.com/v1/chat/completions Use the complete /v1/chat/completions URL. It works whether or not RisuAI auto-fills the request path.
- 4. Paste your key into “Key/Password”
- 5. Type the model ID into “Request Model”: venice-uncensored-1-2
- 6. Set Format to “OpenAI Compatible”
- 7. Send a message in any chat to test


## Recommended settings

Model output limit: 4,096 tokens. Context window: 32,768 tokens.

- In the Parameters tab, keep “Max Response Size” at or below the model output limit and “Max Context Size” at or below the context window above.
- Leave the Auxiliary Model on a different provider, or set it to Custom API too if you want everything to use this key.


## Troubleshooting





| Status | Code | Fix |
| --- | --- | --- |
| 401 | invalid_api_key | The key is missing, mistyped or revoked. Paste the whole key (it starts with ua_) without “Bearer”, or create a new key in the console. |
| 402 | insufficient_credit · key_budget_exceeded · plan_limit | No usage left. Choose a plan or add credit in Billing, create a key with a higher spending limit, or lower the max response length. |
| 429 | rate_limit | More than 30 requests a minute or 3 at once. Turn off multiple swipes, auto-continue and parallel generations, then wait a minute. |
| 503 | inference_unavailable | The model is not accepting requests right now, or the model ID does not match a live model. Check the model ID and the status page, then retry. |
| 400 / 413 | unknown_model · invalid_request · context_limit | Wrong model ID, a response length above the output limit, or a context that is too long. Copy the model ID again and lower context or response size. |

## Limits and terms

Text chat with streaming is supported. Usage is billed per token from your plan allowance or credit, and each key has its own lifetime spending limit. Our terms and the selected model provider’s terms apply to role-play use the same as any other use: you must be 18 or older and the content must be lawful.




## Sources

- [RisuAI source: Custom API model settings](https://github.com/kwaroran/RisuAI)

Canonical: https://tryunrestrictedai.com/api/integrations/risuai