Run Hy4 Outlaw in Open WebUI
Run hy4-outlaw in Open WebUI through Wild West: one key, a hard spend cap, and a model that answers instead of refusing.
| Model id | hy4-outlaw |
|---|---|
| Context window | 1,048,576 tokens (1M) |
| Tool calling | Supported |
| Price per 1M tokens | $3.20 input, $0.60 on a cache hit, $6.40 output |
| Web search | Add :online to the id |
Set it up
- Settings, Admin, Connections: add an OpenAI API connection.
- URL https://wildwestapi.com/v1 (keep the /v1) and your key.
- Leave Model IDs empty to auto-detect, or allowlist hy4-outlaw and hy4-outlaw:online.
OPENAI_API_BASE_URL=https://wildwestapi.com/v1
OPENAI_API_KEY=sk-ww-...
# Model IDs to allow (optional)
hy4-outlaw
hy4-outlaw:online
Open WebUI with Hy4 Outlaw The hy4-outlaw:online id searches the web before it answers, which turns Open WebUI into an uncensored answer engine with no plugin to install.
Hy4 Outlaw has its own page with every limit and price.
What a session costs
For a 10-message chat (about 40K input tokens, no cache hits, 8K output), Hy4 Outlaw comes to about $0.18 at today's prices.
FAQ
Can Hy4 Outlaw be used in Open WebUI?
Yes. Open WebUI does not depend on tool calling, so any chat model works; this one also brings a 1M context.
What does a session cost?
About $0.18 for a 10-message chat (about 40K input tokens, no cache hits, 8K output), at $3.20 in, $6.40 out and $0.60 per million on cache hits. Put a spend cap on the key so a long run cannot overrun it.
Is it uncensored?
Tencent's Hy4, uncensored: a million tokens of context, tool calling, reasoning and vision.