Hy4 Outlaw
hy4-outlawTencent's Hy4, uncensored: a million tokens of context, tool calling, reasoning and vision.
The uncensored Hy4 API
Wild West serves an uncensored build of Hy4 under the model id hy4-outlaw. It has 1.05M tokens of context, costs $3.20 per million input tokens and $6.40 per million output tokens, with cached input at $0.60, and supports tool calling, so it can drive an agent. One key works on the OpenAI-compatible endpoint (https://wildwestapi.com/v1) and on the Anthropic-compatible one Claude Code uses, so the same Hy4 model plugs into Claude Code, Cline, opencode, SillyTavern, the OpenAI SDK and anything else that takes a custom base URL.
Hy4 uncensored against the rest of the line
| Model | Context | Input | Output | Intelligence | Tools | Images |
|---|---|---|---|---|---|---|
| Slingshooter | 1.05M | $2.00 | $5.00 | 45 | Yes | No |
| Hipshooter | 1.05M | $0.30 | $1.00 | 42 | Yes | Yes |
| DeepSeek V4.1 Flash 1017 Outlaw | 1.05M | $1.25 | $2.50 | 39 | Yes | Yes |
| High Noon | 1.05M | $1.00 | $2.00 | 38 | Yes | Yes |
| Sidewinder | 1.05M | $1.50 | $5.00 | 34 | Yes | Yes |
| Qwen3.8 27B Ultrafast Outlaw | 524k | $1.75 | $5.50 | 34 | Yes | Yes |
| DeepSeek Flash Lite Outlaw | 512k | $0.36 | $1.44 | 39 | Yes | Yes |
| Hy4 Outlaw | 1.05M | $3.20 | $6.40 | - | Yes | Yes |
| Kimi K3.1 Pro Outlaw | 1.05M | $7.50 | $37.50 | 55 | Yes | Yes |
Prices are per million tokens. Intelligence is the Artificial Analysis Intelligence Index of the base model. DeepSeek V4.1 Flash 1017 Outlaw has no score of its own, so it shows DeepSeek V4.1 Flash's, the model it was tuned from. DeepSeek Flash Lite Outlaw has no score of its own, so it shows DeepSeek V4.1 Flash's, the model it was tuned from.
What the uncensored tag actually means
hy4-outlaw is tagged uncensored, which here means a loosely aligned finetune. It refuses far less than a frontier instruct model, but it is not abliterated: the refusal behaviour was reduced by training, not surgically removed, so it can still decline. Nothing about the tag promises it will answer anything.
Call it with curl
curl https://wildwestapi.com/v1/chat/completions \ -H "Authorization: Bearer sk-ww-..." \ -H "Content-Type: application/json" \ -d '{ "model": "hy4-outlaw", "messages": [{"role": "user", "content": "Hello"}] }'
Call it with the OpenAI SDK
# pip install openai from openai import OpenAI client = OpenAI( base_url="https://wildwestapi.com/v1", api_key="sk-ww-...", ) resp = client.chat.completions.create( model="hy4-outlaw", messages=[{"role": "user", "content": "Hello"}], ) print(resp.choices[0].message.content)
In Claude Code
This model supports tool calling, so it can drive Claude Code. Set the context length to its real value of 1,048,576:
# Put these in your shell profile, then run: claude export ANTHROPIC_BASE_URL=https://wildwestapi.com export ANTHROPIC_AUTH_TOKEN=sk-ww-... export ANTHROPIC_MODEL=hy4-outlaw export ANTHROPIC_DEFAULT_HAIKU_MODEL=glm-5.3-outlaw export CLAUDE_CODE_MAX_CONTEXT_TOKENS=1048576
FAQ
What does the uncensored tag mean?
Uncensored here means a loosely aligned finetune that refuses much less than a frontier model, but can still decline. It is not the same as abliterated.
How much does it cost?
$3.20 per million input tokens and $6.40 per million output tokens.
Is there an uncensored Hy4 API?
Yes. Wild West serves Hy4 with the refusal training loosened (uncensored) as hy4-outlaw, on an OpenAI-compatible endpoint at https://wildwestapi.com/v1 and an Anthropic-compatible one for Claude Code.
What is the Hy4 context window?
1,048,576 tokens (1.05M).
Does Hy4 uncensored support tool calling?
Yes. It can call tools, so it can drive coding agents such as Claude Code, Cline and opencode.
Can Hy4 uncensored read images?
Yes. Send images as OpenAI image_url content parts, or paste them into the chat.
Can I use Hy4 uncensored in SillyTavern?
Yes. Add Wild West as an OpenAI-compatible (Chat Completion) source with the base URL https://wildwestapi.com/v1, your key, and hy4-outlaw as the model.