Silk Compute
TencentNew

Hy4 Uncensored

hy4-uncensored

Hy4 is Tencent's newest flagship model, with better long-context reading and long agent runs than its preview, and reasoning effort you can set to low, high or max. It takes images as well as text. This abliterated version has its refusal behavior removed. It reads up to 1M tokens of context and writes up to 66K tokens in one reply.

Get an API keyAll models
Context
1M
Max output
66K
Input
$1.60 / M
Cached input
$0.30 / M
Output
$3.20 / M

Quickstart

Paste the agent prompt into Claude Code, Codex or any coding agent and it sets everything up. Or use the code directly, with SILK_API_KEY set in your shell.

Set up this project to use the Silk Compute API with the model hy4-uncensored.

Silk Compute is OpenAI compatible:
- Base URL: https://api.silkcompute.com
- Chat: POST /chat/completions (the Anthropic format is also served at /v1/messages)
- Auth: read the API key from the SILK_API_KEY environment variable. Never hard-code or commit it.

Model hy4-uncensored: 1,048,576 tokens of context, up to 65,536 output tokens. Tool calling and streaming are supported.
Reasoning effort (reasoning_effort): low, high, max (default high).

1. Use the OpenAI SDK if this project already has it; otherwise add the official one for its language.
2. Add a small client that sends a chat request to hy4-uncensored and returns the reply text.
3. Add SILK_API_KEY to the example env file if there is one, then show me how to send one test request.

Full API reference: https://silkcompute.com/llms.txt

Other models

Questions

Is Hy4 Uncensored really uncensored?

Yes. It is an abliterated version of Hy4: its refusal behavior has been removed, and Silk Compute adds no content filter on top.

How much does Hy4 Uncensored cost?

$1.60 per 1M input tokens, $0.30 per 1M cached input tokens, and $3.20 per 1M output tokens, paid from a monthly plan or prepaid credits. Top-ups start at $5.

How do I use Hy4 Uncensored in Claude Code, Codex or OpenCode?

Point the tool at https://api.silkcompute.com with your Silk Compute API key and set the model to hy4-uncensored. The setup for each tool is on this page and in the docs.

What is the context window of Hy4 Uncensored?

1,048,576 tokens of context, and up to 65,536 output tokens in one reply.

Does Hy4 Uncensored take images?

Yes. Send images in the OpenAI, Anthropic or Responses format. Images count as input tokens.

Does Silk Compute store my prompts?

No. Prompts and model outputs pass through our servers and are not stored. We keep only billing records, such as token counts and cost.