Tencent: Hy4 preview

Tencent · 1049K token context · text

Pricing: $1.69 per 1M input tokens, $5.06 per 1M output tokens

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...

Pricing

$1.69 per 1M input tokens and $5.06 per 1M output tokens. Billing is per token: input tokens are charged at the input rate and output tokens at the output rate, from one llmka.dev balance.

Prices checked 2026-11-07

Context and limits

The context window is 1,048,576 tokens (1049K).

The maximum output is 64,000 tokens.

When to use Tencent: Hy4 preview

Tencent: Hy4 preview (model ID `hy4-preview`) takes text input and returns text output.

Supported features in the catalog: function calling (tools), streamed responses over SSE, JSON-schema structured output.

Use Tencent: Hy4 preview for text generation and chat.

FAQ

How much does Tencent: Hy4 preview cost?

$1.69 per 1M input tokens and $5.06 per 1M output tokens. Billing is per token: input tokens are charged at the input rate and output tokens at the output rate, from one llmka.dev balance.

What is the context window and output limit of Tencent: Hy4 preview?

The context window is 1,048,576 tokens (1049K). The maximum output is 64,000 tokens.

How do I get access to Tencent: Hy4 preview?

Create an API key in the llmka.dev dashboard and send requests to model "hy4-preview" at https://api.llmka.dev/v1. The endpoint is OpenAI-compatible. One key and one balance cover all models on the gateway.

Related models

• Tencent HY3 - $0.07 in / $0.30 out per 1M
• Claude Sonnet 4.5 - $1.68 in / $8.42 out per 1M
• GLM 5 (Web) - $1.66 in / $6.26 out per 1M
• Grok Build 0.1 - $1.65 in / $3.30 out per 1M
• Aion 2.0 - $1.78 in / $3.56 out per 1M
• Claude Sonnet 5 - $1.80 in / $9.00 out per 1M
• Hermes 3 Llama 3.1 405b - $1.37 in / $5.49 out per 1M
• MiniMax M2.7 Highspeed - $1.30 in / $5.18 out per 1M

Links

All models · Prices · API documentation · Quick start

Available through the llmka.dev gateway: OpenAI- and Anthropic-compatible endpoints, one key, USDT top-up.