Talk to our sales team
Custom pricing for production workloads
Something went wrong. Please try again.
Custom pricing for production workloads
Hy4 is the latest model developed by Tencent, built to succeed the previous preview version with significant upgrades to its agentic capabilities.
Designed for versatility, the model handles both text and image inputs while providing users with control over its reasoning effort.
The model supports a context window of 1M tokens to handle extensive information.
Users can adjust the reasoning effort to suit the specific demands of their tasks.
Hy4 processes both text and image inputs to generate comprehensive text responses.
The model includes support for tools, streaming, and structured output generation.
Automating complex, long-horizon productivity tasks.
Analyzing visual data alongside textual information.
Generating structured outputs for data processing workflows.
Executing multi-step agentic reasoning processes.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "tencent/hy4", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "tencent/hy4", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"tencent/hy4","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Billed per token: $0.882372 / 1M input tokens, $0.044436 / 1M cached input tokens and $2.646058 / 1M output tokens. Reasoning tokens are billed as output.
Automating complex, long-horizon productivity tasks.
Analyzing visual data alongside textual information.
Generating structured outputs for data processing workflows.
Executing multi-step agentic reasoning processes.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Hy4 This page | Complex agentic tasks and multimodal productivity. | |||
| Long-horizon coding + agentic works | ||||
| Reasoning + agents | ||||
| High-accuracy translation | ||||
| Agentic workflows and structured output |
Hy4 costs $0.882372 / 1M tokens for input and $2.646058 / 1M tokens for output on AI/ML API. Cached input is billed at $0.044436 / 1M tokens.
Hy4 accepts both text and image inputs.
The model features a 1M-token context window.
Yes, Hy4 allows for configurable reasoning effort.
The model supports a maximum output of 65,536 tokens.
