BazaarLinkBazaarLink
Sign in
T

Hy3

High-performance AI language model, available via BazaarLink with USD billing (TWD-quoted).

Intelligence#42 / 563
41
Artificial Analysis Intelligence Index
Speed#268 / 576
47.7
Output tokens per second (median)
Input Price#1 / 576
$0.13NT$ 4
USD / 1M tokens
Output Price#1 / 576
$0.53NT$ 17
USD / 1M tokens
First-token latency#468 / 576
1.48s
Time to first token (AA median)
ProviderTTencent
Released
Model IDtencent/hy3

Technical specifications

Context window
Reasoning
Input
Not specified
Output
Not specified

Pricing comparison

BazaarLink retail price alongside AA's observed market standard.

BazaarLink price our site

Input$0.13NT$ 4
Output$0.53NT$ 17
Cache read$0.03NT$ 1
Cache write
3:1 blended (est.)$0.23NT$ 7
All prices per 1M tokens. Supports TWD credit card / official invoice.

Market reference Artificial Analysis

Input$0.00
Output$0.00
Cache readAA not tracked
Cache writeAA not tracked
3:1 blended$0.00
AA has no reference price.
Source: artificialanalysis.ai

Independent benchmarks

Scores below come from Artificial Analysis, an independent third party. BazaarLink does not participate in the testing.

Intelligence 41
Coding 59
Math
MMLU
GPQA 90
This modelCategory leader
Coding ability
#38out of 176 models
LiveCodeBench / SciCode and similar
Overall intelligence
#42out of 563 models
Aggregated across academic benchmarks
Time to first token
#468out of 576 models
AA 全球 p50:1.48 秒
Intelligence
41
Top 7%
This model
41
Category leader
60
Median
15
Coding
59
Top 22%
This model
59
Category leader
78
Median
36
GPQA
90%
This model
90%
Category leader
94%
Median
68%
HLE
32%
This model
32%
Category leader
53%
Median
7%
SciCode
48%
This model
48%
Category leader
60%
Median
33%
AA-LCR
67%
This model
67%
Category leader
76%
Median
39%

Top 5 — CodingCoding Index leaderboard

1GPT-5.6 Sol (xhigh)openai/gpt-5-6-sol-xhigh78$5 / $30
3GPT-5.6 Sol (high)openai/gpt-5-6-sol-high77$5 / $30
AASource: Artificial Analysis · Independent third-party evaluation; not influenced by BazaarLinkView full evaluation on AA →

Quick Start

Use Hy3 via BazaarLink API — just change the base_url:

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://bazaarlink.ai/api/v1",
    api_key="sk-bl-YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="tencent/hy3",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
TypeScript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://bazaarlink.ai/api/v1",
  apiKey: "sk-bl-YOUR_API_KEY",
});

const response = await client.chat.completions.create({
  model: "tencent/hy3",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Why use Hy3 via BazaarLink?

  • USD billing (TWD-quoted) + unified invoices — no foreign credit card needed for Taiwan teams
  • OpenAI-compatible API — zero code changes required
  • Automatic failover — multi-provider redundancy for the same model
  • Chinese-language support — local team, instant help
Try Now← All Models

Frequently Asked Questions

What is Hy3?

Hy3 is an AI language model by Tencent, available via BazaarLink's OpenAI-compatible API.

How much does the Hy3 API cost?

Hy3 costs $0.1320 per 1K input tokens and $0.5280 per 1K output tokens when accessed through BazaarLink.

How do I use Hy3 with the OpenAI SDK?

Set base_url to "https://bazaarlink.ai/api/v1" and use model ID "tencent/hy3". All OpenAI SDK methods (chat.completions, embeddings, streaming) work without code changes.

What is the context window for Hy3?

See the specifications table on this page for Hy3's context window size.

Is Hy3 available for free?

Hy3 is a paid model. BazaarLink offers free trial credits on registration so you can test it without a credit card.

中轉站誠信檢測 · BazaarLink 獨家

尚無此模型的檢測資料

BazaarLink Probe 對聲稱提供此模型的 endpoint 進行家族指紋驗證與 V3 子模型對照。 如發現行為與真貨基準不符,會列入異常案例。

查看完整檢測報告 →

Related Models & Links

More from Tencent

Hy Mt2 PlusKinfra Text Embedding 4bKinfra Text Embedding 0.6b
All ModelsAPI DocumentationAPI Latency Probe
Support
Support
Hi! How can we help you?
Send a message and we'll get back to you soon.