Hy3 API

Hy3 is Tencent's 295B-parameter Mixture-of-Experts model (21B active) for reasoning, agentic workflows, and production coding tasks.

Modalities: TextText
In / Out price: $0.2116/$0.8464per 1M
Context window: 256K tokens
Released: Jul 6, 2026

Hy3 overview

Hy3 by Tencent

Hy3 API delivers configurable reasoning effort, reliable tool-calling, and strong coding and document-analysis performance through a standard chat completions endpoint.

Hy3 specs

Model ID: tencent/hy3
Developer: Tencent
Context window: 262,144 tokens
Max output: 131,072 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It offers configurable reasoning effort, reliable tool-calling across agent frameworks, and strong performance on coding, document analysis, finance, and frontend development.

Comparison with Other Models
- vs other reasoning models: Hy3 combines configurable reasoning effort with a large 295B MoE architecture at a competitive price point.

Use cases

Hy3 is documented as suited to software development, where it shows progress in code generation and agent capabilities and is used in products like CodeBuddy and WorkBuddy for development workflows. It is also suited to office productivity, including document generation and workflow tasks such as creating PowerPoint, Word, Excel, PDF, and HTML files.

Hy3 is documented for financial modeling, where Tencent says it performs well in productivity scenarios alongside coding and office work. It is also suited to front-end design and game production, which are specifically named as productivity scenarios where the model has made notable progress.

Capabilities

Function calling
Reasoning
Streaming
Structured outputs
Web search

Hy3 benchmarks by Artificial Analysis

See how Hy3 compares in generation speed and latency. Data retrieved Nov 3, 2026.

Speed#116 / 21995.1Output tokens / second Latency#169 / 2162.77Seconds to first token Humanity's Last Exam#83 / 45833.5%Score GPQA Diamond#46 / 43989.7%Score

Speed

Output tokens / second

Benchmark results

Compare 20 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Hy3 API pricing

Hy3 pricing in US dollars
Usage	Price	Unit
Input	$0.2116	1M tokens
Output	$0.8464	1M tokens
Cached input	$0.0529	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Hy3 vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Hy3	$0.2116	$0.8464
Hy-MT2-1.8B	$0.0466	$0.1873
Hy-MT2-30B-A3B	$0.0783	$0.3121
Hy-MT2-7B	$0.0783	$0.3121
Hy4 Preview	$0.8824	$2.65

How to use the Hy3 API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "tencent/hy3",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "tencent/hy3",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = 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/hy3",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Hy3 FAQ

What is the context window of Hy3?

Hy3 has a 262,144 tokens context window and can return up to 131,072 tokens.

What inputs and outputs does Hy3 support?

Hy3 takes image, text as input and returns text.

What is the model ID for Hy3?

Use tencent/hy3 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was Hy3 released?

Hy3 became available on July 6, 2026.

How much does Hy3 cost?

Hy3 costs $0.2116 input and $0.8464 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Hy3 support streaming?

Yes, Hy3 can stream responses as they are generated.

Can Hy3 read images?

Yes, Hy3 accepts image input alongside text.

Who created Hy3?

Hy3 was built by Tencent.

Start building with Hy3

Get API key

Hy3 API

tencent/hy3

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "tencent/hy3",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "tencent/hy3",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = 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/hy3",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Hy3 API

Hy3 overview

Hy3 by Tencent

Hy3 specs

Use cases

Capabilities

Hy3 benchmarks by Artificial Analysis

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Hy3 API pricing

Hy3 vs other models: token prices

How to use the Hy3 API

Build with your agent

1Get your API key

2Make your first request

Related articles

Hy3 FAQ

Start building with Hy3

Hy3 API

Build with your agent

1Get your API key

2Make your first request

Hy3 API

Hy3 overview

Hy3 by Tencent

Hy3 specs

Use cases

Capabilities

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Hy3 API pricing

Hy3 vs other models: token prices

How to use the Hy3 API

Build with your agent

1Get your API key

2Make your first request

Models similar to Hy3

Hy4 Preview

Hy-MT2-1.8B

Hy-MT2-30B-A3B

Mercury 2.5

Mercury 3

Nemotron 3.5 Content Safety

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Hy3 FAQ

Start building with Hy3