HY3

hy3 by Tencent Cloud Released October 2, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$0.13 / 1M
Output from
$0.528 / 1M
Cached input from
$0.033 / 1M
Context window
262K
Endpoints
2
from 2 providers
Regions
Asie, États-Unis

About HY3

Hy3 est un modèle « Mixture-of-Experts » à 295 milliards de paramètres développé par Tencent (21 milliards de paramètres actifs, 192 experts avec routage « top-8 »), conçu pour le raisonnement, les workflows agentiques et une utilisation en production dans le monde réel.

HY3 est un modèle conversationnel développé par Tencent Cloud, disponible sur Eden AI via 2 endpoints chez 2 fournisseurs, à partir de 0,13 $ par million de tokens en entrée et 0,528 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 262K tokens.

Providers and prices

2 endpoints from 2 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
DeepInfra (États-Unis)Official−%deepinfra/tencent/Hy3
États-Unis
262K
$0.13$0.13
$0.53
$0.033
ReasoningToolsJSONCacheVisionWeb
Tencent Cloud (Asie)Official−%tencent/hy3
Asie
256K
$0.132$0.132
$0.528
$0.033
ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
0.75 s
DeepInfra (États-Unis)
Lowest latency
5.68 s
Tencent Cloud (Asie)
Highest throughput
72.98 tok/s
Tencent Cloud (Asie)
Best availability
100%
Tencent Cloud (Asie)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
DeepInfra (États-Unis)
0.75 s
12.58 s
40.71 s
30.88 tok/s
100%
76.09%
0%
0%
Tencent Cloud (Asie)
2.57 s
5.68 s
28.52 s
72.98 tok/s
100%
77.01%
0%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call HY3 with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about HY3

On Eden AI, prices for this model start at $0.13 per million input tokens and $0.528 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 262K tokens, depending on the endpoint.

2 endpoints from 2 providers, available in: Asie, États-Unis. All of them are called with the same Eden AI API key.

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

Over the last 30 days, the fastest first token was 0.75 s (DeepInfra (États-Unis)) and the highest throughput was 72.98 tokens per second (Tencent Cloud (Asie)).