Atlas / Models / Tencent / Tencent: Hy3

Tencent: Hy3✓ Catalog verified

tencent/hy3

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 supports a configurable reasoning effort:...

Input price
$0.13 /1M
Output price
$0.53 /1M
Context
262K
Modalities
text
Released
Jul 6, 2026
Tool calling
✓ Yes
Atlas signal
88/100
01

Overview

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 supports a configurable reasoning effort:...

Access: available through the official Tencent API. Context window: 262K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 6, 2026
02

Specifications

API identifiertencent/hy3
ProviderTencent
Model typeText LLM
Context window262K catalog
Input modalitiestext
Output modalitiestext
ReleasedJul 6, 2026
ModeratedNo
Architecture modalitytext->text
Supported parameters
frequency_penaltyinclude_reasoninglogit_biasmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "top_k": null,
  "top_p": 1,
  "temperature": 0.9,
  "presence_penalty": null,
  "frequency_penalty": null,
  "repetition_penalty": null
}
03

Pricing

Live pricing components for tencent/hy3 as published in the catalog.

$0.13
Input /1M
$0.53
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$1.32e-7$0.13 / 1MPer input token
Completion tokens$5.28e-7$0.53 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.17Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Tencent: Hy3
MMLU Signal (Reasoning)
97signal
Coding Signal (HumanEval proxy)
88signal
Math Signal (GSM8K proxy)
83signal
Science Signal (GPQA proxy)
83signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Tencent: Hy3 through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="tencent/hy3",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Tencent: Hy3 cost?

$0.13 per 1M input tokens and $0.53 per 1M output tokens on the official Tencent API.

What is the context window of Tencent: Hy3?

Tencent: Hy3 supports up to 262K tokens of context.

Does Tencent: Hy3 support tool / function calling?

Yes, Tencent: Hy3 supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access Tencent: Hy3?

Use the official Tencent API with the model id `tencent/hy3`. See the Quick start section above for code examples.