Tencent

Tencent: Hy3 preview

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...

ReasoningTool callingStreaming
262.1K token context Released Apr 22, 2026

Intelligence overview

0
Intelligence
0
Coding
0
Agentic

262.1K tok

Context window

235.9K tok

Max output

Capabilities

What Tencent: Hy3 preview can do.

Reasoning

Extended reasoning

Works through problems step by step before answering, trading latency for accuracy on harder tasks.

Adjustable effort

Choose how much the model deliberates per request — trade speed for depth as the task demands.

Development

Tool calling

Calls external functions mid-response, then continues reasoning from the result.

Streaming

Streams tokens as they're generated instead of waiting on the full response.

Performance

Intelligence25.8
Artificial Analysis
Coding58.8
Artificial Analysis
Agentic25.6
Artificial Analysis
Pricing

Pay for what you use.

Every model in UltraGPT runs behind one flat subscription — this is the underlying per-token cost the catalog tracks.

INPUT

$0.18 / 1M tok

OUTPUT

$0.6 / 1M tok

Cache read$0.06 / 1M tok
Use cases

Built for serious work.

Build

Generate and refactor code, with the ability to run and verify tool calls.

Think

Works through hard problems with adjustable reasoning effort — high, low, none.

Research

Holds up to 262.1K tokens of source material in context without losing the thread.

Automate

Chains tool calls across multi-step workflows, reasoning between each one.

Preview

Ask Tencent: Hy3 preview anything.

A preview of the real UltraGPT composer — the model you see here is the model you get.

Tencent: Hy3 preview Ready

Continues in the UltraGPT app — one login, every model.

Comparison

How Tencent: Hy3 preview stacks up.

The closest models in the catalog by provider, capability and score — real entries, pulled from the same directory.

Specification

Technical details.

Specification

Context window
262.1K tokens
Max output
235.9K tokens
Input modalities
Text
Output modalities
Text
Release date
Apr 22, 2026
Reasoning effort
high, low, none
Streaming
Supported
Tool calling
Supported
JSON mode
Not supported

Model identity

Provider
Tencent
Provider ID
tencent

Model ID

Reasoning

Effort: high, low, none
Directory

More from Tencent, and everything else.

This model is one entry in the full UltraGPT catalog — browse the rest, compare pricing and context windows, or filter by capability.

Tencent: Hy3 preview, one subscription away.

UltraGPT puts this model — and every other one in the directory — behind a single login and one flat monthly price.