When was Hy3 released?

Hy3 was released on July 6, 2026 by Tencent. This is the official Hy3 release date tracked on LLM Stats.

How much does Hy3 cost?

Hy3 pricing starts at $0.14 per million input tokens, $0.04 per million cached input tokens, $0.58 per million output tokens via DeepInfra, the lowest price among tracked providers.

Hy3 has 295 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

What is the license for Hy3?

Hy3 is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Hy3 is available through 1 provider including DeepInfra.

Where is the Hy3 paper or technical report?

Hy3 has a paper or technical report available at https://hy.tencent.com/research/hy3. Use that source for architecture, training, release and evaluation details.

What models should I compare Hy3 against?

Common Hy3 comparisons include Hy3 vs GLM-5.1, Hy3 vs Claude Opus 4.6, Hy3 vs Gemini 3 Flash. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.

Hy3 Benchmarks, Pricing & Context Window

Name: Hy3
Author: Tencent

Hy3: Benchmarks, Pricing & Context Window

Hy3 is a language model from Tencent, released in July 2026, with a 262K-token context window, and pricing from $0.140/M input, $0.035/M cached input, $0.580/M output.

Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and a 3.8B MTP layer, developed by the Tencent Hy Team. Following the Hy3 Preview launch in late April, the team scaled up post-training with higher-quality

Input

Text

Output

Text

Hy3 benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for Hy3 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How Hy3 holds up as conversations get longer.

Quality Tracker

Hy3 Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Tue Oct 20 2026

Notice missing or incorrect data?

Hy3 pricing

Providers

Hy3 starts at $0.140 per million input tokens and $0.580 per million output tokens via DeepInfra. Reused prompt prefixes cost $0.0350 per million cached input tokens.

Provider	Input $/M	Cached input $/M	Output $/M	Context in / out	TTFT p95 s	Output p5 c/s	Modalities in / out
DeepInfra	$0.140	$0.0350	$0.580	262.1K/262.1K	—	—	/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.

Hy3 model size

Hy3 has 295 billion parameters. See how it compares to other models in the same parameter range.

Parameters

295BMoE

Frontier (200B+)

295B

1B7B70B405B

Hy3 context window

Input and output token limits for Hy3, plus how it ranks on long-context understanding.

InputOutput

262Ktokens

≈ 394 pages of text

262K

8K128K1M

Try now

huggle

Hy3in Huggle

Make it with
Hy3.

Hy3 latency

Hy3 time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

Hy3 examples

Recent arena outputs from Hy3, picked from the highest-ranked matchups.

Hy3 license

Hy3 is released under the Apache 2.0 license, which permits commercial use, has 295.0B parameters.

License: Apache 2.0; Commercial use allowed
Parameters: 295.0B

Apache License 2.0 - allows commercial use

Hy3 resources

Official sources for Hy3: official launch post, source repository, model weights.

Hy3 vs other models

The most-compared alternatives to Hy3 are GLM-5.1, Claude Opus 4.6, Gemini 3 Flash. Open any pair side-by-side for benchmarks, pricing, context, and latency.