Tencent: Hy3
Analysis Summary
Tencent's Hy3 pairs strong reasoning results with capable coding performance and a 262K-token context. Tool use and function calling are listed, giving it practical options for integration into business workflows. Its supplied agentic result is lower than its reasoning strength, so it is better treated as a capable assisted model than assumed to be a highly autonomous agent.
The listed price, $0.0825 per million input tokens and $0.33 per million output tokens, makes Hy3 attractive for volume-sensitive work such as routine analysis, structured content, and coding support. Its text-only input limits multimodal uses, but the cost and context size offer a strong case for a production trial. Adopt it for well-defined tasks with quality checks, and keep more demanding agentic or multimodal jobs on models whose capabilities are better matched to those requirements.
Assessed September 23, 2026
Editorial notes
Hy3 offers strong reasoning, useful coding and tool capabilities, a 262K context, and very low listed pricing; its agentic result is less compelling than its core reasoning.
The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?
DFO Verdict
Hy3 offers strong reasoning, useful coding and tool capabilities, a 262K context, and very low listed pricing; its agentic result is less compelling than its core reasoning.
Benchmarks
Artificial Analysis data refreshed Oct 29, 2026. Arena ratings from the Oct 22, 2026 text leaderboard, with style control. Bars: magenta = reasoning, ink = coding and agents, cyan = instructions and long context.
Artificial Analysis no longer lists this model, so its indexes are converted from their older scale to stay comparable.
How Tencent: Hy3 compares
Tencent: Hy3 ranks #96 of 446 AI models we track for overall intelligence, #44 of 199 for coding, #59 of 181 for agentic tasks. Its 262K-token context window is larger than 74% of the models we list. At $0.08 per million input tokens it is cheaper than 66% of comparable models.
Dark bar = input · light bar = output, scaled to the priciest peer.
1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.08 | $0.000083 |
| Output | $0.33 | $0.000330 |
What would Tencent: Hy3 cost your business?
Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.
A website chatbot handling around 100 customer conversations a day, a few short messages each.
Full calculator with 723 models → Price Calculator
These numbers get smaller with the right architecture.
We route routine calls to cheap models and save Tencent: Hy3 for the hard ones. Most clients cut their estimate by 60-80%.
Talk to our teamAbout 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:..
Frequently asked questions about Tencent: Hy3
How much does Tencent: Hy3 cost?
Tencent: Hy3 costs $0.08 per million input tokens and $0.33 per million output tokens.
What is the context window of Tencent: Hy3?
Tencent: Hy3 has a context window of 262,144 tokens (262K).
Is Tencent: Hy3 good for coding?
On our coding benchmark index, Tencent: Hy3 ranks #44 of 199 models, placing it in the top quartile of the field for code generation and debugging.
What can Tencent: Hy3 do?
Tencent: Hy3 supports tool use and function calling.
Who created Tencent: Hy3?
Tencent: Hy3 is developed by Tencent and was released on July 6, 2026.