--- title: "Hy3 AI model: facts and benchmarks | Kendr" canonical: "https://kendr.org/models/tencent-hy3" date_modified: "2026-08-12" profile_kind: "reference" --- # Hy3 model profile Hy3 is a Tencent model profile with a 262,144-token context window. The dated catalog snapshot records text modalities and interfaces for prompt caching, reasoning controls, structured output, text generation, tool calling. Hy3 is an independent knowledge profile. It does not claim that Kendr hosts the model, quote a Kendr customer price, promise API availability, or advertise a Kendr routing receipt. Hy3 accepts text and returns text. The snapshot records prompt caching, reasoning controls, structured output, text generation, and tool calling as capabilities or interfaces. The dated reference snapshot lists $0.132 input and $0.528 output per million tokens. Cached input is $0.033 per million tokens. The 2026-08-12 snapshot includes 6 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Hy3 ranked #2 in the cited trailing-7-day third-party catalog usage dataset as of 2026-08-12. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share. Profile data was reviewed for the 2026-08-12 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated. ## Profile facts - **Profile type:** Model research profile - **Provider or publisher:** Tencent - **Context window:** 262,144 tokens - **Snapshot date:** 2026-08-12 - **Reference catalog ID:** tencent/hy3 ## Context, modalities, and identity Hy3 accepts text and returns text. The snapshot records prompt caching, reasoning controls, structured output, text generation, and tool calling as capabilities or interfaces. - **Provider or publisher:** Tencent - **Context window:** 262,144 tokens - **Maximum output:** 128,000 tokens - **Input modalities:** text - **Output modalities:** text - **Knowledge cutoff:** Not disclosed ## Capabilities and supported controls Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route. - **Supported parameters:** frequency_penalty, include_reasoning, logit_bias, max_completion_tokens, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p - prompt caching - reasoning controls - structured output - text generation - tool calling ## Dated pricing snapshot The dated reference snapshot lists $0.132 input and $0.528 output per million tokens. Cached input is $0.033 per million tokens. These are dated third-party reference prices, not Kendr prices or an availability offer. Routes, tiers, caching, region, and provider policy can change the landed price. - **Price date:** 2026-08-12 - **Input:** $0.132 per 1M tokens - **Cached input:** $0.033 per 1M tokens - **Output:** $0.528 per 1M tokens ## Benchmark evidence and limitations The 2026-08-12 snapshot includes 6 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source. | Design Arena category | Elo | Win rate | Rank | | --- | --- | --- | --- | | 3d | 1230 | 43.8% | #39 | | codecategories | 1204 | 41.2% | #48 | | dataviz | 1154 | 36.1% | #69 | | gamedev | 1178 | 38.6% | #58 | | uicomponent | 1196 | 40.2% | #54 | | website | 1204 | 41.4% | #55 | ## Popularity and market context Hy3 ranked #2 in the cited trailing-7-day third-party catalog usage dataset as of 2026-08-12. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share. - **Third-party catalog rank:** #2 - **Global market share:** Not inferred - **Observation date:** 2026-08-12 ## Frequently asked questions ### What is Hy3? Hy3 is a Tencent model profile with a 262,144-token context window. The dated catalog snapshot records text modalities and interfaces for prompt caching, reasoning controls, structured output, text generation, tool calling. ### What context window does Hy3 have? The dated profile lists 262,144 tokens of context and up to 128,000 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits. ### What benchmark evidence is available for Hy3? The 2026-08-12 snapshot includes 6 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source. ### Is Hy3 available through Kendr? This is an independent knowledge profile, not a Kendr-hosted availability claim. Check Kendr's live public model API for currently enabled Kendr aliases. ### Does the popularity rank represent Hy3's global market share? Hy3 ranked #2 in the cited trailing-7-day third-party catalog usage dataset as of 2026-08-12. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share. No global market-share percentage is inferred when the source does not publish one. ## Sources and evidence dates - [Hy3 third-party catalog record](https://openrouter.ai/tencent/hy3) — catalog, checked 2026-08-12 - [Third-party model catalog methodology](https://openrouter.ai/docs/guides/overview/models) — methodology, checked 2026-08-12 - [Design Arena leaderboard and methodology](https://www.designarena.ai/leaderboard) — benchmark, checked 2026-08-12 Live Kendr operational availability is published separately at https://api.kendr.org/api/public/models.