tencent
Tencent: Hy4 preview
tencent/hy4-preview
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
tencent/hy4-preview is presented in the supplied documentation as a text-to-text mixture-of-experts model with 49B activated parameters out of 770B, a 1M-token context, and reasoning enabled by default. The OpenRouter catalog emphasizes coding agents, complex tool use, and productivity tasks, while Tencent also describes office analysis, game development, and scientific research as target areas. Evidence is limited to the catalog and vendor material, so real-world performance still needs workload-specific validation.[1][2]
Strengths
- Vendor material presents tencent/hy4-preview as a flagship MoE system aimed at long-horizon software work, office analysis, game development, and research.[2]
- The reported design combines 49B activated parameters within a 770B MoE, sparse attention, speculative decoding support, and a 1M-token context.[1][2]
- OpenRouter lists text generation with configurable reasoning effort plus tool calling, structured outputs, and common sampling controls.[1]
Limitations
- Tencent describes this as an early preview and says it may spend too long reasoning and over-verify its own work.[2]
- The source pack contains a catalog entry and vendor documentation, but no independent evaluation; OpenRouter lists no benchmark results.[1][2]
- The supplied sources document text input and output only; suitability for other modalities is unknown.[1][2]
Where to use it
- Evaluate for coding assistants or agents that need long context and multi-step tool use.[1][2]
- Test on turning dispersed project material into documents, spreadsheets, presentations, or analyses.[2]
- Prototype game-development or research copilots, with review of complex reasoning and verification behavior.[2]
Sources
- [1] OpenRouter catalog · Tencent: Hy4 previewSources checked: Nov 13, 2026
- [2] Model documentation · Tencent: Hy4 previewSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...
Specifications
- Model ID
- tencent/hy4-preview
- Canonical ID
- tencent/hy4-preview-20260827
- Creator
- tencent
- Added to OpenRouter
- 28.08.2026
- Context length
- 1,048,576
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.834 / out $2.5
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · default high · efforts: high, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default high · efforts: high, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| GMICloudbf16 | 262,144 | $0.834 | $2.5 | — | — | — |
| AtlasCloudfp8 | 1,048,576 | $0.834 | $2.5 | — | — | — |
| DeepInfrafp4 | 1,048,576 | $0.834 | $2.5 | — | — | 100% |
| Novitafp8 | 1,000,000 | $0.834 | $2.5 | — | — | — |
| SiliconFlowfp8 | 1,048,576 | $0.834 | $2.5 | — | — | 100% |
| Tencentfp8 | 1,048,576 | $0.834 | $2.5 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.