Hy4 preview model profile
Evidence snapshot:
Hy4 preview is a Tencent model profile with a 1,048,576-token context window. The dated catalog snapshot records text modalities and interfaces for prompt caching, reasoning controls, structured output, text generation, tool calling.
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 require planning, context continuity, and sustained multi-step execution.
Hy4 preview is a reference profile: Tencent publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
Hy4 preview 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.
Hy4 preview 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 $0.834 input and $2.501 output per million tokens. Cached input is $0.042 per million tokens.
No comparable third-party benchmark value is present in the 2026-09-06 snapshot. Missing values are not estimated.
Hy4 preview ranked #1 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. 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 2026-09-06 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
- 1,048,576 tokens
- Snapshot date
- 2026-09-06
- Knowledge cutoff
- Not disclosed
- Reference catalog ID
- tencent/hy4-preview
When to pick Hy4 preview
Hy4 preview is a reference profile: Tencent publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.
- Reach for it when a whole corpus has to fit in one prompt. The 1.05M-token context window is in the top quarter of the 163 models publishing a limit here, so long documents can go in whole rather than chunked.
- Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.
- Reach for it when you want to trade depth against cost per call. Reasoning effort is selectable across high, low, none, so one route can serve both cheap and deep work.
- Look elsewhere when you need to call it through Kendr today. This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
- Look elsewhere when the workload is production traffic. The catalog marks this model preview. Preview routes can change behaviour or availability without the notice a stable route carries.
Context, modalities, and identity
Hy4 preview 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
- 1,048,576 tokens
- Maximum output
- 64,000 tokens
- Input modalities
- text
- Output modalities
- text
- Knowledge cutoff
- Not disclosed
Model overview
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 require planning, context continuity, and sustained multi-step execution.
- Reference model ID
- tencent/hy4-preview
- Canonical version
- tencent/hy4-preview-20260827
- Hugging Face ID
- Not separately documented
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
- include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, temperature, tool_choice, tools
- prompt caching
- reasoning controls
- structured output
- text generation
- tool calling
Dated pricing snapshot
The dated reference snapshot lists $0.834 input and $2.501 output per million tokens. Cached input is $0.042 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
- 2026-09-06
- Input
- $0.834 per 1M tokens
- Cached input
- $0.042 per 1M tokens
- Output
- $2.501 per 1M tokens
Provider routes, performance, and uptime
The snapshot retains 1 provider endpoint. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.
- Active provider endpoints
- 1
- Best p50 latency
- 2.79 s
- Best p50 throughput
- 46 tok/s
- Availability with routing
- 99.94% over the sampled window
- Availability without routing
- 99.94% over the sampled window
- Performance date
- 2026-09-06
| Provider | Quantization | Input / 1M | Output / 1M | Cache read / 1M | Context | p50 latency | p50 throughput | Uptime (1d) |
|---|---|---|---|---|---|---|---|---|
| Tencent Cloud | fp8 | $0.834 / 1M | $2.501 / 1M | $0.042 / 1M | 1,048,576 tokens | 2.79 s | 46 tok/s | 100.00% |
Benchmark evidence and limitations
No comparable third-party benchmark value is present in the 2026-09-06 snapshot. Missing values are not estimated.
Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
Popularity and market context
Hy4 preview ranked #1 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.
- Third-party catalog rank
- #1
- Global market share
- Not inferred
- Observation date
- 2026-09-06
Frequently asked questions
When should I use Hy4 preview?
Hy4 preview is a reference profile: Tencent publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. Reach for it when a whole corpus has to fit in one prompt: The 1.05M-token context window is in the top quarter of the 163 models publishing a limit here, so long documents can go in whole rather than chunked. Reach for it when the model has to call tools: Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose. Reach for it when you want to trade depth against cost per call: Reasoning effort is selectable across high, low, none, so one route can serve both cheap and deep work. Look elsewhere when you need to call it through Kendr today: This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr. Look elsewhere when the workload is production traffic: The catalog marks this model preview. Preview routes can change behaviour or availability without the notice a stable route carries.
What is Hy4 preview?
Hy4 preview is a Tencent model profile with a 1,048,576-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 Hy4 preview have?
The dated profile lists 1,048,576 tokens of context and up to 64,000 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.
What benchmark evidence is available for Hy4 preview?
No comparable third-party benchmark value is present in the 2026-09-06 snapshot. Missing values are not estimated. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
Is Hy4 preview 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 Hy4 preview's global market share?
Hy4 preview ranked #1 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. 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
- Hy4 preview third-party catalog record (catalog, checked 2026-09-06)
- Third-party model catalog methodology (methodology, checked 2026-09-06)