H

Tencent: hy4-preview

hy4-preview
1M context64K outReasoningToolsParallel toolsCacheStructuredWeb search
Released Aug 28, 2026Updated Nov 2, 2026

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.

Mode chatTokenizer Othertencent/Hy4-preview

Inputs used for the providers' own purposes

At least one provider of this model uses your inputs for its own purposes, for example to train AI models. Do not enter personal data of third parties or sensitive data. You can object to this use at any time in your account settings or via "Manage consents" in the chat.

Read the privacy policy

Pricing

Input price
$0.64/ 1M tokens24% off
Output price
$1.91/ 1M tokens24% off
Compatible endpoints openaiVendor Tencent

Uptime

Performance

Loading performance data...

Usage & Ranking

Loading usage...

Supported parameters

All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.

ParameterProvidersDefault
frequency_penaltyAll providers-
include_reasoningAll providers-
logit_biasSome providers-
logprobsSome providers-
max_completion_tokensSome providers-
max_tokensAll providers-
min_pSome providers-
parallel_tool_callsSome providers-
presence_penaltyAll providers-
reasoningAll providers-
reasoning_effortAll providers-
repetition_penaltyAll providers-
response_formatAll providers-
seedAll providers-
stopAll providers-
structured_outputsAll providers-
temperatureAll providers-
tool_choiceAll providers-
toolsAll providers-
top_kAll providers-
top_logprobsSome providers-
top_pAll providers-

Frequently asked questions

Similar models