Models / tencent
Hy4 preview
by tencent ·
tencent/hy4-previewTencent: 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...
reasoningtool-usereleased 2026-08-28
Legal score · raw
-
not yet benchmarked
Context
1.05M
max output 64K
Input
$1.04
per 1M tokens
Output
$3.13
per 1M tokens
Suite cost
-
no run recorded
Prompt caching
Grounded answers re-send the same retrieved authority every turn, so a cached read is what a long matter actually costs. Prices are per 1M tokens, from the provider’s own catalog.
Cache read
$0.05
20x cheaper than uncached
Uncached input
$1.04
per 1M tokens
Capabilities
Modalities
in text
out text
Request parameters it accepts
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.