Models / tencent
Hy3
by tencent ·
tencent/hy3Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
reasoningtool-usereleased 2026-07-06
Legal score · raw
-
not yet benchmarked
Context
262K
max output 128K
Input
$0.16
per 1M tokens
Output
$0.66
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
$0.04
4.0x cheaper than uncached
Uncached input
$0.16
per 1M tokens
Capabilities
Modalities
in text
out text
Request parameters it accepts
frequency_penaltyinclude_reasoninglogit_biasmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_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.