T
TENCENT / tencent/Hy4-base

Tencent Hy4 Base

Hy4 pretrained checkpoint with weights published on November 20. Its language backbone has 770 billion parameters and activates 49 billion per token; vision supports images and video. It is distinct from the Hy4 assistant and its FP8 quantization.

01 / SUMMARY

The essential

ORIENTATION770B-parameter multimodal MoE base

Primary use stated or inferred cautiously from official documentation.

CONTEXT1.048.576 tokens

Maximum input capacity when published by the source.

EXITText; separate output maximum unpublished

Documented maximum generation limit.

ACCESSHugging Face · downloadable checkpoint

Verified availability channels.

MODEL TYPEMultimodal · Text and reasoning · Code

Primary functional family and verified specialties.

LICENSETencent Hy License 1.0

Declared terms for API access, model weights, or self-hosting.

02 / TECHNICAL SHEET

Limits and integration

API IDtencent/Hy4-base
Model typeMultimodal · Text and reasoning · Code
Access modelOpen weights
LicenseTencent Hy License 1.0
DeploymentSelf-hosted
Release20 NOV 2026
Knowledge cutoffNot published
EntranceText · Image · Video
ExitText
Context window1.048.576 tokens
maximum outputText; separate output maximum unpublished
ReasoningNot published
Published tools
Structured OutingsNot published
Batch processingNot published
Prompt cacheNot published
Fine-tuningNot published
Verified platformsHugging Face · Transformers
BEST SUITED FOR

Research and further adaptation; not an instruction-tuned chat model.

WORTH MONITORING

Tencent Hy License has its own commercial conditions for large MaaS providers; it is not Apache 2.0. Weight context does not replace TokenHub limits. Synthetic data and answer formats can affect the few-shot table.

03 / CAPABILITIES

What it can do

01

Orientation

Research and further adaptation; not an instruction-tuned chat model.

02

Context

1.048.576 tokens · Text; separate output maximum unpublished

03

Tools and integration

Not published

04

Access

Hugging Face · downloadable checkpoint

Input modalities
TextImageVideo
04 / PRICES

Documented cost

ConceptWorthUnit/condition
Standard inputNo published official API rateStandard API rate
Cached inputNot publishedReading reused prefixes
Cache write or storageNot publishedThe condition varies by provider
Standard outputSelf-hosted infrastructure costMay include reasoning tokens
Batch inputNot publishedAsynchronous processing
Batch outputNot publishedAsynchronous processing

No verified official API tariff. Self-hosting requires memory, compute and maintenance; downloadable weights do not make inference free.

i Prices change and may depend on level, region or context length. Check the source before making a decision.

05 / EVALUATIONS

How to read the results

“

Hy4 Base scores 73.9% on MMLU-Pro with five examples and macro accuracy. This Tencent evaluation concerns the base model, not the assistant or FP8.

BenchmarkResultMetricSource
MMLU-Pro (Hy4 Base 5-shot)73.9 %Macro accuracy · 5-shotView source ↗

Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.

06 / VERSIONS

Chronology

tencent/Hy4-base

BF16 checkpoint.

07 / SOURCES

Traceability