Context
1.0M tokens (~524 books)
Input $/1M
$0.04
Output $/1M
$0.14
Type
multimodal
License
Proprietary
Benchmarks
0 tested
Data as of
About
Hy4 flash is Tencent's most cost effective Hy4 model · API id hy4-flash on Tencent Cloud TokenHub · 224B total parameters including 64B Engram parameters, 12B active · 1M token context · text and image in, text out · $0.070 input, $0.281 output, $0.003 cached input per 1M tokens · open weights planned.
No benchmark data available yet.
Links
Research
Documentation
Community
BenchGecko API
hy4-flash
Specifications
- Typemultimodal
- Context1.0M tokens (~524 books)
- ReleasedNov 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.000
Available On
Learn More
Share & Export
Frequently Asked Questions
Hy4 flash is a proprietary multimodal AI model by tencent, released in November 2026. Context window: 1M tokens.
Related Models
ERNIE-5.5-Flash-Preview (free) · baiduQwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteJais 3 0.9B · MBZUAIBenchmarks
Key facts · as of 2026-11-17
- Hy4 flash by tencent. Not enough public benchmark scores to rank yet.
- List price $0.0350 input · $0.14 output per 1M tokens (as of 2026-11-17).
- Sold by 1 provider (as of 2026-11-17): Tencent (fp8) $0.0350 in / $0.14 out.
How to cite · data as of 2026-11-17
Hy4 flash · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-17. https://benchgecko.ai/model/hy4-flash
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP