Hy4 flash is Tencent Hunyuan's latest model, with about one-quarter the parameters of the flagship. While offering lower pricing, it achieves flagship open-source model performance on everyday tasks. It is suitable for programming assistance, agent workflows, document and chart understanding, and other high-frequency, large-scale scenarios in daily office use.
Pricing
- Input Tokens: $0.081 /M tokens
- Output Tokens: $0.324 /M tokens
- Cache Read: $0.0032 /M tokens
Input Modalities
- Text
- Vision
Output Modalities
- Text
Providers
Tencent tencent-hy4-flash
Pricing$0.081$0.324
Cache$0.0032
PrecisionⓘNot Disclosed
Latency4.1S
Throughput70.2TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
99.92% uptime today
Performance for hy4-flash
Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).
Uptime
Loading...
Latency
Loading...
Throughput
Loading...
Try this model
Python