Tencent: Hy4 Preview is a hybrid expert (MoE) model launched by Tencent, with a total parameter size of 770B and an activation parameter size of 49B. It is designed for coding agents, complex tool usage workflows, and productivity tasks that require planning, contextual continuity, and sustained multi-step execution.
- By:
- Tencent
- Input:
- Output:
- Context length:
- 1.05M
- Max output:
- 64K
- Published:
- 2026-08-28
Providers
Same model, different providers. Automatic routing picks the cheapest healthy one within the same quality tier.
| Provider | |||||||
|---|---|---|---|---|---|---|---|
| 35% offtencent-cloud | — | $0.834$0.5421/1M tokens | $2.501$1.6257/1M tokens | Read$0.042$0.0273/1M tokensWrite— | 1.05M | — | — |
Availability
7 daysSuccess rate of the requests Amux actually sent to each provider. Client errors are excluded from the denominator — a malformed request isn't the provider's fault.
Throughput
7 daysAverage output speed on streaming requests, in tokens per second (TPS).
Latency
7 daysAverage time to first token (TTFT) on streaming requests — how long from sending a request to receiving its first token.
Activity
7 daysToken usage and cost for this model over time, split by the provider that served each request.
Related models
More models from Tencent