← All models
T
Get an API keytencent
tencent/…
1 serving nowup to 256K context
Every tencent model we serve, with the numbers most providers leave out — the quantisation each endpoint actually runs at, measured first-token latency, and real uptime. Model ids are copyable: pass one straight to any OpenAI-compatible client.
Hy3 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:...
- Parameters
- 295B (21B active)
- Max context
- 256K
| Quantisation | Context | p50 TTFT | Throughput | Uptime | Input /M | Output /M | Cached in /M | Status |
|---|---|---|---|---|---|---|---|---|
| Undisclosed | 256K | — | — | 99.95% | $0.16 | $0.68 | $0.04 | live |
moereasoningagentlong-contextcoding
Qwen
DeepSeek
Ornith
Infersia
Google
Meta
OpenAI
Thinking Machines Lab
xAI