Models10in catalog
Largest context1.0MHy4 preview
Avg context
238K
Cheapest input
$0.044/M
Hy-MT2-1.8B
Largest output
262K
Hy3 (free)
Speed tiers
balanced 5fast 5
Capabilities
What Tencent models support across the catalog.
Tool use
5 / 10
50% of models
Function calling
5 / 10
50% of models
Extended thinking
7 / 10
70% of models
Streaming
10 / 10
100% of models
Prompt caching
3 / 10
30% of models
All Tencent models
Sorted by context window, largest first. Tap a row for full specs.
| Model | Context | Max output | Input $/M | Speed |
|---|---|---|---|---|
| Hy4 preview | 1.0M | 64K | $0.834/M | balanced |
| Hy3 | 262K | 131K | $0.132/M | balanced |
| Hy3 (free) | 262K | 262K | — | balanced |
| Hy3 preview | 262K | 262K | $0.180/M | balanced |
| Hy3 preview (free) | 262K | 262K | — | balanced |
| Hunyuan A13B Instruct | 131K | 131K | — | fast |
| Hunyuan A13B Instruct | 131K | 118K | $0.140/M | fast |
| Hy-MT2-1.8B | 8K | 4K | $0.044/M | fast |
| Hy-MT2-30B-A3B | 8K | 4K | $0.074/M | fast |
| Hy-MT2-7B | 8K | 4K | $0.074/M | fast |
See rankings
How Tencent models rank against the full catalog.