TTencent · Released Aug 28, 2026
Hy4 preview
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...
- Top 20%ProofBench
- Released
- Aug 28 2026
- Context window
- 1M 64K out
- Input / 1M tokens
- $0.83
- Output / 1M tokens
- $2.50
Where to run it
4 providers compared
All 4 providers charge the same: $0.83 / $2.50 per 1M input / output tokens.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| DeepInfraFP4 | $0.83 | $2.50 | $0.042 | 1M | 131K | 100%24h | Cheapest |
| NovitaFP8 | $0.83 | $2.50 | $0.042 | 1M | 64K | 100%24h | Cheapest |
| TencentFP8 | $0.83 | $2.50 | $0.042 | 1M | 64K | 100%24h | Cheapest |
| SiliconFlowFP8 | $0.83 | $2.50 | $0.042 | 1M | 262K | 99.9%24h | Cheapest |
Value
Price vs. performance
Hy4 preview Other Tencent Other labs Value frontier · ProofBench vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
1 benchmark score
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| ProofBenchMaths · Graduate maths proofs verified in Lean 4 | 75.0% | #14of 70 | Claude Sonnet 5.5100.0% |
Specs
Details
- Model ID
tencent/hy4-preview- Developer
- Tencent
- Release date
- Aug 28, 2026 ·
- Context window
- 1,048,576 tokens
- Max output
- 64,000 tokens
- API price
- $0.83 / $2.50 per 1M input / output tokens
- Providers
- 4
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.