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 from $0.67
- Output / 1M tokens
- $2.50 from $2.00
Where to run it
21 providers compared
Included in Tencent Token Plan, OpenCode Go. Cheapest: Vancine at $0.67 / $2.00 per 1M input / output tokens — 42% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Tencent Token Plansubscription plan | Plan | Plan | Plan | 1.02M | 64K | — | Plan |
| OpenCode Gosubscription plan | Plan | Plan | Plan | 1.02M | 64K | — | Plan |
| Vancine | $0.67 | $2.00 | $0.034 | 1.02M | 64K | — | Cheapest |
| NovitaFP8 | $0.83 | $2.50 | $0.042 | 1M | 64K | 100%24h | +25% |
| SiliconFlowFP8 | $0.83 | $2.50 | $0.042 | 1M | 262K | 100%24h | +25% |
| TencentFP8 | $0.83 | $2.50 | $0.042 | 1M | 64K | 100%24h | +25% |
| DeepInfraFP4 | $0.83 | $2.50 | $0.042 | 1M | 131K | 98.2%24h | +25% |
| NanoGPT | $0.83 | $2.50 | $0.042 | 1M | 64K | — | +25% |
| Kilo Gateway | $0.83 | $2.50 | $0.042 | 1M | 64K | — | +25% |
| Vercel AI Gateway | $0.83 | $2.50 | $0.042 | 1.02M | 64K | — | +25% |
| LLM Gateway | $0.83 | $2.50 | $0.042 | 1M | 66K | — | +25% |
| Novita AI | $0.83 | $2.50 | $0.042 | 1M | 64K | — | +25% |
| DevPass (LLM Gateway) | $0.83 | $2.50 | $0.042 | 1M | 64K | — | +25% |
| Hugging Face | $0.83 | $2.50 | — | 1M | 64K | — | +25% |
| CommandCode | $0.83 | $2.50 | $0.042 | 1.02M | 64K | — | +25% |
| Tencent TokenHub | $0.83 | $2.50 | $0.042 | 1.02M | 64K | — | +25% |
| Eden AI | $0.83 | $2.50 | $0.042 | 1M | 64K | — | +25% |
| AIHubMix | $0.84 | $2.54 | $0.042 | 1.02M | 64K | — | +26% |
| CrossModel | $0.96 | $2.88 | $0.048 | 1M | 66K | — | +44% |
| Venice AI | $1.04 | $3.13 | $0.053 | 1M | 64K | — | +56% |
| AI/ML API | $1.15 | $3.44 | $0.058 | 1M | 64K | — | +72% |
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
- 21
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; 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.