Last refreshed 2026-08-31. Next refresh: weekly.
Why use Hunyuan Hy4 Preview on OpenRouter?
OpenRouter offers Hunyuan Hy4 Preview with pay-as-you-go pricing at $0.83/1M input tokens. OpenRouter is a multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.
Compare Hunyuan Hy4 Preview across 2 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: tencent/hy4-previewtencent/hy4-previewRequest example
tencent/hy4-preview.Gotchas
- Use provider model ID "tencent/hy4-preview", not the LLMReference slug "hy4-preview".
Compare Hunyuan Hy4 Preview Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Tencent Cloud TI Platform | $0.83 | $2.50 |
| OpenRouter | $0.83 | $2.50 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.83 |
| Output tokens | $2.50 |
Capabilities
About Hunyuan Hy4 Preview
Tencent Hunyuan Hy4 preview is a Mixture-of-Experts flagship language model released and open-sourced August 28, 2026. First-party Tencent release: 770B total parameters with 49B activated per token, context window exceeding 1M tokens, aimed at coding, office productivity, game development, and scientific research. Hugging Face model card (tencent/Hy4-preview) documents a 78-layer MoE backbone (256 routed experts, top-8 plus 1 shared expert), Gated DeepSeek Sparse Attention with IndexCache, iHC residual streams, native MTP speculative decoding, Apache License 2.0 weights (also Hy4-preview-FP8), and OpenAI-compatible serving via vLLM/SGLang with tool-call and reasoning parsers.