Hy4 Preview on QuickSilver Pro
Hy4 Preview is Tencent's Hy4 preview — the successor to Hy3 — for coding and agentic workflows with reasoning over a 1M-token context. QuickSilver Pro pins Tencent's official route and charges $0.6672 input / $2.0008 output per 1M tokens — 20% below its current $0.834 / $2.501 OpenRouter rate.
At a glance
Tencent's Hy4 preview for coding and agentic workflows with reasoning over a 1M-token context.
Pricing comparison ($/1M tokens)
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $0.6672 | $2.0008 | lowest-cost |
| OpenRouter (tencent/hy4-preview) | $0.834 | $2.501 | 20% lower |
When to use
Reach for Hy4 Preview on coding and agentic workflows that want a current-generation Tencent model over a large 1M-token context: multi-file edits, tool-using agents, and reasoning-heavy code generation. It succeeds Hy3 as the newer Tencent flagship; because it is a preview endpoint, A/B it against your existing pick before moving production traffic.
When to use something else
It is a preview endpoint, so treat its availability and behavior as subject to change — for stable production pin a GA model. For the lowest token price, Hy3 or Qwen 3.7 Flash cost less; for a frontier reasoning flagship, use DeepSeek V4 Pro or Kimi K3.
Quickstart (curl)
curl https://api.quicksilverpro.io/v1/chat/completions \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hy4-preview",
"messages": [{"role": "user", "content": "Hello!"}]
}'OpenAI-compatible. One-line migration via base_url.
FAQ
Tencent's Hy4, the successor to Hy3, offered here as a preview endpoint. It takes text input and returns text over a 1M-token context, with reasoning, tool calling, and JSON-schema structured output. Because it is a preview, its capabilities and availability may change.
Yes — Hy4 Preview is an OpenAI-compatible chat completions endpoint on QuickSilver Pro. Set base_url=https://api.quicksilverpro.io/v1, paste your QSP key, and use model="hy4-preview". Streaming, tool calling, json_schema strict mode, and usage.cost accounting all work. Migration is a base_url + key swap, dropping the `tencent/` provider prefix from the model ID.
QuickSilver Pro lists Hy4 Preview at $0.6672 input / $2.0008 output per 1M tokens — 20% below Tencent's current $0.834 / $2.501 OpenRouter rate. QSP pins Tencent's official endpoint; drop the `tencent/` prefix when migrating.