Hy4 preview
by Tencent · tencent/hy4-preview · #257 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:22 PM UTC · refreshed hourly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.834
per 1M tokens
Output
$2.50
per 1M tokens
Blended (3:1)
$1.25
3 input : 1 output
Cache read
$0.042
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Hy4 preview with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.25 | $0.0876 | — |
| 50% | $0.954 | $0.048 | −45% |
| 90% | $0.716 | $0.0163 | −81% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.001167 | $1.17 |
| Document summary | 8,000 | 1,000 | $0.009173 | $9.17 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.03 | $30.02 |
| Long-context analysis | 150,000 | 5,000 | $0.1376 | $137.60 |
Specs
Context window
1.05M
tokens
Max output
64K
tokens
Input modalities
text
Tokenizer
Other