All models
Tencent
Hy4 preview balancedruns locally
tencent/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...
Input / 1M
$0.83
USD per million tokens
Output / 1M
$2.50
USD per million tokens
Est. cost / token
$0.000001251
$1.25 per 1M, 3:1 mix
Context window
1.05M
max output 64K
Major features
Open weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding4
- reasoning4
- math4
- summarization4
- extraction4
- classification4
- chat4
- creative4
- translation4
- vision1
- long context5
- agentic4
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 351 GB |
| Q3_K_M | fair | 408 GB |
| Q4_K_Mrecommended | good | 509 GB |
| Q5_K_M | very good | 590 GB |
| Q6_K | excellent | 680 GB |
| Q8_0 | near-lossless | 878 GB |
| F16 | lossless | 1646 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.83 | $2.50 | $0.042 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.83
- Output
- $2.50
- Cached input
- $0.042
- Blended (3:1)
- $1.25
Details
- Company
- Tencent
- Version
- 4
- Family
- Hy
- Released
- 2026-08-28
- Parameters
- 780B
- Max output
- 64K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 46 min ago