Tencent Hy4 Preview
Hy4 Preview is Tencent's 770B-parameter mixture-of-experts model with 49B active parameters. It is designed for coding agents, complex tool-use workflows, and productivity tasks, with a 1M-token context window and configurable reasoning effort.
- Reasoning
- Tool Calling
- Structured Output
Added Aug 28, 2026
Model weightsPricing
Auto routing · per 1M tokens- Input
- $0.751
- Output
- $2.25
- Cache read
- $0.0378
Specifications
- Context window
- 1M
- Max output
- 64K
- Parameters
- 770B / 49B
- Total / active
Benchmarks
No public benchmark scores for this model yet.
Providers
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
| $0.751 | $2.25 | $0.0378 | N/A | N/A | |
| $0.751 | $2.25 | $0.0378 | N/A | N/A | |
| $0.876 | $2.63 | $0.0441 | N/A | N/A | |
| $0.876 | $2.63 | $0.0441 | N/A | N/A | |
| $0.876 | $2.63 | $0.0441 | N/A | N/A | |
| $0.876 | $2.63 | $0.0441 | N/A | N/A | |
| $0.876 | $2.63$2.63 | $0.0441 | N/A | N/A | |
| $0.919$0.889 | $2.76$2.67 | N/A | N/A | N/A | |
| $0.90 | $2.70 | $0.045 | N/A | N/A | |
| $1.09 | $3.28 | $0.0551 | N/A | N/A |
Privacy:ZDR, prompts not retainedNo training on promptsRetention and training unclear
Batch API
Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.