Compare DeepSeek V4 Pro 0423 from DeepSeek and Hy3 preview from tencent on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.




DeepSeek V4 Pro 0423 and Hy3 preview are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
DeepSeek V4 Pro 0423, from DeepSeek, has a 1,048,576-token context window and is priced at $0.90/M tokens input, $1.50/M tokens output on OpenRouter.
Hy3 preview, from tencent, has a 262,144-token context window and is priced at $0.18/M tokens input, $0.60/M tokens output on OpenRouter.
| Attribute | DeepSeek V4 Pro 0423 | Hy3 preview |
|---|---|---|
| Input price | $0.90/M tokens | $0.18/M tokens |
| Output price | $1.50/M tokens | $0.60/M tokens |
| Context window | 1,048,576 tokens | 262,144 tokens |
| Intelligence Index | 30.1 | 22.7 |
| Coding Index | 58.7 | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 0.91 s | 2.26 s |
| Throughput (p50) | 83.0 tok/s | 91.0 tok/s |
Benchmark data updated
Hy3 preview is cheaper than DeepSeek V4 Pro 0423 on OpenRouter: Hy3 preview costs $0.18/M tokens input and $0.60/M tokens output, while DeepSeek V4 Pro 0423 costs $0.90/M tokens input and $1.50/M tokens output.
DeepSeek V4 Pro 0423 has the longer context window at 1,048,576 tokens, compared with 262,144 tokens for Hy3 preview.
Hy3 preview is faster on OpenRouter, generating a median 91.0 tokens per second compared with 83.0 tokens per second for DeepSeek V4 Pro 0423.