Compare GLM 5.2 from Z.ai and DeepSeek V4 Pro 0423 from DeepSeek on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
| Attribute | GLM 5.2 | DeepSeek V4 Pro 0423 |
|---|---|---|
| Input price | $0.006/M tokens | $0.90/M tokens |
| Output price | $6.80/M tokens | $1.50/M tokens |
| Context window | 1,048,576 tokens | 1,048,576 tokens |
| Intelligence Index | Not available | Not available |
| Coding Index | 68.8 | 58.7 |
| Agentic Index | 38.4 | Not available |
| Latency (p50) | 0.43 s | 0.81 s |
| Throughput (p50) | 127.0 tok/s | 80.0 tok/s |
| Provided by | Z.ai | DeepSeek |
| Model page | GLM 5.2 model details, providers and pricing | DeepSeek V4 Pro 0423 model details, providers and pricing |
Benchmark data updated
GLM 5.2 and DeepSeek V4 Pro 0423 trade off on price: GLM 5.2 costs $0.006/M tokens input and $6.80/M tokens output, while DeepSeek V4 Pro 0423 costs $0.90/M tokens input and $1.50/M tokens output, so GLM 5.2 is cheaper for input tokens and DeepSeek V4 Pro 0423 is cheaper for output tokens.
GLM 5.2 and DeepSeek V4 Pro 0423 have the same context window of 1,048,576 tokens.
GLM 5.2 is faster on OpenRouter, generating a median 127.0 tokens per second compared with 80.0 tokens per second for DeepSeek V4 Pro 0423.
GLM 5.2 scores higher on coding, with an Artificial Analysis Coding Index of 68.8 compared with 58.7 for DeepSeek V4 Pro 0423.