Compare DeepSeek V3.1 Base from DeepSeek and GLM 4 32B from Z.ai on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.


DeepSeek V3.1 Base and GLM 4 32B are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
DeepSeek V3.1 Base, from DeepSeek, has a 163,840-token context window and is priced by the provider serving it on OpenRouter.
GLM 4 32B , from Z.ai, has a 128,000-token context window and is priced by the provider serving it on OpenRouter.
| Attribute | DeepSeek V3.1 Base | GLM 4 32B |
|---|---|---|
| Input price | Pricing varies by provider | Pricing varies by provider |
| Output price | Pricing varies by provider | Pricing varies by provider |
| Context window | 163,840 tokens | 128,000 tokens |
| Intelligence Index | Not available | Not available |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | Not available | Not available |
| Throughput (p50) | Not available | Not available |
DeepSeek V3.1 Base has the longer context window at 163,840 tokens, compared with 128,000 tokens for GLM 4 32B .