Compare GPT-5.2 from OpenAI and GLM 5 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.
GPT-5.2 and GLM 5 are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
GPT-5.2, from OpenAI, has a 400,000-token context window and is priced at $1.75/M tokens input, $14/M tokens output on OpenRouter.
GLM 5, from Z.ai, has a 204,800-token context window and is priced at $0.60/M tokens input, $1.92/M tokens output on OpenRouter.
| Attribute | GPT-5.2 | GLM 5 |
|---|---|---|
| Input price | $1.75/M tokens | $0.60/M tokens |
| Output price | $14/M tokens | $1.92/M tokens |
| Context window | 400,000 tokens | 204,800 tokens |
| Intelligence Index | 30.4 | 27.9 |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 3.56 s | 1.95 s |
| Throughput (p50) | 50.0 tok/s | 57.0 tok/s |
Benchmark data updated
GLM 5 is cheaper than GPT-5.2 on OpenRouter: GLM 5 costs $0.60/M tokens input and $1.92/M tokens output, while GPT-5.2 costs $1.75/M tokens input and $14/M tokens output.
GPT-5.2 has the longer context window at 400,000 tokens, compared with 204,800 tokens for GLM 5.
GLM 5 is faster on OpenRouter, generating a median 57.0 tokens per second compared with 50.0 tokens per second for GPT-5.2.