# Z.ai: GLM 5.2 — price and measured latency by host

Updated July 25, 2026. Served by 33 providers; 8 of them measured here.

Latency and uptime are measured by llmlatency.dev probes. Prices are published by the providers and read via OpenRouter on 2026-07-25 — not measured.

| Host | Input $/M | Output $/M | Context | Fastest p50 | From | Uptime |
| --- | --- | --- | --- | --- | --- | --- |
| novita | $0.724 | $2.275 | 1,048,576 | 71 ms | us-central | 100% |
| deepinfra | $0.930 | $3.000 | 1,048,576 | 226 ms | us-central | 99.9% |
| siliconflow | $1.302 | $4.092 | 1,048,576 | 82 ms | us-central | 100% |
| glm | $1.400 | $4.400 | 1,048,576 | 349 ms | ap-tokyo | 100% |
| fireworks | $1.400 | $4.400 | 1,048,576 | 17 ms | ap-tokyo | 100% |
| friendli | $1.400 | $4.400 | 1,048,576 | 185 ms | us-central | 100% |
| together | $1.400 | $4.400 | 262,144 | 111 ms | us-central | 100% |
| baseten | $1.400 | $4.400 | 524,288 | 54 ms | us-central | 100% |

Source: https://llmlatency.dev/model/z-ai-glm-5.2 · CC BY 4.0