# Z.ai: GLM 5.3 Flash — price and measured latency by host

Updated September 04, 2026. Served by 23 providers; 9 of them measured here.

Latency and uptime are measured by llmlatency.dev probes. Prices are published by the providers and read via OpenRouter on 2026-09-04 — not measured.

| Host | Input $/M | Output $/M | Context | Fastest p50 | From | Uptime |
| --- | --- | --- | --- | --- | --- | --- |
| novita | $0.075 | $0.250 | 1,048,576 | 74 ms | us-central | 100% |
| deepinfra | $0.075 | $0.250 | 1,048,576 | 264 ms | us-central | 99.9% |
| glm | $0.075 | $0.250 | 1,048,576 | 92 ms | ap-tokyo | 100% |
| fireworks | $0.150 | $0.500 | 1,048,576 | 20 ms | ap-tokyo | 100% |
| friendli | $0.150 | $0.500 | 1,048,576 | 222 ms | us-central | 99.6% |
| siliconflow | $0.150 | $0.500 | 1,048,576 | 83 ms | us-central | 100% |
| together | $0.150 | $0.500 | 1,048,575 | 122 ms | us-central | 100% |
| reka | $0.150 | $0.500 | 262,144 | 99 ms | us-central | 100% |
| baseten | $0.150 | $0.500 | 1,048,576 | 61 ms | us-central | 100% |

Source: https://llmlatency.dev/model/z-ai-glm-5.3-flash · CC BY 4.0