GLM 4.5 Air vs GLM 5.3 Flash
Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.
| Detail | GLM 4.5 Airzai/glm-4.5-air | GLM 5.3 Flashzai/glm-5.3-flash |
|---|---|---|
| Maker | zai | zai |
| Kind | Chat | Chat |
| Input per 1M tokens | $0.21 | $0.1575 Lower |
| Cached input per 1M tokens | $0.0315 | $0.0315 |
| Cache write per 1M tokens | Same as input | Same as input |
| Output per 1M tokens | $1.155 | $0.525 Lower |
| Context window | 128,000 tokens | 1,000,000 tokens Larger |
| Max output | 96,000 tokens | 131,000 tokens Larger |
| Capabilities | Reasoning, tool use | Reasoning, tool use, vision |
| Takes | Text | Text, image |
| Returns | Text | Text |
| Zero data retention | Not on every provider | Not on every provider |
| No training on requests | Not on every provider | Not on every provider |
| Released | 2025-07-28 | 2026-08-26 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | GLM 4.5 Air | GLM 5.3 Flash |
|---|---|---|
| 1,000 tokens in, 200 out | $0.000441 | $0.000263 |
| 10,000 tokens in, 1,000 out | $0.003255 | $0.0021 |
| 100,000 tokens in, 4,000 out | $0.02562 | $0.01785 |