GLM 4.5 Air vs GLM Latest
GLM 4.5 Air (Z.ai) and GLM Latest (Z.ai) are listed at different prices. GLM Latest costs less for input, $0.0699 per 1M tokens against $0.13; GLM 4.5 Air costs less for output, $0.85 per 1M tokens against $1.40. GLM Latest has the larger context window, 1,048,576 tokens against 131,072 for GLM 4.5 Air. Only GLM Latest supports structured outputs. Both accept text and produce text.
Z.ai: GLM 4.5 Air and Z.ai: GLM Latest both accept and produce text and support tools and reasoning. GLM Latest also supports structured outputs and response formats, and has a larger context and maximum output limit.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | GLM 4.5 Air | GLM Latest |
|---|---|---|
| Maker | Z.ai | Z.ai |
| Added to catalog | 25 Jul 2025 | 19 Aug 2026 |
| Input, per 1M tokens | $0.13 | $0.0699 |
| Output, per 1M tokens | $0.85 | $1.40 |
| Cached input read, per 1M | $0.025 | $0.0689 |
| Context windowTokens | 131,072 | 1,048,576 |
| Max outputTokens | 98,304 | 943,718 |
| Accepts | text | text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | No | Yes |
| Reasoning effort control | No | Yes |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | GLM 4.5 Air | GLM Latest |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0003 | $0.0005 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0039 | $0.0029 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0056 | $0.0049 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.021 | $0.013 |
Which to choose
Choose GLM 4.5 Air if
- Output tokens cost less: $0.85 against $1.40 per 1M
- Cached input costs less: $0.025 against $0.0689 per 1M
Choose GLM Latest if
- Input tokens cost less: $0.0699 against $0.13 per 1M
- You need the larger context window: 1,048,576 tokens against 131,072
- You need longer answers in one response: 943,718 tokens against 98,304
- You need answers in a fixed JSON schema
- You want to set how much it reasons before it answers
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.