Side-by-side comparison
GLM 4.5 Air vs Hy3 preview
| GLM 4.5 Air | Hy3 preview | |
|---|---|---|
| Provider | Z.ai | Tencent |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 131,072 | 262,144 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | tools | tools |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.1300 | 0.0660 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 0.8500 | 0.2600 |
Frequently asked questions
Which is cheaper, GLM 4.5 Air or Hy3 preview?
Hy3 preview is cheaper than GLM 4.5 Air on a 50/50 input/output blend by about $0.327 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, GLM 4.5 Air or Hy3 preview?
Hy3 preview has the larger context window at 262k tokens versus 131k tokens for GLM 4.5 Air. That means Hy3 preview can ingest about 2.0x as much text per request.
What is the difference between GLM 4.5 Air and Hy3 preview?
GLM 4.5 Air comes from Z.ai; Hy3 preview comes from Tencent. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.