Model comparison
GLM 4.5 Air (Thinking) vs GLM 4.5 (Thinking)
Compare published model capabilities and API prices.
Zai Org
GLM 4.5 Air (Thinking)
Efficient GLM model for fast reasoning, coding, and agent workflows
Zai Org
GLM 4.5 (Thinking)
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
| Metric | GLM 4.5 Air (Thinking) | GLM 4.5 (Thinking) |
|---|---|---|
| Provider | Zai Org | Zai Org |
| Context window | 128,000 | 128,000 |
| Input $/Mtok | $0.120 | $0.300 |
| Output $/Mtok | $0.800 | $1.30 |
| Modalities | text | text |
| License | closed | closed |
Quick take
On input price, GLM 4.5 Air (Thinking) is cheaper at $0.120/Mtok. For context window, GLM 4.5 Air (Thinking) leads with 128,000 tokens.
Pick based on your workload: high-volume cheap inference vs long-document / agent loops. Enterprise DNA can wire either model into Omni with evals, secrets, and job orchestration.