GLM-4.5-Air
AI model by ZAI. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. GLM-4.5-Air is a budget-tier option from ZAI at $0.98/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, GLM-4.5-Air reports 43 tok/s output speed and 2820ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, GLM-4.5-Air costs $0.27 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
GLM-4.5-AirCurrent | $0.17 | $0.98 | 43 tok/s |
| Qwen3 Omni 30B A3B Instruct | $0.25 | $0.97 | 93 tok/s |
| Qwen3 Omni 30B A3B (Reasoning) | $0.25 | $0.97 | 99 tok/s |
| QwQ 32B | $0.66 | $1.00 | — |
| DeepSeek V3.1 Terminus (Non-reasoning) | $0.27 | $1.00 | — |
| Qwen3 235B A22B 2507 Instruct | $0.23 | $0.92 | 56 tok/s |