Z.ai: GLM 4.5 Air
z-ai/glm-4.5-air
Cheapest provider
$0.13 / 1M
Io Net
Fastest provider (p95)
56 tok/s
SiliconFlow
Intelligence (estimated)
68.5
Family + generation + popularity + price tier
Per-provider performance
Latency / throughput / uptime / price measured across providers over the last 30 minutes of live traffic. This is what proves “sourced cheapest” — Atlas mode draws on these per call to serve the cheapest path that holds quality.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| Io Net | q8· fp8 | $0.1250 | $0.8500 | 719ms / 2863ms | 18 / 37 tok/s | 99.76% | 93.1% |
| Novita | full· bf16 | $0.1300 | $0.8500 | 918ms / 7548ms | 23 / 37 tok/s | 100.00% | 97.2% |
| SiliconFlow | q8· fp8 | $0.1400 | $0.8600 | 2303ms / 14401ms | 18 / 56 tok/s | 98.52% | 98.5% |
| Z.AI | q8· fp8 | $0.2000 | $1.1000 | 3351ms / 11555ms | 25 / 39 tok/s | 99.98% | 99.8% |
“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).
Intelligence estimate
No public benchmark numbers indexed for this model yet, so the leaderboard score is derived from the catalogue data we sync: model family standing, generation, and live usage rank — applied identically to open- and closed-weight models. The heuristic ceiling sits below confirmed-benchmark frontier models so curated rankings stay clearly on top.
- ·glm air family base
- ·v4.5 generation +3
Want a curated score? File a benchmark report and we’ll add it to the next sync.
How Atlas mode sources Z.ai: GLM 4.5 Air
- Strict mode — pin Z.ai: GLM 4.5 Air exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently Io Net at $0.13/1M.
- Atlas mode — the default. Each call is auto-optimized for the cheapest path that holds quality, at least 5% off going direct from call one and climbing as it ramps. You always see which model served the call and exactly what you saved — thumbs-down anything you don’t like for a full refund.