Compare
 GLM 5.3 FlashZ.ai | |
|---|---|
| Best input | $0.075 /MTok |
| Best output | $0.25 /MTok |
| Batch in / out | — |
| Cache read | $0.015 |
| Measured TTFT | — |
| Measured TPS | — |
| Context | 1.31M |
| Max output | 131K |
| Modalities in | image, text, video |
| Tool calling | ✓ |
| Structured output | ✓ |
| Reasoning | ✓ |
| Vision | ✓ |
| Audio input | — |
| Prompt caching | ✓ |
| Providers | 10 |
| Cheapest provider | Z.AI |
| License | Open weights |
| Released | Aug 26, 2026 |
| Cost at your workload | — |
● = best of the compared models · TTFT/TPS: fastest measured endpoint per model (P50, trailing 72h, chat10k) · ° = via OpenRouter routing · ✕ = probed, no measurable stream · prices are standard tier