Hy3-preview vs GLM 5 Turbo
API pricing, benchmark indices and specs — updated 19 October 2026.
z-ai · B · API-only
Input / 1M
$1.20
Output / 1M
$4.00
AA index
26.6
proprietary · 202.8K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Hy3-preview | GLM 5 Turbo |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 298.8 B | n/a — API-only |
| Architecture | HYV3ForCausalLM | n/a — API-only |
| Context length | 262,144 | 202,752 |
| Licence | other | Proprietary |
| Commercial use | Unknown | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 84,611 | n/a — API-only |
| Downloads all time | 491 K | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2026-04-13 | n/a — API-only |
| API input price / 1M tokens | $0.18 | $1.20 |
| API output price / 1M tokens | $0.60 | $4.00 |
| Est. cost per 1M input + 1M output tokens | $0.78 | $5.20 |
| Cached input / 1M tokens | $0.06 | $0.24 |
| AA Intelligence Index | 25.3 | 26.6 |
| AA Coding Index | 58.8 | — |
| AA Agentic Index | 24.1 | — |
| Max output tokens | 235,929 | 131,072 |
| API providers | 1 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Hy3-preview
$0.78
GLM 5 Turbo
$5.20
Hy3-preview is 6.7× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Hy3-preview · fp16 @ 256K ctx
2,092.0 GB / 24 GB