GLM-5.2 vs GLM-5.3
Specs, VRAM requirements and download trends — updated 10 November 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5.2 | GLM-5.3 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 753.3 B | 753.3 B |
| Architecture | GlmMoeDsaForCausalLM | GlmMoeDsaForCausalLM |
| Context length | 1,048,576 | 1,048,576 |
| Licence | mit | other |
| Commercial use | Allowed | Unknown |
| Languages | 2 | 2 |
| Downloads 30d | 320,374 | 2,016,722 |
| Downloads all time | 5.1 M | 4.3 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-06-16 | 2026-08-25 |
| API input price / 1M tokens | $0.006 | $0.07 |
| API output price / 1M tokens | $6.80 | $1.40 |
| Est. cost per 1M input + 1M output tokens | $6.81 | $1.47 |
| Cached input / 1M tokens | $0.005 | $0.069 |
| AA Intelligence Index | — | 31.7 |
| AA Coding Index | 68.8 | 74.8 |
| AA Agentic Index | 38.4 | 53.1 |
| Max output tokens | 943,718 | 943,718 |
| API providers | 24 | 36 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-5.2
$6.81
GLM-5.3
$1.47
GLM-5.3 is 4.6× cheaper at list price.
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.8 M263 K
GLM-5.2
GLM-5.3
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
GLM-5.3 · fp16 @ 1024K ctx
15,295.6 GB / 24 GB
GLM-5.2 · fp16 @ 1024K ctx
16,121.8 GB / 24 GB