GLM-5.3 vs DeepSeek-R1-0528
Specs, VRAM requirements and download trends — updated 10 November 2026.
deepseek-ai · B · Open weights
Params
684.5 B
Context
163,840
30d
164 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5.3 | DeepSeek-R1-0528 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 753.3 B | 684.5 B |
| Architecture | GlmMoeDsaForCausalLM | DeepseekV3ForCausalLM |
| Context length | 1,048,576 | 163,840 |
| Licence | other | mit |
| Commercial use | Unknown | Allowed |
| Languages | 2 | — |
| Downloads 30d | 2,016,722 | 163,888 |
| Downloads all time | 4.3 M | 17.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-08-25 | 2025-05-28 |
| API input price / 1M tokens | $0.07 | $0.50 |
| API output price / 1M tokens | $1.40 | $2.15 |
| Est. cost per 1M input + 1M output tokens | $1.47 | $2.65 |
| Cached input / 1M tokens | $0.069 | $0.35 |
| AA Intelligence Index | 31.7 | — |
| AA Coding Index | 74.8 | — |
| AA Agentic Index | 53.1 | — |
| Max output tokens | 943,718 | 32,768 |
| API providers | 36 | 3 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-5.3
$1.47
DeepSeek-R1-0528
$2.65
GLM-5.3 is 1.8× cheaper at list price.
Download trend
Daily snapshots, last 67 days (5 Sep – 10 Nov)
2.5 M158 K
GLM-5.3
DeepSeek-R1-0528
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
DeepSeek-R1-0528 · fp16 @ 160K ctx
2,811.5 GB / 24 GB
GLM-5.3 · fp16 @ 1024K ctx
15,295.6 GB / 24 GB