GLM-5 vs DeepSeek-V4-Pro-0813
Specs, VRAM requirements and download trends — updated 24 October 2026.
deepseek-ai · B · Open weights
Params
1,650.5 B
Context
1,048,576
30d
150 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5 | DeepSeek-V4-Pro-0813 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 753.9 B | 1,650.5 B |
| Architecture | GlmMoeDsaForCausalLM | DeepseekV4ForCausalLM |
| Context length | 202,752 | 1,048,576 |
| Licence | mit | mit |
| Commercial use | Allowed | Allowed |
| Languages | 2 | — |
| Downloads 30d | 1,020,783 | 150,373 |
| Downloads all time | 2.4 M | 380 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-11 | 2026-08-13 |
| API input price / 1M tokens | $1.00 | $0.66 |
| API output price / 1M tokens | $3.20 | $1.98 |
| Est. cost per 1M input + 1M output tokens | $4.20 | $2.64 |
| Cached input / 1M tokens | $0.20 | $0.022 |
| AA Intelligence Index | 27.9 | 36 |
| AA Coding Index | — | 68.8 |
| AA Agentic Index | — | 41.3 |
| Max output tokens | 131,072 | 393,216 |
| API providers | 8 | 21 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-5
$4.20
DeepSeek-V4-Pro-0813
$2.64
DeepSeek-V4-Pro-0813 is 1.6× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
1.0 M150 K
GLM-5
DeepSeek-V4-Pro-0813
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
GLM-5 · fp16 @ 198K ctx
4,457.7 GB / 24 GB
DeepSeek-V4-Pro-0813 · fp16 @ 1024K ctx
32,672.1 GB / 24 GB