GLM-5 vs DeepSeek-V3.1-Terminus
Specs, VRAM requirements and download trends — updated 24 October 2026.
deepseek-ai · B · Open weights
Params
684.5 B
Context
163,840
30d
13 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5 | DeepSeek-V3.1-Terminus |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 753.9 B | 684.5 B |
| Architecture | GlmMoeDsaForCausalLM | DeepseekV3ForCausalLM |
| Context length | 202,752 | 163,840 |
| Licence | mit | mit |
| Commercial use | Allowed | Allowed |
| Languages | 2 | — |
| Downloads 30d | 1,020,783 | 13,067 |
| Downloads all time | 2.4 M | 272 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-11 | 2025-09-22 |
| API input price / 1M tokens | $1.00 | $0.27 |
| API output price / 1M tokens | $3.20 | $1.00 |
| Est. cost per 1M input + 1M output tokens | $4.20 | $1.27 |
| Cached input / 1M tokens | $0.20 | — |
| AA Intelligence Index | 27.9 | 14.8 |
| AA Coding Index | — | 43.5 |
| AA Agentic Index | — | 6.8 |
| Max output tokens | 131,072 | 147,456 |
| API providers | 8 | 2 |
| 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-V3.1-Terminus
$1.27
DeepSeek-V3.1-Terminus is 3.3× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
1.0 M14 K
GLM-5
DeepSeek-V3.1-Terminus
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
DeepSeek-V3.1-Terminus · fp16 @ 160K ctx
2,811.5 GB / 24 GB
GLM-5 · fp16 @ 198K ctx
4,457.7 GB / 24 GB