GLM-5.2 vs Kimi-K2.5
Specs, VRAM requirements and download trends — updated 14 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5.2 | Kimi-K2.5 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 753.3 B | 1,026.4 B |
| Architecture | GlmMoeDsaForCausalLM | KimiK25ForConditionalGeneration |
| Context length | 1,048,576 | — |
| Licence | mit | other |
| Commercial use | Allowed | Unknown |
| Languages | 2 | — |
| Downloads 30d | 320,374 | 166,174 |
| Downloads all time | 5.1 M | 6.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-06-16 | 2026-01-27 |
| API input price / 1M tokens | $0.006 | not on OpenRouter |
| API output price / 1M tokens | $6.80 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $6.81 | not on OpenRouter |
| Cached input / 1M tokens | $0.005 | not on OpenRouter |
| AA Intelligence Index | — | not on OpenRouter |
| AA Coding Index | 68.8 | not on OpenRouter |
| AA Agentic Index | 38.4 | not on OpenRouter |
| Max output tokens | 943,718 | not on OpenRouter |
| API providers | 24 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | Yes | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-5.2
$6.81
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.8 M166 K
GLM-5.2
Kimi-K2.5
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Kimi-K2.5 · fp16
877.8 GB / 24 GB
GLM-5.2 · fp16 @ 1024K ctx
16,121.8 GB / 24 GB