Kimi-K2-Instruct vs GLM-5
Specs, VRAM requirements and download trends — updated 24 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Kimi-K2-Instruct | GLM-5 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 1,026.5 B | 753.9 B |
| Architecture | DeepseekV3ForCausalLM | GlmMoeDsaForCausalLM |
| Context length | 131,072 | 202,752 |
| Licence | other | mit |
| Commercial use | Unknown | Allowed |
| Languages | — | 2 |
| Downloads 30d | 350,413 | 1,020,783 |
| Downloads all time | 4.5 M | 2.4 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-07-11 | 2026-02-11 |
| API input price / 1M tokens | $0.57 | $1.00 |
| API output price / 1M tokens | $2.30 | $3.20 |
| Est. cost per 1M input + 1M output tokens | $2.87 | $4.20 |
| Cached input / 1M tokens | — | $0.20 |
| AA Intelligence Index | 12.7 | 27.9 |
| AA Coding Index | — | — |
| AA Agentic Index | — | — |
| Max output tokens | 98,304 | 131,072 |
| API providers | 1 | 8 |
| Tool calling | Yes | Yes |
| Reasoning mode | No | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Kimi-K2-Instruct
$2.87
GLM-5
$4.20
Kimi-K2-Instruct is 1.5× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
1.0 M157 K
Kimi-K2-Instruct
GLM-5
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Kimi-K2-Instruct · fp16 @ 128K ctx
3,596.1 GB / 24 GB
GLM-5 · fp16 @ 198K ctx
4,457.7 GB / 24 GB