GLM-5.3-Flash vs Kimi-K2.7-Code
Specs, VRAM requirements and download trends — updated 24 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5.3-Flash | Kimi-K2.7-Code |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 321.3 B | 1,026.9 B |
| Architecture | Glm5NextForConditionalGeneration | KimiK25ForConditionalGeneration |
| Context length | 1,048,575 | 262,144 |
| Licence | mit | other |
| Commercial use | Allowed | Unknown |
| Languages | 2 | — |
| Downloads 30d | 6,319,699 | 89,102 |
| Downloads all time | 10.3 M | 2.0 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-08-25 | 2026-06-11 |
| API input price / 1M tokens | $0.15 | $0.67 |
| API output price / 1M tokens | $0.50 | $3.35 |
| Est. cost per 1M input + 1M output tokens | $0.65 | $4.02 |
| Cached input / 1M tokens | $0.03 | $0.15 |
| AA Intelligence Index | 41.8 | 25.8 |
| AA Coding Index | 71.5 | 60.8 |
| AA Agentic Index | 50.9 | 21 |
| Max output tokens | 943,717 | 235,929 |
| API providers | 34 | 11 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-5.3-Flash
$0.65
Kimi-K2.7-Code
$4.02
GLM-5.3-Flash is 6.2× cheaper at list price.
Download trend
Daily snapshots, last 56 days (30 Aug – 24 Oct)
6.6 M94 K
GLM-5.3-Flash
Kimi-K2.7-Code
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
GLM-5.3-Flash · fp16
409.9 GB / 24 GB
Kimi-K2.7-Code · fp16
809.2 GB / 24 GB