GLM-4.5-Air vs c4ai-command-a-03-2025
Specs, VRAM requirements and download trends — updated 24 October 2026.
CohereLabs · B · Open weights
Params
111.1 B
Context
—
30d
1 K
cc-by-nc-4.0 · non-commercial
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-4.5-Air | c4ai-command-a-03-2025 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 110.5 B | 111.1 B |
| Architecture | Glm4MoeForCausalLM | Cohere2ForCausalLM |
| Context length | 131,072 | 256,000 |
| Licence | mit | cc-by-nc-4.0 |
| Commercial use | Allowed | Not allowed |
| Languages | 2 | 23 |
| Downloads 30d | 850,129 | 1,494 |
| Downloads all time | 5.5 M | 126 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2025-07-20 | 2025-03-11 |
| API input price / 1M tokens | $0.13 | $2.50 |
| API output price / 1M tokens | $0.85 | $10.00 |
| Est. cost per 1M input + 1M output tokens | $0.98 | $12.50 |
| Cached input / 1M tokens | $0.025 | — |
| AA Intelligence Index | 11.1 | 13.1 |
| AA Coding Index | — | 27.8 |
| AA Agentic Index | — | 1 |
| Max output tokens | 98,304 | 8,192 |
| API providers | 3 | 1 |
| Tool calling | Yes | No |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-4.5-Air
$0.98
c4ai-command-a-03-2025
$12.50
GLM-4.5-Air is 12.8× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
850 K2 K
GLM-4.5-Air
c4ai-command-a-03-2025
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
c4ai-command-a-03-2025 · fp16
261.5 GB / 24 GB
GLM-4.5-Air · fp16 @ 128K ctx
508.7 GB / 24 GB