GLM-4.5-Air vs Mistral-Small-4-119B-2603
Specs, VRAM requirements and download trends — updated 24 October 2026.
mistralai · B · Open weights
Params
119.4 B
Context
—
30d
69 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-4.5-Air | Mistral-Small-4-119B-2603 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 110.5 B | 119.4 B |
| Architecture | Glm4MoeForCausalLM | Mistral3ForConditionalGeneration |
| Context length | 131,072 | 262,144 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 2 | 24 |
| Downloads 30d | 850,129 | 68,887 |
| Downloads all time | 5.5 M | 698 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-07-20 | 2026-01-23 |
| API input price / 1M tokens | $0.13 | $0.15 |
| API output price / 1M tokens | $0.85 | $0.60 |
| Est. cost per 1M input + 1M output tokens | $0.98 | $0.75 |
| Cached input / 1M tokens | $0.025 | $0.015 |
| AA Intelligence Index | 11.1 | 11.3 |
| AA Coding Index | — | 26.6 |
| AA Agentic Index | — | 0.8 |
| Max output tokens | 98,304 | 209,715 |
| API providers | 3 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-4.5-Air
$0.98
Mistral-Small-4-119B-2603
$0.75
Mistral-Small-4-119B-2603 is 1.3× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
850 K70 K
GLM-4.5-Air
Mistral-Small-4-119B-2603
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Mistral-Small-4-119B-2603 · fp16
284.4 GB / 24 GB
GLM-4.5-Air · fp16 @ 128K ctx
508.7 GB / 24 GB