GLM-5.3-Flash vs Inkling
Specs, VRAM requirements and download trends — updated 23 October 2026.
thinkingmachines · B · Open weights
Params
952.4 B
Context
—
30d
1.4 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-5.3-Flash | Inkling |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 321.3 B | 952.4 B |
| Architecture | Glm5NextForConditionalGeneration | InklingForConditionalGeneration |
| Context length | 1,048,576 | 524,288 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 2 | — |
| Downloads 30d | 6,421,899 | 1,383,288 |
| Downloads all time | 10.2 M | 1.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-08-25 | 2026-07-14 |
| API input price / 1M tokens | $0.0052 | $1.00 |
| API output price / 1M tokens | $0.20 | $4.05 |
| Est. cost per 1M input + 1M output tokens | $0.20 | $5.05 |
| Cached input / 1M tokens | $0.0052 | $0.17 |
| AA Intelligence Index | 41.8 | 25 |
| AA Coding Index | 71.5 | 52.1 |
| AA Agentic Index | 50.9 | 22.5 |
| Max output tokens | 943,718 | 471,859 |
| API providers | 32 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-5.3-Flash
$0.20
Inkling
$5.05
GLM-5.3-Flash is 24.8× cheaper at list price.
Download trend
Daily snapshots, last 55 days (30 Aug – 23 Oct)
6.6 M190 K
GLM-5.3-Flash
Inkling
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
GLM-5.3-Flash · fp16
409.9 GB / 24 GB
Inkling · fp16
2,238.6 GB / 24 GB