GLM-5.3 is already live in Command Code. Same price as GLM-5.2, ~50% better on Zai's internal Code Bench. Still 5–10x cheaper than the frontier closed models (per 1M output tokens, list price today).
Plans: $1 Go ($10 credits) · $10 GOAT ($20 credits)
GLM-5.3 at a glance
Frontier coding with emergent cyber capabilities.
| Spec | GLM-5.3 |
|---|---|
| Model ID | zai-org/glm-5.3 |
| Context window | 1M tokens |
| Released | August 18, 2026 |
| Intelligence Index | 44.8 |
| Coding Index | 74.8 |
| Input | $1.40 per 1M tokens |
| Output | $4.40 per 1M tokens |
| Cache read | $0.26 per 1M tokens |
| Effective input in an agent loop | $0.60 per 1M tokens |
| Plans | Go and above |
Specs, pricing and plans are from the GLM-5.3 model page as of September 28, 2026, including any deal running that day, so they can differ from the launch pricing above. Intelligence and Coding Index scores are from Artificial Analysis.
Use GLM-5.3
1cmd --model zai-org/glm-5.3Or type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on GLM-5.3
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0074 |
| Review a 500-line PR | 60K · 4K | $0.05 |
| Fix a bug (agent loop) | 180K · 12K | $0.15 |
| Refactor a module | 320K · 20K | $0.27 |
| Full-repo agent run | 900K · 45K | $0.66 |
Try Command Code
The best coding agent for open models, in your terminal or on your desktop.
1npm i -g command-codeDesktop App · Docs · X · Discord
