GLM-5
| Maker | Z.ai |
|---|---|
| Family | GLM |
| Released | 2026-02-12 |
| Context | 204.8K |
| Max output | 131.1K |
|---|---|
| Open weights | Open |
| Modalities | text → text |
| Input / 1M | $1.00 |
| Output / 1M | $3.20 |
|---|---|
| Review call | $0.0339 |
| Hosts | OpenRouter |
| Model id | z-ai/glm-5 |
CodePanel's benchmark has not run GLM-5 as a pull-request reviewer yet, so this page has no recall, false-alarm or measured-cost figures for it. The methodology explains how ranked models are scored.
The newest ranked model in the GLM line is GLM-5.3 (Workers AI). It caught 61% [50%–72%] of the known bugs at rank 3 of 17, with a measured review cost of $0.0311. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0339 on GLM-5 and $0.0473 on GLM-5.3 (Workers AI), so this model's call is 28% less than that one's.
A newer GLM model is current: GLM-5.2.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| OpenRouter | z-ai/glm-5 | $1.00 | $3.20 |
Source: models.dev's OpenRouter listing, Oct 23, 2026
| Version | Released | Input / 1M | Output / 1M | Context | Rank | Bugs caught |
|---|---|---|---|---|---|---|
| GLM-5.3 (Workers AI) | 2026-08-18 | $1.40 | $4.40 | 1M | #3 | 61% |
| GLM-5.2 | 2026-06-13 | $0.0341 | $7.00 | 1M | – | – |
| GLM-4.7 | 2025-12-22 | $0.54 | $1.98 | 204.8K | – | – |
| Model | Maker | Input / 1M | Output / 1M | Review call | Context |
|---|---|---|---|---|---|
| Kimi K2.6 | Moonshot | $0.95 | $4.00 | $0.0346 | 262.1K |
| Step 5 Preview (OpenRouter) | StepFun | $1.00 | $2.70 | $0.0327 | 1M |
| Inkling | Thinking Machines | $1.00 | $4.05 | $0.036 | 524.3K |
| Grok Build 0.1 | xAI | $1.00 | $2.00 | $0.031 | 256K |
Updated Oct 23, 2026