GLM-5.2
| Maker | Z.ai |
|---|---|
| Family | GLM |
| Released | 2026-06-13 |
| Context | 1M |
| Max output | 943.7K |
| Open weights | Open |
|---|---|
| Modalities | text → text |
| Input / 1M | $0.0341 |
| Output / 1M | $7.00 |
| Review call | $0.0178 |
| Reasoning efforts | none, high, xhigh |
|---|---|
| Hosts | OpenRouter, Cloudflare Workers AI |
| Model id | z-ai/glm-5.2 |
CodePanel's benchmark has not run GLM-5.2 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 $0.0178 on GLM-5.2 and $0.0473 on GLM-5.3 (Workers AI), so this model's call is 62% less than that one's.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| OpenRouter | z-ai/glm-5.2 | $0.0341 | $7.00 |
| Cloudflare Workers AI | @cf/zai-org/glm-5.2 | $1.40 | $4.40 |
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 | 2026-02-12 | $1.00 | $3.20 | 204.8K | – | – |
| GLM-4.7 | 2025-12-22 | $0.54 | $1.98 | 204.8K | – | – |
| Model | Maker | Input / 1M | Output / 1M | Review call | Context | Bugs caught |
|---|---|---|---|---|---|---|
| Nemotron 3 Super (Workers AI) | NVIDIA | $0.50 | $1.50 | $0.0167 | 256K | – |
| Mistral Large 3 | Mistral | $0.50 | $1.50 | $0.0167 | 262.1K | – |
| Qwen3.8 27B (Workers AI) | Qwen | $0.45 | $3.20 | $0.0195 | 262.1K | – |
| DeepSeek V4 Flash (Workers AI) | DeepSeek | $0.44 | $1.32 | $0.0147 | 1M | 49% |
Updated Oct 23, 2026