GLM-5.2 by Z.ai is a 744B open-weight (MIT) mixture-of-experts coding model with a 1M-token context, IndexShare sparse attention, and selectable thinking-effort levels.
Available on
Privacy
- ZDR
- Training
- No
- Region
- Multi, US, EU
JetBrains AI Assistant brings AI chat, code generation, and agents into IntelliJ IDEA, PyCharm, WebStorm, and the rest of the JetBrains IDEs. Its bring-your-own-key support takes OpenAI-compatible custom endpoints with your own API key, no JetBrains AI subscription required. Point it at Opper's gateway and your IDE runs on any of 700+ models with one key and a choice of region.
Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
GLM-5.2 runs on the routes below. Route only to EU providers when your data has to stay in Europe.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| evroc | EU | No | $1.40 | $5.61 | |
| GreenPT | EU | No | $1.23 | $4.94 | |
| Inceptron | EU | No | $1.01 | $3.18 | |
| Mistral | EU | No | $1.40 | $4.40 | |
| Scaleway | EU | No | $2.02 | $6.17 | |
| TensorX | EU | No | $1.50 | $4.50 | |
| DeepInfra | US | No | $0.75 | $2.40 | |
| DigitalOcean | US | No | $0.70 | $2.20 | |
| Morph | US | No | $1.10 | $4.10 | |
| Novita | US | No | $1.40 | $4.40 | |
| Alibaba Cloud | Multi | No | $1.19 | $4.18 | |
| Baidu Qianfan | Multi | —Not established | — | $1.40 | $4.40 |
| BytePlus | Multi | No | $1.40 | $4.40 | |
| Nebius | Multi | No | $1.40 | $4.40 | |
| Tencent Cloud | Multi | No | $1.40 | $4.40 | |
| Z.ai | Multi | No | $1.40 | $4.40 |
GLM-5.2 by Z.ai is a 744B open-weight (MIT) mixture-of-experts coding model with a 1M-token context, IndexShare sparse attention, and selectable thinking-effort levels.
Point Cursor's OpenAI base URL at Opper to run it on any of 700+ models.
OpenAI-compatibleCline's OpenAI-Compatible provider points straight at Opper's gateway.
OpenAI-compatibleAdd Opper as an OpenAI provider in config.yaml and Continue's chat, edit and autocomplete run on any model.
OpenAI-compatible