GLM-5.3-Flash by Z.ai is a natively multimodal 320B MoE with 18B active parameters, hybrid sparse and linear attention, a 1M-token context, and MIT open weights for coding and agent work.
Available on
Privacy
- ZDR
- Training
- No
- Region
- EU, US, Multi
Copilot for Obsidian puts an AI assistant inside your Obsidian vault: chat with your notes, generate and rewrite content, and query your whole knowledge base without leaving the app. It is open source, its bring-your-own-key setup needs no Copilot license, and Opper is one of the providers in its catalogue: pick Opper, paste your key, and your vault runs on any of 700+ models, with your notes going only to the model you chose.
Obsidian → Settings → Copilot → BYOK → Add a provider, search for Opper — the base URL comes prefilled, then paste your Opper key. Then pick GLM-5.3-Flash.
GLM-5.3-Flash 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 |
|---|---|---|---|---|---|
| Berget | EU | No | $0.29 | $0.57 | |
| GreenPT | EU | No | $0.13 | $0.50 | |
| Inceptron | EU | No | $0.15 | $0.50 | |
| Nextbit | EU | No | $0.15 | $0.50 | |
| Sference | EU | No | $0.20 | $0.60 | |
| TensorX | EU | No | $0.20 | $0.50 | |
| DeepInfra | US | No | $0.15 | $0.50 | |
| DigitalOcean | US | No | $0.15 | $0.50 | |
| Morph | US | No | $0.10 | $0.35 | |
| Novita | US | No | $0.15 | $0.50 | |
| Perplexity | US | No | $0.15 | $0.50 | |
| Wafer | US | No | $0.10 | $0.35 | |
| Modal | Multi | No (opt-in) | $0.45 | $1.50 | |
| Nebius | Multi | No | $0.15 | $0.50 | |
| Z.ai | Multi | No | $0.15 | $0.50 |
GLM-5.3-Flash by Z.ai is a natively multimodal 320B MoE with 18B active parameters, hybrid sparse and linear attention, a 1M-token context, and MIT open weights for coding and agent work.
Anthropic's desktop agent for knowledge work. Run it on any model on Opper, not just Claude.
Anthropic-compatibleAn open-source personal agent for everyday tasks. Run it on any model on Opper.
opper launch openclawNous Research's open agent. Run it on any model on Opper.
opper launch hermes