Strengths
- Z.ai cites a score of 57 on the Artificial Analysis Intelligence Index, yet it costs only $0.15 input and $0.50 output per million tokens.
- It accepts text, images and video and handles a one-million-token context.
- Through Mistral AI's API, with data in the EU, it costs the same as directly from Z.ai.
- In the GLM Coding Plan it uses only a third of the quota that GLM-5.3 does.
Weaknesses
- Thinking cannot be turned off, so even a simple answer is not instant.
- At max effort it trails Claude Opus 4.8 slightly on Z.ai Code Bench (29.0 vs 29.5).
- The MIT license is stated by Mistral, while Z.ai's model page does not mention it.
Best for
- cheap agents that work with images and video
- lots of coding help for little money
- a budget model with EU data hosting via Mistral
Not ideal for
- tasks that need an instant answer without thinking
How to use it in Europe
Through the Z.ai API or the GLM Coding Plan subscription. EU companies can use it through Mistral AI's API (model zai-glm-5-3-flash, available since 22 October 2026), where data is stored in the EU by default. With Z.ai, check its terms for where your data is processed. The weights are open, so you can also run the model on your own server.
Price compared with similar models
Benchmark results
| Benchmark | Score | Source |
|---|---|---|
| Artificial Analysis Intelligence Index v4.1.1 (cited by Z.ai) | 57 | docs.z.ai ↗, August 2026 |
| DeepSWE v1.1 | 63.4 | docs.z.ai ↗ (vendor-reported), August 2026 |
| AutomationBench | 48.8 | docs.z.ai ↗ (vendor-reported), August 2026 |
Benchmarks cover only a narrow slice of ability and vendors often report them at their best settings. Treat them as a rough guide.
More models from this vendor
- GLM-5.3: Z.ai's open model for agentic coding, also offered through Mistral's European API with data kept in the EU.
Similar models from other vendors
- Claude Haiku 5.5 (Anthropic): Claude's cheapest and fastest model, built for classification, data extraction and large volumes of simple tasks.
- DeepSeek V4.1 Flash (DeepSeek): DeepSeek's cheap, fast open-weight model with a 1 million token window. In the app and API, though, your data goes to China.
- Gemini 3.5 Flash-Lite (Google): A very fast, low-cost Google model for large volumes of simple tasks, such as pulling data out of documents.
- Mistral Small 4 (Mistral AI): Mistral's cheap, fast open model under Apache 2.0 for everyday tasks through the API or on your own server.
- GPT-6.1 Terra (OpenAI): OpenAI's fast, cheaper model for working with images, operating a computer and everyday office work.
- Qwen3.8-Flash (Alibaba (Qwen)): A very cheap, fast Qwen model for high volumes of tasks. Unlike Max and Plus, it runs in Frankfurt with processing kept in the EU.