AI Agent StoreZ.ai · Provider API ID verified
GLM 5.3 FlashX Legal
A specialized option for legal research and document workflows in English and Chinese. Check its answers against the underlying documents before relying on them.
First reviewed 2026-10-23 · Checked 2026-11-03. The launch date has not been confirmed.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact provider API ID: glm-5.3-flashx-legal. The guide requires thinking to stay on and recommends max effort. It does not say which setting applies if you leave it out.
The native guide no longer limits access to selected enterprise applicants. OpenRouter and Gateway now list this exact Legal variant; use the ID and limits of your chosen service. Downloadable Legal weights and independent legal-task results remain unverified.
The shared Flash/FlashX guide lists 1M context and 128K maximum output. The catalog identifies Legal as a specialized model, not a new measurement of the general Flash model.
OpenRouter declares 1,048,576 context and 131,072 output, with mandatory thinking and max default. Gateway separately declares 1,000,000/131,072 and low/high/max controls without a default. These do not replace native 1M/128K documentation. Inspect the separate OpenRouter offer ↗
Native prices per million tokens: $0.37 input, $0.075 cached input and $1.25 output. Cache storage is currently marked limited-time free. Allow for retries and any tool fees. Models that think before answering may also charge for that work.
Provider release and specifications ↗
Check availability and plans ↗
More setup and licensing details ↗
More setup and licensing details ↗
More setup and licensing details ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗