Z.ai GLM-5.3-FlashX-Legal: Pricing, Specs and Limits
Z.ai GLM-5.3-FlashX-Legal: legal-domain variant of GLM-5.3-FlashX, 1M context, 0.37 in / 1.25 out per 1M tokens. Specs, limits and test prompts.
By ShilpBot Team · Published · 3 min read
GLM-5.3-FlashX-Legal is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image and video and produces text. The listing says it adds legal-domain mid-training and post-training with reinforcement learning.
A domain-tuned model can read legal vocabulary more reliably than a general one, but it is still an AI model. Its output is not legal advice and should be reviewed by a qualified lawyer.
Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.
Z.ai GLM-5.3-FlashX-Legal quick facts
| Detail | Value |
|---|---|
| Developer | Z.ai |
| Model ID | z-ai/glm-5.3-flashx-legal |
| Added to the catalogue | 2026-11-02 |
| Type | Legal-domain variant of GLM-5.3-FlashX |
| Parameters | Not listed |
| Context window | about 1M tokens (1,048,576) |
| Maximum output | 131,072 tokens |
| Input types | text, image, video |
| Price | 0.37 in / 1.25 out per 1M tokens (cached input 0.075) |
Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.
What Z.ai GLM-5.3-FlashX-Legal is good for
- First-pass review and summarisation of contracts and legal documents.
- Extracting clauses, parties, dates and obligations into tables.
- Scanned documents, since image input is listed.
Limits of Z.ai GLM-5.3-FlashX-Legal
- Never rely on it for legal decisions. Have a qualified lawyer verify anything important.
- Laws differ by country and change over time, and the listing does not say which jurisdictions it covers.
- Do not upload privileged or confidential documents to a service you have not reviewed.
How Z.ai GLM-5.3-FlashX-Legal compares
- Mistral Large 4: Both have a 1,048,576-token context window; its output cap is 131,072 tokens against 262,144; it also accepts video input; it costs 0.37 input and 1.25 output per million tokens against 0.70 and 2.10.
- Cohere Command A+: It has a larger context window (1,048,576 against 192,000 tokens); its output cap is 131,072 tokens against 64,000; it also accepts video input; it costs 0.37 input and 1.25 output per million tokens against 0.30 and 1.50.
- Qwen4 Max: It has a larger context window (1,048,576 against 1,000,000 tokens); both cap output at 131,072 tokens; it costs 0.37 input and 1.25 output per million tokens against 1.50 and 4.50.
Calling Z.ai GLM-5.3-FlashX-Legal from code
Use the model ID z-ai/glm-5.3-flashx-legal with any OpenAI-compatible client pointed at OpenRouter:
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "z-ai/glm-5.3-flashx-legal", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'Prompts that show what Z.ai GLM-5.3-FlashX-Legal can do
- Give it a sample rental agreement and ask for a table of the tenant's obligations with clause numbers.
- Ask it to spot unusual clauses in a standard NDA and explain why they are unusual.
- Check every citation or clause reference it gives against the source.
What Z.ai GLM-5.3-FlashX-Legal costs
The catalogue lists 0.37 per million input tokens and 1.25 per million output tokens, with cached input at 0.075 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 0.49. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.068 before caching. If your client reuses the same prompt prefix, cached input at 0.075 per million tokens can cut the input side of that bill by about 80 percent. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.
Keep reading
Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.
Frequently asked questions
Is GLM-5.3-FlashX-Legal legal advice?
No. It is an AI tool that can help read and summarise documents. Decisions with legal consequences need a qualified human lawyer.
What are the cost and limits of Z.ai GLM-5.3-FlashX-Legal?
As of 2026-11-16 the catalogue lists 0.37 per million input tokens and 1.25 per million output tokens. About 1M tokens (1,048,576) context window, up to 131,072 output tokens, model ID z-ai/glm-5.3-flashx-legal. Prices can change, so check the live model page.
