GLM-Legal API
Z.ai's legal model, built on GLM-5.3-Flash, for contract review, evidence analysis and compliance. API access by application for now.
Model spec
- Price
- TBASet when the API ships
Model ID
OpenAI-compatible · api.companyfabric.com/v1
Overview
About GLM-Legal
GLM-Legal is Z.ai's model for legal work, announced on 12 October 2026: contract review, evidence analysis, compliance and other real legal workflows. It is built on GLM-5.3-Flash, and Z.ai says it matches frontier models on mainstream legal benchmarks. API access is by application only for now, through Z.ai's design-partner form, with no public price or model id yet. This page tracks availability, and GLM-Legal goes live on the same CompanyFabric key the day it can be called. Until then, GLM-5.3 Flash, the model it is built on, is live here, and Muse Wonder leads Meta's own launch table on legal agent work. Every model on CompanyFabric shares the same API key, billing balance, and rate-limit envelope, one integration covers the entire library.
Facts
At a glance
Availability
Announced
API pending, this page tracks it
Pricing
TBA
Not announced by the provider yet
Capabilities
Commercial use
See license
Proprietary. API access by application only (Z.ai design partners); no public API terms or price yet.
Variants
All endpoints
GLM-5.3-Flash
$0.15/Mtok inNative multimodal coding model at the lowest rate in the catalog.
Chat Completions
GLM-5.2
$1.4/Mtok inZ.ai's open-weight frontier challenger, strong coding and reasoning with one of the best free tiers in class.
Chat Completions
GLM-5.3
$1.4/Mtok inZ.ai's flagship coding and agent model, GLM-5.2's base post-trained further, at the same price.
Chat Completions
GLM-Legal
Coming soonZ.ai's legal model, built on GLM-5.3-Flash, for contract review, evidence analysis and compliance. API access by application for now.
Chat Completions
Quickstart
How to use the GLM-Legal API
- 1
Create a free CompanyFabric account, starter credits are included, no card required.
- 2
Copy your API key from the dashboard. One key covers every model in the library.
- 3
Point any OpenAI SDK at api.companyfabric.com/v1 and set model to "z-ai/glm-legal".
- 4
Read the exact metered cost of the call from the response, the same number shown in the playground.
Use cases
What teams build with it
Agents & copilots
Drive agent loops, tool calls, and user-facing assistants over the OpenAI-compatible endpoint.
agentstool useassistants
Content pipelines
Summarization, rewriting, and structured generation at metered per-token cost.
contentsummarization
Extraction & classification
Turn unstructured input into typed JSON with schema-constrained output.
extractionjson mode
Get better output
Prompting tips
- State the output format before the task, models follow contracts declared early.
- Few-shot beats description: two worked examples outperform a paragraph of rules.
- Cap output length explicitly when cost matters; output tokens dominate most bills.
Exact, metered, prepaid
GLM-Legal pricing
Z.ai has not published a price for GLM-Legal yet. It will be billed per token like every other model here, at exactly the provider's rate, and this page will show that rate the day it is announced.
Every call is metered exactly and attributed to your key, the dashboard, the API usage response, and your invoice all read from the same ledger row. Cap any key's monthly spend with a budget cap.
| Endpoint | Type | Price |
|---|---|---|
| GLM-5.3-Flash | Chat | $0.15 / M input · $0.5 / M output |
| GLM-5.2 | Chat | $1.4 / M input · $4.4 / M output |
| GLM-5.3 | Chat | $1.4 / M input · $4.4 / M output |
| GLM-Legal | Chat | Price not announced |
GLM-Legal is not billable yet: its row shows the provider's announced price, or that none has been announced.
Comparisons
GLM-Legal vs the alternatives
GLM-Legal vs Muse Wonder
GLM-Legal and Muse Wonder compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.
Full comparison: GLM-Legal vs Muse Wonder →GLM-Legal vs Kimi K3
GLM-Legal and Kimi K3 compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.
Full comparison: GLM-Legal vs Kimi K3 →GLM-Legal vs Claude Fable 5
GLM-Legal and Claude Fable 5 compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.
Full comparison: GLM-Legal vs Claude Fable 5 →Compare
GLM-Legal head to head
FAQ
Frequently asked questions
Is there a GLM-Legal API?
Not yet, GLM-Legal is announced but API access is not public. This page tracks availability and updates the moment access ships. Until then, GLM-5.3-Flash is the closest live model and runs today with the same key.
When will the GLM-Legal API launch?
Z.ai has not committed to a public date. Create a free key now and you can call GLM-Legal on day one, no waitlist, same endpoint.
Why use GLM-Legal on CompanyFabric instead of going direct?
One key, one prepaid balance, and one rate-limit envelope across the whole library, at pricing at parity with or below the direct API. Model switching is a one-line change, and BYOK routing is 0% fee.
Is the API OpenAI-compatible?
Yes, point any OpenAI SDK at api.companyfabric.com/v1 and set model to "z-ai/glm-legal".
Can I use the output commercially?
Proprietary. API access by application only (Z.ai design partners); no public API terms or price yet.
How does billing work?
Prepaid credits via card, or BYOK with your own provider keys at 0% platform fee. No subscription required; balances never expire.
How good is GLM-Legal?
On Harvey LAB, Harvey's legal agent benchmark, Z.ai reports an all-pass rate of 19.2% for GLM-Legal, against 12.9% for Kimi K3, 11.3% for Claude Fable 5, 6.7% for GLM-5.3-Flash and 5.4% for GPT-6 Astra. All-pass means every check on a task passed, so the numbers are low across the board. These are Z.ai's numbers, not independent results.
Can I use the GLM-Legal API today?
Only if Z.ai accepts your application: API access is gated behind a consultation form for design partners and collaborators, and there is no public price yet. Z.ai's AutoClaw agent lets you try it in a browser. On CompanyFabric it goes live the day public API access opens.
How much will GLM-Legal cost?
Z.ai has not published a price. Its base model, GLM-5.3-Flash, costs $0.15 per million input tokens and $0.50 per million output tokens on CompanyFabric, but a specialised model is usually priced separately. This page will show the real price when Z.ai publishes one.
Provider
About Z.ai
Z.ai publishes the glm family. Also in this family: GLM-5.3-Flash, GLM-5.2, GLM-5.3. License: Proprietary. API access by application only (Z.ai design partners); no public API terms or price yet.
One key. Every model. Exact prices.
Get a key now and call GLM-Legal the day it ships, GLM-5.3-Flash runs today. Free starter credits included, no subscription required.