Provider key onboarding probe

Zhipu AI (GLM) | key inventory fit

Zhipu AI (GLM) key inventory fit decides whether a key can move from identification into inventory, pricing, routing, and launch. TestKey starts with 13 covered models, China route, sample models GLM 4 32B · GLM 4.5 · GLM 4.5 Air, then verifies with read-only probes.

Provider

Zhipu AI (GLM)

China route

Model coverage

13

GLM 4 32B · GLM 4.5 · GLM 4.5 Air

Probe dimension

key inventory fit

inventory-fit

Onboarding signal

13 models can become inventory candidates

zhipu

Read-only probes

2

current_key

Sample metrics

10

key_valid / requests_total / runtime_model / runtime_model_allowed

Ten capabilities

6

operational actions / model permission matrix / limit matrix

Provider onboarding summary

Provider

Zhipu AI (GLM)

Probe dimension

inventory-fit

Model coverage

13

Read-only check. Detection data burns after 5 minutes.

Why this probe matters

Zhipu AI (GLM) key inventory fit decides whether a key can move from identification into inventory, pricing, routing, and launch. TestKey starts with 13 covered models, China route, sample models GLM 4 32B · GLM 4.5 · GLM 4.5 Air, then verifies with read-only probes.

Provider: Zhipu AI (GLM)
Model coverage: 13
Probe dimension: key inventory fit

How to prove it

Read-only check. Detection data burns after 5 minutes.

Identify the real provider first, then verify key inventory fit; do not treat OpenAI-compatible as real OpenAI by default.
Use 13 covered models as candidates, then read /models, balance, error bodies, and limit headers.
13 models can become inventory candidates

Next action

Zhipu AI (GLM) key inventory fit should become an action: add provider config, fill pricing, import inventory, set route, add monitoring, or send to human review.

Read-only check. Detection data burns after 5 minutes.
Onboarding signal: 13 models can become inventory candidates
Model coverage: GLM 4 32B · GLM 4.5 · GLM 4.5 Air

Ten key capability anchors

Zhipu AI (GLM) has 2 read-only account probes configured, currently supporting operational actions / model permission matrix / limit matrix / key identity / capability matrix / continuous monitoring. These anchors feed the real TestKey detection path, not just admin display.

Read-only probes: current_key, used to prove provider identity, models, balance, or subscription state.
Sampleable metrics: key_valid / requests_total / runtime_model / runtime_model_allowed / tokens_limit / tokens_limit_day / token_type / token_role / ....
Ten-capability anchors: operational actions / model permission matrix / limit matrix / key identity / capability matrix.

Open key check

Read-only check. Detection data burns after 5 minutes.

Open providers

Zhipu AI (GLM)

Open models

GLM 4 32B · GLM 4.5 · GLM 4.5 Air