Identity confirmedModel verified
Confirmed as the official glm-5.3
Behavior matches the official glm-5.3.
Brand consistency100/100
Model match score (glm-5.3)100/100
Checks14/17 Passed
- Providers
- TokenDos
- Claimed model
- glm-5.3
- Plan
- Full check
- Reference
- 103 official models
- Requests
- 15
- Duration
- 9 分钟
01Identity check
Behaviour compared with each official referenceIndependent sample A采样 AValidIndependent sample B采样 BValidIndependent sample C采样 CInvalidReference103 official models · 2/3 Valid
Answer by answer2 answers: 2 match glm-5.3
Similarity to official modelsTop 5
- glm-5.3Claimed model>99%
- claude-sonnet-5<1%
- claude-fable-5<1%
- glm-5.3-flash<1%
- claude-opus-5<1%
02Test details
17 items · 14 passed · 3 notes · 0 failed| No. | Check | Result | Methodology |
|---|---|---|---|
| Connectivity & auth | |||
| A-01 | Endpoint reachable | Passed | The endpoint responds normally |
| A-02 | Key authentication | Passed | API key is valid and allowed to make calls |
| A-03 | Model on sale | Passed | The model list includes glm-5.3 |
| API conformance | |||
| B-01 | Basic call | Passed | Returns the expected content as instructed |
| B-02 | Response structure | Meets the spec | All OpenAI-compatible fields are present |
| B-03 | Model ID echoed back | Match | The model ID in the response matches the request |
| B-04 | Usage record | Complete and consistent | Input, output and total are all present, and the total equals the sum |
| B-05 | Output cleanliness | Nothing added | No inserted ads, watermarks or extra notes found |
| Identity check | |||
| C-01 | Independent sampling | 2 / 3 valid | Some samples could not be used for comparison |
| C-02 | Brand consistency | Match | Behavior belongs to the Zhipu GLM family; brand match score 100 |
| C-03 | Model consistency | Match | 与官方 glm-5.3 吻合，型号一致度 100 |
| C-04 | Cross-brand swap check | None found | Similarity to other brands' models totals under 1% |
| Billing & capabilities | |||
| D-01 | Cache billing | Partly works | On average 12% of repeated requests were billed at the cache price; the rest at the regular price. |
| D-02 | Context length | 32K passed | Read in full up to 32K; 128K failed: Input truncated; about 79K actually received. |
| D-03 | Streaming output | Normal | Streamed content is complete |
| D-04 | Tool use | Supported | Returns the correct function name and arguments |
| D-05 | Structured output | Supported | Returned in the required JSON structure |
Cache billing check
The same long content was sent 5 times: the 1st is billed at the regular price, and from the 2nd on the repeated part should be billed at the cache price.
Cache billing ratio12.2%
Partly works
On average 12% of repeated requests were billed at the cache price; the rest at the regular price.
Usage this run30.1KCached tokens2.9KNon-cached tokens27.1KAverage per run6.0K
Usage reportedReportedCache billingHappenedResultPartly works
Cache share by testThis is only the cache share the endpoint reported; the real discount is on the bill
Context length check
Long documents are sent tier by tier to check whether the whole document is read.
Verified up to 32K
这条线能稳定读完 32K 的内容；到 128K 就读不稳了，建议按 32K 来用。
Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths32K / 128KTested from short to long, stopping at the first failure.
- 32KRead in full · 47.4K received
- 128KInput truncated; about 79K actually received
Token usage check
Reported usage is used; estimates appear only when none is reported.
Reported usage164.9KThe actual usage reported by the API; this page goes by it.Estimated usage157.4K-302.3KEstimated from this test's requests.DeviationWithin the estimateThe reported usage is within the estimated range.Usage checkMatches the estimateFigures are as reported by the API; your bill is authoritative.
Method: independent samples from the tested endpoint are compared against reference samples collected from official channels; billing, context and capability items come from real calls. API keys, request bodies and raw model output are not stored.
This report reflects the endpoint at the time of testing.
Post an anonymous comment
Before you buy AI, check MozhenzhenScan to view reportOpen full report
Mozhenzhen verification report · Measured with real calls
glm-5.3 verification report
Identity confirmedModel verified
Confirmed as the official glm-5.3
Behavior matches the official glm-5.3.
Brand consistency100/100
Model match score (glm-5.3)100/100
Checks14/17 Passed
- Providers
- TokenDos
- Claimed model
- glm-5.3
- Plan
- Full check
- Reference
- 103 official models
- Requests
- 15
- Duration
- 9 分钟
01Identity check
Behaviour compared with each official referenceIndependent sample A采样 AValidIndependent sample B采样 BValidIndependent sample C采样 CInvalidReference103 official models · 2/3 Valid
Answer by answer2 answers: 2 match glm-5.3
Similarity to official modelsTop 5
- glm-5.3Claimed model>99%
- claude-sonnet-5<1%
- claude-fable-5<1%
- glm-5.3-flash<1%
- claude-opus-5<1%
02Test details
17 items · 14 passed · 3 notes · 0 failed| No. | Check | Result | Methodology |
|---|---|---|---|
| Connectivity & auth | |||
| A-01 | Endpoint reachable | Passed | The endpoint responds normally |
| A-02 | Key authentication | Passed | API key is valid and allowed to make calls |
| A-03 | Model on sale | Passed | The model list includes glm-5.3 |
| API conformance | |||
| B-01 | Basic call | Passed | Returns the expected content as instructed |
| B-02 | Response structure | Meets the spec | All OpenAI-compatible fields are present |
| B-03 | Model ID echoed back | Match | The model ID in the response matches the request |
| B-04 | Usage record | Complete and consistent | Input, output and total are all present, and the total equals the sum |
| B-05 | Output cleanliness | Nothing added | No inserted ads, watermarks or extra notes found |
| Identity check | |||
| C-01 | Independent sampling | 2 / 3 valid | Some samples could not be used for comparison |
| C-02 | Brand consistency | Match | Behavior belongs to the Zhipu GLM family; brand match score 100 |
| C-03 | Model consistency | Match | 与官方 glm-5.3 吻合，型号一致度 100 |
| C-04 | Cross-brand swap check | None found | Similarity to other brands' models totals under 1% |
| Billing & capabilities | |||
| D-01 | Cache billing | Partly works | On average 12% of repeated requests were billed at the cache price; the rest at the regular price. |
| D-02 | Context length | 32K passed | Read in full up to 32K; 128K failed: Input truncated; about 79K actually received. |
| D-03 | Streaming output | Normal | Streamed content is complete |
| D-04 | Tool use | Supported | Returns the correct function name and arguments |
| D-05 | Structured output | Supported | Returned in the required JSON structure |
Cache billing check
The same long content was sent 5 times: the 1st is billed at the regular price, and from the 2nd on the repeated part should be billed at the cache price.
Cache billing ratio12.2%
Partly works
On average 12% of repeated requests were billed at the cache price; the rest at the regular price.
Usage this run30.1KCached tokens2.9KNon-cached tokens27.1KAverage per run6.0K
Usage reportedReportedCache billingHappenedResultPartly works
Cache share by testThis is only the cache share the endpoint reported; the real discount is on the bill
Context length check
Long documents are sent tier by tier to check whether the whole document is read.
Verified up to 32K
这条线能稳定读完 32K 的内容；到 128K 就读不稳了，建议按 32K 来用。
Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths32K / 128KTested from short to long, stopping at the first failure.
- 32KRead in full · 47.4K received
- 128KInput truncated; about 79K actually received
Token usage check
Reported usage is used; estimates appear only when none is reported.
Reported usage164.9KThe actual usage reported by the API; this page goes by it.Estimated usage157.4K-302.3KEstimated from this test's requests.DeviationWithin the estimateThe reported usage is within the estimated range.Usage checkMatches the estimateFigures are as reported by the API; your bill is authoritative.
Method: independent samples from the tested endpoint are compared against reference samples collected from official channels; billing, context and capability items come from real calls. API keys, request bodies and raw model output are not stored.
This report reflects the endpoint at the time of testing.