Verification report details

Is gpt-5.4 genuine? Deep check result

Report ID MZZR20260809191934E9EDF7Generated at 2026/08/10 03:19

High risk

gpt-5.4 本次深度验真结果：High risk（41/100）。主要问题：接口根本调不通；有检测项没Passed。

41Model consistency score

主要问题：接口根本调不通；有检测项没Passed。

Tested byMozhenzhen
Tested modelGPT-5.4
ProvidersAPI 节点 B003A646
Requests5
Duration1 sec
Identity verdictNot verified
Reference模真真既有版本化基线

This call did not complete

Reason for failure

The basic call returned no recognizable answer. The available records cannot establish a specific cause.

What to do

Check the endpoint address, key and model permissions. If this persists, give the provider the report ID for troubleshooting.

Token usage check

Reported usage is used; estimates appear only when none is reported.

Estimated usage1.7MThe API did not report actual usage; the estimate is shown.DeviationNoneThe API did not report actual usage; only the estimate is shown.Usage checkEstimate onlyFigures are as reported by the API; your bill is authoritative.
Token cache usage test

Several runs in a row to see whether repeated content is billed at the cheaper cache rate; 0% means no cache discount this time.

Total 0 request
Share billed at the cache rate--
No usage record

This provider's endpoint does not report usage reliably; check it against your bill.

Usage this run0Cached tokens0Non-cached tokens0Average per run--
Usage reportedNot reportedCache billingDid not happenResultNormal
Cache share by testThis is only the cache share the endpoint reported; the real discount is on the bill

No per-test records are available; only the aggregate result is shown.

Long-context test

We test how much it can read at once, then compare that with the officially stated length.

7 tiers
No stable result this time

The basic call failed (Basic API call unavailable), so the long-context add-on was skipped.

Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths990K / 800K / 400K / 200K / 100K / 64K / 32KTests begin at the longest generated context and step down to verify stable, correct responses.
Current guidance

The basic call failed (Basic API call unavailable), so the long-context add-on was skipped.

Results for this test

Review API availability, model identity, response completeness, and other checks separately.

Scoring breakdown

High risk41/100

主要问题：接口根本调不通；有检测项没Passed。

Can you call it, and is the model listed0 / 10
接口根本调不通（基础调用探针） -10
Does the API respond properly0 / 12
接口根本调不通（基础调用探针） -12
Is it the model it claims to be10 / 18
接口根本调不通（基础调用探针） -8
Does it answer like the official model13 / 25
接口根本调不通（基础调用探针） -12
Is usage and billing reasonable5 / 10
接口根本调不通（基础调用探针） -5
Will it keep working13 / 25
接口根本调不通（基础调用探针） -10有检测项没Passed -2

Test details

Expand any row for details; anything private has been removed.

24 checks
Model list visibility

gpt-5.4 is visible in the API model list.

Passed
Test details
This test ran 4 times; result: Passed.
Basic call probe

基础调用未成功，可能是 Key 权限、额度、接口路径或模型能力类型问题。

Failed
Test details
This test ran 1 times; result: Failed.
Why it failed: Basic API call unavailable
Model self-identification

问它自己是什么模型，看答案对不对。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
指令跟随

用几道题看它的回答水平像不像官方模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
JSON 结构

用几道题看它的回答水平像不像官方模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
标签结构复述

按官方接口的标准调用，看返回是否规范。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
隐藏提示词边界

用几道题看它的回答水平像不像官方模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
品牌边界

问它自己是什么模型，看答案对不对。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
用量数据是否完整

核对它报回来的用量和缓存计费。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
逻辑网格推理

用几道题看它的回答水平像不像官方模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
复测一致性

反复多问几次，看会不会答一半就断或偷偷换模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
OpenAI 身份与安全边界

问它自己是什么模型，看答案对不对。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
OpenAI 身份与安全边界

用几道题看它的回答水平像不像官方模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
模型代码锚定

问它自己是什么模型，看答案对不对。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
Model-family test: series and tier identification

问它自己是什么模型，看答案对不对。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
Deep model test: family-specific boundary

用几道题看它的回答水平像不像官方模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
连问 5 次，重复内容有没有按缓存价计费

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
32K 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
64K 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
100K 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
200K 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
400K 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
800K 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
1M 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Reviews

还没有人评论，来写第一条。

发表评论

Home/Providers/API 节点 B003A646/Verification reports
MozhenzhenBefore you buy AI, check Mozhenzhen
Scan to view reportOpen full report
Mozhenzhen verification report · Measured with real calls

Is gpt-5.4 genuine? Deep check result

Report ID:MZZR20260809191934E9EDF7Generated at：2026/08/10 03:19
Provider detailsAI model details
Model consistency score

High risk

gpt-5.4 本次深度验真结果：High risk（41/100）。主要问题：接口根本调不通；有检测项没Passed。

Tested byMozhenzhen
Tested modelGPT-5.4
ProvidersAPI 节点 B003A646
Requests5
Duration1 sec
Identity verdictNot verified
Reference模真真既有版本化基线

This call did not complete

Reason for failure

The basic call returned no recognizable answer. The available records cannot establish a specific cause.

What to do

Check the endpoint address, key and model permissions. If this persists, give the provider the report ID for troubleshooting.

Token usage check

Reported usage is used; estimates appear only when none is reported.

Estimated usage1.7MThe API did not report actual usage; the estimate is shown.DeviationNoneThe API did not report actual usage; only the estimate is shown.Usage checkEstimate onlyFigures are as reported by the API; your bill is authoritative.
Token cache usage test

Several runs in a row to see whether repeated content is billed at the cheaper cache rate; 0% means no cache discount this time.

Total 0 request
Share billed at the cache rate--
No usage record

This provider's endpoint does not report usage reliably; check it against your bill.

Usage this run0Cached tokens0Non-cached tokens0Average per run--
Usage reportedNot reportedCache billingDid not happenResultNormal
Cache share by testThis is only the cache share the endpoint reported; the real discount is on the bill

No per-test records are available; only the aggregate result is shown.

Long-context test

We test how much it can read at once, then compare that with the officially stated length.

7 tiers
No stable result this time

The basic call failed (Basic API call unavailable), so the long-context add-on was skipped.

Reference windowReference window 1MModel-center context window; available lengths may vary by provider.Tested context lengths990K / 800K / 400K / 200K / 100K / 64K / 32KTests begin at the longest generated context and step down to verify stable, correct responses.
Current guidance

The basic call failed (Basic API call unavailable), so the long-context add-on was skipped.

Results for this test

Review API availability, model identity, response completeness, and other checks separately.

Scoring breakdown

High risk41/100

主要问题：接口根本调不通；有检测项没Passed。

Can you call it, and is the model listed0 / 10
接口根本调不通（基础调用探针） -10
Does the API respond properly0 / 12
接口根本调不通（基础调用探针） -12
Is it the model it claims to be10 / 18
接口根本调不通（基础调用探针） -8
Does it answer like the official model13 / 25
接口根本调不通（基础调用探针） -12
Is usage and billing reasonable5 / 10
接口根本调不通（基础调用探针） -5
Will it keep working13 / 25
接口根本调不通（基础调用探针） -10有检测项没Passed -2

Test details

Expand any row for details; anything private has been removed

24 checks
Model list visibility

gpt-5.4 is visible in the API model list.

Passed
Test details
This test ran 4 times; result: Passed.
Basic call probe

基础调用未成功，可能是 Key 权限、额度、接口路径或模型能力类型问题。

Failed
Test details
This test ran 1 times; result: Failed.
Why it failed: Basic API call unavailable
Model self-identification

问它自己是什么模型，看答案对不对。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
指令跟随

用几道题看它的回答水平像不像官方模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
JSON 结构

用几道题看它的回答水平像不像官方模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
标签结构复述

按官方接口的标准调用，看返回是否规范。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
隐藏提示词边界

用几道题看它的回答水平像不像官方模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
品牌边界

问它自己是什么模型，看答案对不对。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
用量数据是否完整

核对它报回来的用量和缓存计费。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
逻辑网格推理

用几道题看它的回答水平像不像官方模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
复测一致性

反复多问几次，看会不会答一半就断或偷偷换模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
OpenAI 身份与安全边界

问它自己是什么模型，看答案对不对。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
OpenAI 身份与安全边界

用几道题看它的回答水平像不像官方模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
模型代码锚定

问它自己是什么模型，看答案对不对。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
Model-family test: series and tier identification

问它自己是什么模型，看答案对不对。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
Deep model test: family-specific boundary

用几道题看它的回答水平像不像官方模型。 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，后续题包已跳过，避免继续消耗 token。
连问 5 次，重复内容有没有按缓存价计费

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
32K 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
64K 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
100K 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
200K 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
400K 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
800K 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。
1M 上下文能力实测

针对这个模型再做一项专门检测。 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Skipped
Test details
Result of this test: Skipped.
Why it was not tested: 基础调用探针Failed，专项检测已跳过，避免继续消耗 token。

Reviews

还没有人评论，来写第一条。

发表评论