Is gpt-5.4-codex genuine? Deep check result

Report ID MZZR20260805075708F0E9D8Generated at 2026/08/05 15:57

Highly matched

gpt-5.4-codex 本次深度验真结果：Highly matched（100/100）。本轮主要检测项均已Passed。

100Model consistency score

All primary checks passed in this run.

Tested byMozhenzhen

Tested modelGPT-5.4 Codex

Providersconeverse.com

Requests34

Duration1 min 29 sec

Identity verdictVerified

Reference模真真既有版本化基线

Token usage check

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

Reported usage44.0KThe actual usage reported by the API; this page goes by it.Estimated usage74.8KEstimated from this test's requests.Deviation41% belowThe reported usage is below the estimate, possibly because of how tokens are counted or compressed.Usage checkBelow the estimateFigures 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 5 request

Share billed at the cache rate56.8%

Low cache share

Caching was used, but only a little; check your bill to see how much it really saves.

Usage this run14.9KCached tokens8.4KNon-cached tokens6.4KAverage per run3.0K

Usage reportedReportedCache billingHappenedResultNormal

Cache share by testThis is only the cache share the endpoint reported; the real discount is on the bill

Long-context test

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

1 tiers

Verified up to 32K

All tested context tiers (32K) returned reliably.

Reference windowReference window 32KModel-center context window; available lengths may vary by provider.Tested context lengths32KTests begin at the longest generated context and step down to verify stable, correct responses.

Results for this test

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

Scoring breakdown

Highly matched100/100

All primary checks passed in this run.

Can you call it, and is the model listed10 / 10

No deductions

Does the API respond properly12 / 12

No deductions

Is it the model it claims to be18 / 18

No deductions

Does it answer like the official model25 / 25

No deductions

Is usage and billing reasonable10 / 10

No deductions

Will it keep working25 / 25

No deductions

Test details

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

22 checks

Model list visibility

gpt-5.4-codex is visible in the API model list.

Passed

Test details

This test ran 8 times; result: Passed.

Basic call probe

The basic API call succeeded and returned a recognizable response.

Passed

Test details

This test ran 1 times; result: Passed.

Model self-identification

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 415 tokens

指令跟随

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 322 tokens

JSON 结构

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 335 tokens

标签结构复述

按官方接口的标准调用，看返回是否规范。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 376 tokens

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。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 353 tokens

品牌边界

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 386 tokens

用量数据是否完整

核对它报回来的用量和缓存计费。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 336 tokens

逻辑网格推理

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 537 tokens

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。 2 次都对。

Passed

Test details

This test ran 2 times: 2 passed.
This test used 668 tokens

OpenAI 身份与安全边界

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 432 tokens

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。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 779 tokens

模型代码锚定

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 415 tokens

Model-family test: series and tier identification

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 383 tokens

Deep model test: family-specific boundary

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 480 tokens

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。 5 次都对。

Passed

Test details

This test ran 5 times: 5 passed.
This test used 14.9K tokens
of which 8.4K tokens were billed at the cache price

32K 上下文能力实测

32K 长度的内容能稳定读完，这就是本次上下文实测的依据。

Passed

Test details

This test ran 1 times: 1 passed.
Content length used: 32K
This test used 21.1K tokens

按官方接口标准调用：OpenAI Responses

针对这个模型再做一项专门检测。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 324 tokens

边打字边回和一次性回，结果一样吗

针对这个模型再做一项专门检测。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 324 tokens

让它调用工具，返回格式对不对

针对这个模型再做一项专门检测。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 395 tokens

让它按指定格式输出，格式兑现了吗

针对这个模型再做一项专门检测。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 381 tokens

Reviews

还没有人评论，来写第一条。

发表评论

Before you buy AI, check Mozhenzhen

Scan to view reportOpen full report

Mozhenzhen verification report · Measured with real calls

Is gpt-5.4-codex genuine? Deep check result

Report ID:MZZR20260805075708F0E9D8Generated at：2026/08/05 15:57

Provider details AI model details

Model consistency score

Highly matched

gpt-5.4-codex 本次深度验真结果：Highly matched（100/100）。本轮主要检测项均已Passed。

Tested byMozhenzhen

Tested modelGPT-5.4 Codex

Providersconeverse.com

Requests34

Duration1 min

Identity verdictVerified

Reference模真真既有版本化基线

Token usage check

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

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 5 request

Share billed at the cache rate56.8%

Low cache share

Caching was used, but only a little; check your bill to see how much it really saves.

Usage this run14.9KCached tokens8.4KNon-cached tokens6.4KAverage per run3.0K

Usage reportedReportedCache billingHappenedResultNormal

Cache share by testThis is only the cache share the endpoint reported; the real discount is on the bill

Long-context test

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

1 tiers

Verified up to 32K

All tested context tiers (32K) returned reliably.

Results for this test

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

Scoring breakdown

Highly matched100/100

All primary checks passed in this run.

Can you call it, and is the model listed10 / 10

No deductions

Does the API respond properly12 / 12

No deductions

Is it the model it claims to be18 / 18

No deductions

Does it answer like the official model25 / 25

No deductions

Is usage and billing reasonable10 / 10

No deductions

Will it keep working25 / 25

No deductions

Test details

Expand any row for details; anything private has been removed

22 checks

Model list visibility

gpt-5.4-codex is visible in the API model list.

Passed

Test details

This test ran 8 times; result: Passed.

Basic call probe

The basic API call succeeded and returned a recognizable response.

Passed

Test details

This test ran 1 times; result: Passed.

Model self-identification

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 415 tokens

指令跟随

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 322 tokens

JSON 结构

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 335 tokens

标签结构复述

按官方接口的标准调用，看返回是否规范。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 376 tokens

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。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 353 tokens

品牌边界

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 386 tokens

用量数据是否完整

核对它报回来的用量和缓存计费。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 336 tokens

逻辑网格推理

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 537 tokens

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。 2 次都对。

Passed

Test details

This test ran 2 times: 2 passed.
This test used 668 tokens

OpenAI 身份与安全边界

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 432 tokens

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。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 779 tokens

模型代码锚定

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 415 tokens

Model-family test: series and tier identification

Asked the model to identify itself; all 1 responses matched the expected name.

Passed

Test details

This test ran 1 times: 1 passed.
This test used 383 tokens

Deep model test: family-specific boundary

用几道题看它的回答水平像不像官方模型。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 480 tokens

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。 5 次都对。

Passed

Test details

This test ran 5 times: 5 passed.
This test used 14.9K tokens
of which 8.4K tokens were billed at the cache price

32K 上下文能力实测

32K 长度的内容能稳定读完，这就是本次上下文实测的依据。

Passed

Test details

This test ran 1 times: 1 passed.
Content length used: 32K
This test used 21.1K tokens

按官方接口标准调用：OpenAI Responses

针对这个模型再做一项专门检测。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 324 tokens

边打字边回和一次性回，结果一样吗

针对这个模型再做一项专门检测。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 324 tokens

让它调用工具，返回格式对不对

针对这个模型再做一项专门检测。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 395 tokens

让它按指定格式输出，格式兑现了吗

针对这个模型再做一项专门检测。 1 次都对。

Passed

Test details

This test ran 1 times: 1 passed.
This test used 381 tokens

Reviews

还没有人评论，来写第一条。