Is gpt-5.4-codex genuine? Deep check result

Report ID MZZR2026071505500447775AGenerated at 2026/07/15 13:50

Matched

gpt-5.4-codex 本次深度验真结果：Matched（86/100）。主要问题：等太久没回应；有检测项没Passed。

86Model consistency score

主要问题：等太久没回应；有检测项没Passed。

Tested byMozhenzhen

Tested modelGPT-5.4 Codex

ProvidersConeverse AI

Requests34

Duration6 min 10 sec

Identity verdictVerified

ReferenceMozhenzhen's own test standard

This call did not complete

Reason for failure

The API did not return a result within this test’s waiting period.

What to do

Try again later. If this persists, ask the provider whether this model is responding normally.

Token usage check

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

Reported usage37.1KThe actual usage reported by the API; this page goes by it.Estimated usage74.8KEstimated from this test's requests.Deviation50% 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 rate37.8%

Low cache share

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

Usage this run14.9KCached tokens5.6KNon-cached tokens9.3KAverage 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

Matched86/100

主要问题：等太久没回应；有检测项没Passed。

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

No deductions

Does the API respond properly8 / 12

等太久没回应（JSON 结构） -4

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 working15 / 25

等太久没回应（JSON 结构） -8有检测项没Passed -2

Test details

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

18 checks

Model list visibility

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

Passed

Test details

This test ran 24 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 421 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。有几次没对上。

Failed

Test details

This test ran 1 times: 1 failed.

标签结构复述

按官方接口的标准调用，看返回是否规范。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

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。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

品牌边界

问它自己是什么模型，看答案对不对。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

用量数据是否完整

核对它报回来的用量和缓存计费。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

逻辑网格推理

用几道题看它的回答水平像不像官方模型。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

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。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

OpenAI 身份与安全边界

问它自己是什么模型，看答案对不对。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

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。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

模型代码锚定

问它自己是什么模型，看答案对不对。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

Model-family test: series and tier identification

问它自己是什么模型，看答案对不对。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

Deep model test: family-specific boundary

用几道题看它的回答水平像不像官方模型。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

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 5.6K 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

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:MZZR2026071505500447775AGenerated at：2026/07/15 13:50

Provider details AI model details

Model consistency score

Matched

gpt-5.4-codex 本次深度验真结果：Matched（86/100）。主要问题：等太久没回应；有检测项没Passed。

Tested byMozhenzhen

Tested modelGPT-5.4 Codex

ProvidersConeverse AI

Requests34

Duration6 min

Identity verdictVerified

ReferenceMozhenzhen's own test standard

This call did not complete

Reason for failure

The API did not return a result within this test’s waiting period.

What to do

Try again later. If this persists, ask the provider whether this model is responding normally.

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 rate37.8%

Low cache share

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

Usage this run14.9KCached tokens5.6KNon-cached tokens9.3KAverage 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

Matched86/100

主要问题：等太久没回应；有检测项没Passed。

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

No deductions

Does the API respond properly8 / 12

等太久没回应（JSON 结构） -4

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 working15 / 25

等太久没回应（JSON 结构） -8有检测项没Passed -2

Test details

Expand any row for details; anything private has been removed

18 checks

Model list visibility

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

Passed

Test details

This test ran 24 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 421 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。有几次没对上。

Failed

Test details

This test ran 1 times: 1 failed.

标签结构复述

按官方接口的标准调用，看返回是否规范。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

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。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

品牌边界

问它自己是什么模型，看答案对不对。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

用量数据是否完整

核对它报回来的用量和缓存计费。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

逻辑网格推理

用几道题看它的回答水平像不像官方模型。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

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。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

OpenAI 身份与安全边界

问它自己是什么模型，看答案对不对。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

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。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

模型代码锚定

问它自己是什么模型，看答案对不对。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

Model-family test: series and tier identification

问它自己是什么模型，看答案对不对。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

Deep model test: family-specific boundary

用几道题看它的回答水平像不像官方模型。前序检测已确认等太久没回应，为避免继续制造无效请求，本项已跳过。

Skipped

Test details

Result of this test: Skipped.
Why it was not tested: service_failure_circuit_breaker

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 5.6K 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

Reviews

还没有人评论，来写第一条。