Verification report details

Is kimi-k3 genuine? Standard check result

Report ID MZZR202609151909336B0E9FGenerated at 2026/09/16 03:09

Insufficient evidence to determine

Insufficient evidence to determine model identity. API, speed, tool, and token observations are recorded separately and do not establish identity.

Insufficient evidenceEvidence status

主要问题：让它按固定格式输出，它做不稳；它自称的型号前后对不上。

Tested byMozhenzhen
Tested modelKimi K3
Providers推爆AI应用
Requests21
Duration6 min 18 sec
Identity verdictInsufficient evidence to determine
ReferenceNo reference under matching conditions

API and capability checks

The basic API call succeeded and returned a recognizable response.

  • Model self-identification：Needs review
  • 让它按指定格式输出，格式兑现了吗：Needs review

API results and model identity are assessed separately. Insufficient evidence does not mean a failed request or a fake model.

Model reference evidence

No reference samples under matching conditions are available for this model.

Model self-identification and individual answers do not establish authenticity. Official references only reflect API behavior at the time of sampling.

Rule version：2026-09-14.v1

Token usage check

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

Reported usage17.8KThe actual usage reported by the API; this page goes by it.Estimated usage59.1KEstimated from this test's requests.Deviation70% 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 rate52.8%
Low cache share

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

Usage this run14.5KCached tokens7.7KNon-cached tokens6.9KAverage per run2.9K
Usage reportedReportedCache billingHappenedResultNormal
Cache share by testThis is only the cache share the endpoint reported; the real discount is on the bill
100%75%50%25%0第 1 次：缓存占比 0.0%，缓存 0 token，本次用量 2.9K token0.0%1times第 2 次：缓存占比 87.1%，缓存 2.6K token，本次用量 2.9K token87.1%2times第 3 次：缓存占比 89.3%，缓存 2.6K token，本次用量 2.9K token89.3%3times第 4 次：缓存占比 0.0%，缓存 0 token，本次用量 2.8K token0.0%4times第 5 次：缓存占比 85.9%，缓存 2.6K token，本次用量 3.0K token85.9%5times

Test details

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

16 checks
Model list visibility

kimi-k3 is visible in the API model list.

Passed
Test details
This test ran 2 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

问它自己是什么模型，看答案对不对。 1 次里对了 0 次。

Needs review
Test details
This test ran 1 times: 1 need attention.
Why it failed: Self-reported model identity needs review
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 226 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 283 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 94 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 65 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 552 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 286 tokens
Kimi 长上下文边界

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 895 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 113 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 96 tokens
边打字边回和一次性回，结果一样吗

对照官方公开的产品说明来测。 1 次都对。

Passed
Test details
This test ran 1 times: 1 passed.
This test used 43 tokens
让它调用工具，返回格式对不对

对照官方公开的产品说明来测。 1 次都对。

Passed
Test details
This test ran 1 times: 1 passed.
This test used 183 tokens
让它按指定格式输出，格式兑现了吗

对照官方公开的产品说明来测。 1 次里对了 0 次。

Needs review
Test details
This test ran 1 times: 1 need attention.
Why it failed: Structured output was unstable
This test used 405 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 14.5K tokens
of which 7.7K tokens were billed at the cache price

Reviews

还没有人评论，来写第一条。

发表评论

Latest verification reports/Verification reports
MozhenzhenBefore you buy AI, check Mozhenzhen
Scan to view reportOpen full report
Mozhenzhen verification report · Measured with real calls

Is kimi-k3 genuine? Standard check result

Report ID:MZZR202609151909336B0E9FGenerated at：2026/09/16 03:09
Provider detailsAI model details
Evidence status

Insufficient evidence to determine

Insufficient evidence to determine model identity. API, speed, tool, and token observations are recorded separately and do not establish identity.

Tested byMozhenzhen
Tested modelKimi K3
Providers推爆AI应用
Requests21
Duration6 min
Identity verdictInsufficient evidence to determine
ReferenceNo reference under matching conditions

API and capability checks

The basic API call succeeded and returned a recognizable response.

  • Model self-identification：Needs review
  • 让它按指定格式输出，格式兑现了吗：Needs review

API results and model identity are assessed separately. Insufficient evidence does not mean a failed request or a fake model.

Model reference evidence

No reference samples under matching conditions are available for this model.

Model self-identification and individual answers do not establish authenticity. Official references only reflect API behavior at the time of sampling.

Rule version：2026-09-14.v1

Token usage check

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

Reported usage17.8KThe actual usage reported by the API; this page goes by it.Estimated usage59.1KEstimated from this test's requests.Deviation70% 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 rate52.8%
Low cache share

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

Usage this run14.5KCached tokens7.7KNon-cached tokens6.9KAverage per run2.9K
Usage reportedReportedCache billingHappenedResultNormal
Cache share by testThis is only the cache share the endpoint reported; the real discount is on the bill
100%75%50%25%0第 1 次：缓存占比 0.0%，缓存 0 token，本次用量 2.9K token0.0%1times第 2 次：缓存占比 87.1%，缓存 2.6K token，本次用量 2.9K token87.1%2times第 3 次：缓存占比 89.3%，缓存 2.6K token，本次用量 2.9K token89.3%3times第 4 次：缓存占比 0.0%，缓存 0 token，本次用量 2.8K token0.0%4times第 5 次：缓存占比 85.9%，缓存 2.6K token，本次用量 3.0K token85.9%5times

Test details

Expand any row for details; anything private has been removed

16 checks
Model list visibility

kimi-k3 is visible in the API model list.

Passed
Test details
This test ran 2 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

问它自己是什么模型，看答案对不对。 1 次里对了 0 次。

Needs review
Test details
This test ran 1 times: 1 need attention.
Why it failed: Self-reported model identity needs review
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 226 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 283 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 94 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 65 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 552 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 286 tokens
Kimi 长上下文边界

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 895 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 113 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 96 tokens
边打字边回和一次性回，结果一样吗

对照官方公开的产品说明来测。 1 次都对。

Passed
Test details
This test ran 1 times: 1 passed.
This test used 43 tokens
让它调用工具，返回格式对不对

对照官方公开的产品说明来测。 1 次都对。

Passed
Test details
This test ran 1 times: 1 passed.
This test used 183 tokens
让它按指定格式输出，格式兑现了吗

对照官方公开的产品说明来测。 1 次里对了 0 次。

Needs review
Test details
This test ran 1 times: 1 need attention.
Why it failed: Structured output was unstable
This test used 405 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 14.5K tokens
of which 7.7K tokens were billed at the cache price

Reviews

还没有人评论，来写第一条。

发表评论