Does not match the claimed model grok-4.20-0309-reasoning
行为特征与官方 grok-4.20-0309-reasoning 明显不符。
- Providers
- APIGOTO
- Claimed model
- grok-4.20-0309-reasoning
- Plan
- Full check
- Reference
- 105 official models
- Requests
- 16
- Duration
- 5 分钟
01Identity check
Behaviour compared with each official referenceAnswer by answer3 answers: 0 match grok-4.20-0309-reasoning;another 1 look more like grok-4.20-0309-non-reasoning;another 2 match no model clearly on their own
- grok-4.20-0309-non-reasoning99%
- grok-4.3<1%
- qwen3-coder-480b-a35b-instruct<1%
- gpt-5.4-nano<1%
- minimax-m3<1%
02Test details
17 items · 13 passed · 3 notes · 1 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 grok-4.20-reasoning |
| 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 | Mismatch | Requested grok-4.20-reasoning; the response says grok-4.20-0309-reasoning |
| B-04 | Usage record | Inconsistent | Total 359 does not equal the sum 204 |
| B-05 | Output cleanliness | Nothing added | No inserted ads, watermarks or extra notes found |
| Identity check | |||
| C-01 | Independent sampling | 3 / 3 valid | All independent samples can be used for comparison |
| C-02 | Brand consistency | Match | Behavior belongs to the xAI Grok family; brand match score 100 |
| C-03 | Model consistency | Mismatch | 型号一致度 0,与官方 grok-4.20-0309-reasoning 明显不同 |
| 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 75% of repeated requests were billed at the cache price; the rest at the regular price. |
| D-02 | Context length | 128K passed | 32K / 128K: every tier was read in full. |
| 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 |
03Which apps can connect
Tried once per app with grok-4.20-reasoning, the way each app connectsUsing this test’s address, key and model, we test responses and tool calls in each app’s API format. We do not launch the apps or test installation, sign-in or complete tasks.
| Software | Result | Methodology |
|---|---|---|
| Codex | Connects | Replied normally and called the toolConnected the way Codex does (OpenAI Responses format) |
| Cherry Studio, Chatbox, LobeChat, Open WebUI, Cline | Connects | Replied normally and called the toolConnected the way Cherry Studio and similar apps do (OpenAI-compatible format) |
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.
On average 75% of repeated requests were billed at the cache price; the rest at the regular price.
Long documents are sent tier by tier to check whether the whole document is read.
32K / 128K: every tier was read in full.
- 32KRead in full · 28.8K received
- 128KRead in full · 121.3K received
Token usage check
Reported usage is used; estimates appear only when none is reported.
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.
Reviews
还没有人评论,来写第一条。
Before you buy AI, check Mozhenzhengrok-4.20-reasoning verification report
Does not match the claimed model grok-4.20-0309-reasoning
行为特征与官方 grok-4.20-0309-reasoning 明显不符。
- Providers
- APIGOTO
- Claimed model
- grok-4.20-0309-reasoning
- Plan
- Full check
- Reference
- 105 official models
- Requests
- 16
- Duration
- 5 分钟
01Identity check
Behaviour compared with each official referenceAnswer by answer3 answers: 0 match grok-4.20-0309-reasoning;another 1 look more like grok-4.20-0309-non-reasoning;another 2 match no model clearly on their own
- grok-4.20-0309-non-reasoning99%
- grok-4.3<1%
- qwen3-coder-480b-a35b-instruct<1%
- gpt-5.4-nano<1%
- minimax-m3<1%
02Test details
17 items · 13 passed · 3 notes · 1 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 grok-4.20-reasoning |
| 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 | Mismatch | Requested grok-4.20-reasoning; the response says grok-4.20-0309-reasoning |
| B-04 | Usage record | Inconsistent | Total 359 does not equal the sum 204 |
| B-05 | Output cleanliness | Nothing added | No inserted ads, watermarks or extra notes found |
| Identity check | |||
| C-01 | Independent sampling | 3 / 3 valid | All independent samples can be used for comparison |
| C-02 | Brand consistency | Match | Behavior belongs to the xAI Grok family; brand match score 100 |
| C-03 | Model consistency | Mismatch | 型号一致度 0,与官方 grok-4.20-0309-reasoning 明显不同 |
| 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 75% of repeated requests were billed at the cache price; the rest at the regular price. |
| D-02 | Context length | 128K passed | 32K / 128K: every tier was read in full. |
| 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 |
03Which apps can connect
Tried once per app with grok-4.20-reasoning, the way each app connectsUsing this test’s address, key and model, we test responses and tool calls in each app’s API format. We do not launch the apps or test installation, sign-in or complete tasks.
| Software | Result | Methodology |
|---|---|---|
| Codex | Connects | Replied normally and called the toolConnected the way Codex does (OpenAI Responses format) |
| Cherry Studio, Chatbox, LobeChat, Open WebUI, Cline | Connects | Replied normally and called the toolConnected the way Cherry Studio and similar apps do (OpenAI-compatible format) |
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.
On average 75% of repeated requests were billed at the cache price; the rest at the regular price.
Long documents are sent tier by tier to check whether the whole document is read.
32K / 128K: every tier was read in full.
- 32KRead in full · 28.8K received
- 128KRead in full · 121.3K received
Token usage check
Reported usage is used; estimates appear only when none is reported.
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.
Reviews
还没有人评论,来写第一条。
发表评论