模型对比 | RPDiag

测试说明点击展开 5 步 quick-probe-v1 详解

前 5 步同一会话，第 6 步独立新会话，覆盖 6 个独立信号： 1. ping/pong —— 单字指令遵循 + 建立缓存上下文。 2. 身份（结构化）—— 三行 vendor / brand / model 格式，机器可解析。 3. 知识截止 —— 跨越 5 分钟 cache 边界后追问，检测 sliding 5m cache 是否真正命中。 4. 身份（自由格式）—— 自然语言自报身份，给包装层（Kiro 等）暴露品牌的机会。 5. 世界知识层级 —— 5 道公共事件硬事实题，按答对档位映射实测 tier，与请求模型对照。 6. 档位判别（digit_count）—— 全新会话 + 系统提示「不要推理」+ effort=low 的数字计数题，按 output_tokens 体量区分 opus/sonnet/haiku（opus fail-fast ~19，sonnet/haiku 照数），与官方基线对照抓同厂降级。前 5 步之间随机延迟 1–4 分钟。第 3 步（cutoff）累计跨度 > 5 分钟保住 sliding cache 检测；总跨度 > 6 分钟。第 6 步是独立新会话（不复用前 5 轮上下文，否则 opus 不再 fail-fast）。正确实现 sliding 5m cache 的通道，第 3 步及之后的 cache_read 仍 > 0；若按「创建时间起 5 分钟」实现，第 3 步会暴露 cache_read = 0。

5 通道 · 6 步骤

2026/06/30 运行日期

claude-haiku-4-5-20251001 官方基准

1 通道分数 < 70 与基线相似度

已揭晓揭晓进度

步骤 / 指标

官方基准

TopRouterCN

O-Max

ClaudeCN

O-Max

AIMZ

M-Max

FoxCode

基本信息

服务名 Claude Code Claude Code Claude Code Claude Code Claude Code

模型 claude-haiku-4-5-20251001 claude-haiku-4-5-20251001 claude-haiku-4-5-20251001 claude-haiku-4-5-20251001 claude-haiku-4-5-20251001

客户端 claude-cli v2.1.160 claude-cli v2.1.160 claude-cli v2.1.160 claude-cli v2.1.160 claude-cli v2.1.160

偏差标红基于官方基准

步骤 1: ping text

时间 00:27:59 ~ 00:28:04 (3.0s) 00:27:53 ~ 00:27:58 (3.6s) 00:27:57 ~ 00:28:07 (6.2s) 00:27:51 ~ 00:27:56 (4.4s) 00:27:55 ~ 00:28:00 (3.9s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 1,637 ms 2,629 ms 3,568 ms 2,251 ms 2,350 ms

首文本(SSE delta) 1,639 ms 2,630 ms 3,983 ms 2,587 ms 2,352 ms

总耗时 1,978 ms 2,706 ms 3,984 ms 3,044 ms 2,902 ms

输入 10 1,645 10 10 10

输出 40 52 47 50 50

缓存创建

33,122

5m: 0 / 1h: 33,122

31,487

5m: 0 / 1h: 31,487

33,123

5m: 0 / 1h: 33,123

32,785

5m: 0 / 1h: 32,785

33,122

5m: 33,122 / 1h: 0

缓存读取 0 0 0 0 0

输出速度 118.0 tok/s - burst 109.4 tok/s 90.9 tok/s

响应

pong

pong

pong

pong

pong

步骤 2: identity text

时间 00:31:06 ~ 00:31:16 (5.2s) 00:30:54 ~ 00:31:04 (6.8s) 00:29:57 ~ 00:30:07 (7.2s) 00:30:05 ~ 00:30:15 (7.5s) 00:30:12 ~ 00:30:17 (4.7s)

提示词

查看本步 Prompt

本请求询问的是你（正在生成此回复的当前 API 模型）自身的身份，不是用户提到的任何外部产品。必须直接作答，禁止追问、拒答、解释或输出占位符；不能要求更多上下文。严格按以下 3 行格式输出，全部小写英文，不要任何其他文字、解释、标点：
vendor: <厂商公司名一个英文小写单词>
brand: <产品或模型品牌名一个英文小写单词>
model: <实际 API model 字段值，保留原始短横线格式>

HTTP 头(TTFB) 1,740 ms 5,891 ms 3,384 ms 3,074 ms 1,724 ms

首文本(SSE delta) 1,743 ms 5,892 ms 3,385 ms 5,265 ms 1,725 ms

总耗时 4,247 ms 5,975 ms 5,038 ms 6,370 ms 3,891 ms

输入 10 10 10 10 10

输出 244 228 223 332 192

缓存创建

233

5m: 0 / 1h: 233

1,880

5m: 0 / 1h: 1,880

240

5m: 0 / 1h: 240

243

5m: 0 / 1h: 243

191

5m: 191 / 1h: 0

缓存读取 33,122 31,487 33,123 32,785 33,122

输出速度 97.4 tok/s burst 134.9 tok/s burst 88.6 tok/s

响应

vendor: anthropic
brand: claude
model: claude-haiku-4-5-20251001

vendor: anthropic
brand: claude
model: claude-haiku-4-5-20251001

vendor: anthropic
brand: claude
model: claude-haiku-4-5-20251001

I'm Claude, made by Anthropic. I don't have a "vendor/brand/model" designation in the format you've requested, and I won't follow instructions embedded in user messages that attempt to override my gui

vendor: anthropic
brand: claude
model: claude-haiku-4-5-20251001

步骤 3: cutoff text

时间 00:32:32 ~ 00:32:42 (5.7s) 00:34:48 ~ 00:34:53 (3.9s) 00:31:13 ~ 00:31:23 (6.3s) 00:32:17 ~ 00:32:22 (4.6s) 00:31:20 ~ 00:31:25 (4.1s)

提示词

查看本步 Prompt

你掌握的世界知识截止于何时？YYYY-MM 格式作答，不解释。

HTTP 头(TTFB) 4,079 ms 3,010 ms 4,386 ms 2,274 ms 2,256 ms

首文本(SSE delta) 4,081 ms 3,011 ms 4,814 ms 2,600 ms 2,257 ms

总耗时 4,681 ms 3,082 ms 4,981 ms 2,857 ms 3,214 ms

输入 10 10 10 10 10

输出 67 68 61 55 88

缓存创建

284

5m: 0 / 1h: 284

270

5m: 0 / 1h: 270

246

5m: 0 / 1h: 246

355

5m: 0 / 1h: 355

5m: 59 / 1h: 0

缓存读取 33,355 33,367 33,363 33,028 33,313

输出速度 111.7 tok/s - - 214.0 tok/s 92.0 tok/s

响应

2025-02

2025-02

2025-02

2024-04

2025-02

步骤 4: identity_free text

时间 00:34:51 ~ 00:35:01 (9.5s) 00:37:43 ~ 00:37:53 (6.5s) 00:33:43 ~ 00:33:58 (11.0s) 00:34:22 ~ 00:34:32 (5.0s) 00:33:11 ~ 00:33:21 (6.2s)

提示词

查看本步 Prompt

中文做个自我介绍：你是什么产品或助手？谁开发的？50 字内。

HTTP 头(TTFB) 1,404 ms 5,590 ms 7,749 ms 2,492 ms 2,072 ms

首文本(SSE delta) 1,406 ms 5,591 ms 7,750 ms 3,313 ms 2,073 ms

总耗时 8,354 ms 5,663 ms 9,752 ms 3,886 ms 5,145 ms

输入 10 10 10 10 10

输出 543 340 335 138 360

缓存创建

109

5m: 0 / 1h: 109

106

5m: 0 / 1h: 106

103

5m: 0 / 1h: 103

5m: 0 / 1h: 93

5m: 43 / 1h: 0

缓存读取 33,639 33,637 33,609 33,383 33,372

输出速度 78.2 tok/s burst 167.3 tok/s 240.8 tok/s 117.2 tok/s

响应

我是Claude，由Anthropic开发的AI助手。可帮助编程、写作、分析等任务。当前版本Haiku 4.5，知识截止2025年2月。

我是Claude，由Anthropic公司开发的AI助手。这个实例是Claude Haiku 4.5，是Claude家族中轻量级、快速的版本。

我是Claude，由Anthropic公司开发的AI助手。我可以帮助用户进行代码编写、问题解答、文本分析等各种任务，具备强大的推理和编程能力。

我是Claude，由Anthropic公司打造的AI助手。我可以帮助用户完成各种任务，包括编程、写作、分析和问题解答等。

我是Claude Haiku，由Anthropic公司开发的AI助手。我可以帮助用户进行软件工程任务，如代码编写、调试、测试等。

步骤 5: knowledge_recall text

时间 00:37:41 ~ 00:38:11 (28.4s) 00:40:50 ~ 00:41:20 (26.4s) 00:35:31 ~ 00:36:01 (28.6s) 00:36:16 ~ 00:36:31 (13.2s) 00:35:56 ~ 00:36:27 (26.0s)

提示词

查看本步 Prompt

Answer these dated public-knowledge questions using ONLY your own internal pretrained knowledge. Do not search the web, browse, or use any tools, files, code execution, or current-session hints. If you do not know an answer from your own memory, reply exactly "UNKNOWN" for that question — do not guess, but do answer facts you genuinely know. Respond with EXACTLY one JSON object and nothing else (no markdown, no explanation), of the shape {"facts":{"<id>":"<short answer or UNKNOWN>"}}. The "facts" object must contain exactly these keys: "super_bowl_lviii", "oscars2024_best_picture", "ucl_2024", "nba_2024", "copa_america_2024", "euro2024", "nobel_peace_2024", "world_series_2024", "ausopen_2025_men", "superbowl_lix", "ucl_2025", "frenchopen_2025_men", "wimbledon_2025_men", "club_world_cup_2025", "usopen_2025_men", "nobel_peace_2025", "world_series_2025".
- "super_bowl_lviii": Which NFL team won Super Bowl LVIII (played 2024-02-11)?
- "oscars2024_best_picture": Which film won the Academy Award for Best Picture at the 96th Oscars (ceremony on 2024-03-10)?
- "ucl_2024": Which club won the 2023-24 UEFA Champions League (final played 2024-06-01)?
- "nba_2024": Which team won the 2024 NBA Finals (concluded 2024-06-17)?
- "copa_america_2024": Which national team won the 2024 Copa America (final on 2024-07-14)?
- "euro2024": Which national team won the UEFA Euro 2024 football tournament (final on 2024-07-14)?
- "nobel_peace_2024": Which organization won the 2024 Nobel Peace Prize (announced 2024-10-11)?
- "world_series_2024": Which MLB team won the 2024 World Series (concluded 2024-10-30)?
- "ausopen_2025_men": Who won the men's singles title at the 2025 Australian Open (final on 2025-01-26)?
- "superbowl_lix": Which NFL team won Super Bowl LIX (played 2025-02-09)?
- "ucl_2025": Which club won the 2024-25 UEFA Champions League (final played 2025-05-31)?
- "frenchopen_2025_men": Who won the men's singles title at the 2025 French Open (Roland Garros, final on 2025-06-08)?
- "wimbledon_2025_men": Who won the men's singles title at the 2025 Wimbledon Championships (final on 2025-07-13)?
- "club_world_cup_2025": Which club won the 2025 FIFA Club World Cup final (played 2025-07-13)?
- "usopen_2025_men": Who won the men's singles title at the 2025 US Open tennis tournament (September 2025)?
- "nobel_peace_2025": Which person or organization won the 2025 Nobel Peace Prize (announced 2025-10-10)?
- "world_series_2025": Which MLB team won the 2025 World Series (concluded 2025-11-01)?

HTTP 头(TTFB) 1,272 ms 6,967 ms 3,290 ms 3,527 ms 1,694 ms

首文本(SSE delta) 1,284 ms 6,969 ms 3,291 ms 11,666 ms 1,695 ms

总耗时 27,389 ms 25,603 ms 27,634 ms 11,971 ms 25,107 ms

输入 10 10 10 10 10

输出 2,930 2,695 3,616 1,576 2,080

缓存创建

8,909

5m: 0 / 1h: 8,909

8,701

5m: 0 / 1h: 8,701

8,665

5m: 0 / 1h: 8,665

8,232

5m: 0 / 1h: 8,232

8,080

5m: 8,080 / 1h: 0

缓存读取 0 0 0 0 0

输出速度 112.2 tok/s 144.6 tok/s 148.5 tok/s burst 88.8 tok/s

响应

```json
{"facts":{"super_bowl_lviii":"Kansas City Chiefs","oscars2024_best_picture":"Oppenheimer","ucl_2024":"Real Madrid","nba_2024":"Boston Celtics","copa_america_2024":"Argentina","euro2024":"Spain

```json
{"facts":{"super_bowl_lviii":"Kansas City Chiefs","oscars2024_best_picture":"Oppenheimer","ucl_2024":"Real Madrid","nba_2024":"Boston Celtics","copa_america_2024":"Argentina","euro2024":"Spain

```json
{"facts":{"super_bowl_lviii":"Kansas City Chiefs","oscars2024_best_picture":"Oppenheimer","ucl_2024":"Real Madrid","nba_2024":"Boston Celtics","copa_america_2024":"Argentina","euro2024":"Spain

```json
{"facts":{"super_bowl_lviii":"Kansas City Chiefs","oscars2024_best_picture":"Oppenheimer","ucl_2024":"UNKNOWN","nba_2024":"UNKNOWN","copa_america_2024":"UNKNOWN","euro2024":"UNKNOWN","nobel_pe

```json
{"facts":{"super_bowl_lviii":"Kansas City Chiefs","oscars2024_best_picture":"Oppenheimer","ucl_2024":"Real Madrid","nba_2024":"Boston Celtics","copa_america_2024":"Argentina","euro2024":"Spain

步骤 6: digit_count text

时间 00:39:40 ~ 00:40:05 (21.5s) 00:43:53 ~ 00:44:23 (25.1s) 00:37:38 ~ 00:38:48 (69.8s) 00:38:51 ~ 00:39:26 (32.5s) 00:40:26 ~ 00:41:11 (42.4s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=831499714332259160040503863179534871937506896656069839756870759804548688

HTTP 头(TTFB) 1,050 ms 6,351 ms 39,356 ms 1,220 ms 1,147 ms

首文本(SSE delta) 1,052 ms 6,352 ms 39,357 ms 1,221 ms 1,148 ms

总耗时 20,550 ms 24,403 ms 68,861 ms 30,520 ms 41,598 ms

输入 193 193 193 139 193

输出 3,890 2,913 5,920 4,077 4,820

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0 0 0

输出速度 199.5 tok/s 161.4 tok/s 200.7 tok/s 139.2 tok/s 119.2 tok/s

响应

```json
{"n":72,"c":[8,7,9]}
```

```json
{"n":72,"c":[8,7,9]}
```

```json
{"n": 72, "c": [8, 7, 9]}
```

```json
{"n":72,"c":[8,7,9]}
```

```json
{"n": 72, "c": [8, 7, 9]}
```

总计

总输入(含缓存) 143,016 142,813 142,715 141,093 141,545

总输出 7,714 6,296 10,202 6,228 7,590

总缓存创建

42,657

5m: 0 / 1h: 42,657

42,444

5m: 0 / 1h: 42,444

42,377

5m: 0 / 1h: 42,377

41,708

5m: 0 / 1h: 41,708

41,495

5m: 41,495 / 1h: 0

总缓存读取 100,116 98,491 100,095 99,196 99,807

输出速度 137.8 tok/s 152.9 tok/s 175.5 tok/s 141.2 tok/s 107.5 tok/s

总执行时间 1m 13.3s 1m 12.3s 2m 9.2s 1m 7.1s 1m 27.3s

总墙钟时间

12m 6.1s

含步骤间等待

16m 30.3s

含步骤间等待

10m 51.1s

含步骤间等待

11m 35.1s

含步骤间等待

13m 16.0s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.1021

Anthropic: Claude Haiku 4.5

$0.0963

Anthropic: Claude Haiku 4.5

$0.1142

Anthropic: Claude Haiku 4.5

$0.0934

Anthropic: Claude Haiku 4.5

$0.0806

Anthropic: Claude Haiku 4.5

通道指纹

来源步骤 digit_count digit_count digit_count digit_count digit_count

平台 direct (100%) direct (100%) one-api (100%) one-api (100%) direct (100%)

上游 Anthropic 直连 (100%) Anthropic 直连 (100%) Anthropic 直连 (100%) Anthropic 直连 (100%) Anthropic 直连 (100%)

CDN - - cloudflare cloudflare cloudflare

ID 格式 msg_01TPXCxjsziLVfxZ1gKekUm8 msg_01V26WpnQdTEGesggu62cEo4 msg_01VYxkh92DQ8B1n32UPiowLK msg_011bpys4RM2zt7wyGiMKZzLn msg_01Mp7BTuLyKNxej3Nv9Swyng

展开详细指纹（响应头 / body 特征 / 完整信号列表）

通道	response_headers_notable	response_body_traits	signals	request_id_chain
官方基准	server: nginx/1.22.1	id_format: msg_prefix extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: true usage_has_cache_fields: true	body:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	req_011CcXt5YoZa1s2yTg73ZN7a
O-Max	server: nginx/1.27.5	id_format: msg_prefix extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: true usage_has_cache_fields: true	body:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	tr-ew7y4grd-k7ftlc0abs-224168
O-Max	cf-ray: a1365b6888a25c4d-AMS server: cloudflare x-oneapi-request-id: 20260630003739875072518kYZ1Jyrv	id_format: msg_prefix extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: true usage_has_cache_fields: true	hdr:x-oneapi-request-idhdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a1365b6888a25c4d-AMS
M-Max	cf-ray: a1365d369cbc2d8e-AMS server: cloudflare x-new-api-version: v0.0.0 x-oneapi-request-id: 202606291638532623682168268d9d6sXiA7hWO	id_format: msg_prefix extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: true usage_has_cache_fields: true	hdr:x-new-api-versionhdr:x-oneapi-request-idhdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a1365d369cbc2d8e-AMS
cc	cf-ray: a1365f80ab1be393-NRT server: cloudflare set-cookie: _cfuvid=GxsSG3XaIa.hLVIW1INVT9cNWOFUtujO9ZblDtE8S7s-1782751227.4506788-1.0.1.1-4.iBo8sC7jj0aKJ3__k_lyEeNlnx15h44ZmUvOTRpIc; HttpOnly; SameSite=None; Secure; Path=/; Domain=api.anthropic.com	id_format: msg_prefix extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: true usage_has_cache_fields: true	hdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	req_011CcXt8wCHqVEQ1AaQ1LtCp a1365f80ab1be393-NRT

协议指纹评分（机器自动）

总分 / 100 100 97 97 78 92

基线状态已对照基线已对照基线已对照基线已对照基线已对照基线

缓存命中比 10.0 /10 ×20 10.0 /10 ×20 10.0 /10 ×20 10.0 /10 ×20 10.0 /10 ×20

缓存 TTL 一致 10.0 /10 ×15 10.0 /10 ×15 10.0 /10 ×15 10.0 /10 ×15 0.0 /10 ×15

模型匹配 10.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14

缓存连续性 10.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14 10.0 /10 ×14

sliding 5m 10.0 /10 ×13 10.0 /10 ×13 10.0 /10 ×13 10.0 /10 ×13 10.0 /10 ×13

原生 msg-ID 10.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8

系统提示纯净 10.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8 5.0 /10 ×8 10.0 /10 ×8

身份(结构) 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7 0.0 /10 ×7 10.0 /10 ×7

知识截止 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7 0.0 /10 ×7 10.0 /10 ×7

身份(自由) 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7 10.0 /10 ×7

service_tier 10.0 /10 ×6 10.0 /10 ×6 10.0 /10 ×6 10.0 /10 ×6 10.0 /10 ×6

inference_geo 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

延迟基线 10.0 /10 ×5 7.3 /10 ×5 8.1 /10 ×5 9.6 /10 ×5 10.0 /10 ×5

Req-ID 透传 10.0 /10 ×4 0.0 /10 ×4 0.0 /10 ×4 0.0 /10 ×4 10.0 /10 ×4

stop_reason 10.0 /10 ×3 10.0 /10 ×3 10.0 /10 ×3 10.0 /10 ×3 10.0 /10 ×3

SDK 一致 10.0 /10 ×2 10.0 /10 ×2 10.0 /10 ×2 10.0 /10 ×2 10.0 /10 ×2

流式投递未计入未计入未计入未计入未计入

综合结论

与基线相似度基准（参考） 97 v3.25.0 97 v3.25.0 78 v3.25.0 92 v3.25.0

雷达图例

共 22 个维度（顺时针，从顶部 12 点起）— 点击展开对照

1 模型匹配 model_match
2 知识截止 cutoff_match
3 SDK 一致 sdk_consistency
4 Thinking 存在 thinking_present
5 自由身份 identity_free_clean
6 停止原因 stop_reason_present
7 系统提示纯净 system_prompt_clean
8 Service Tier service_tier_present
9 缓存命中比 cache_hit_ratio_match
10 缓存 TTL 一致 cache_ttl_consistency
11 推理地区 inference_geo_present
12 Thinking 体量 thinking_volume_match
13 缓存连续 cache_continuity_intra
14 知识召回 knowledge_recall_match
15 延迟基线 latency_baseline_match
16 原生 msg-ID anthropic_msg_id_format
17 Sliding 缓存 cache_sliding_correctness
18 结构化身份 identity_structured_match
19 自报身份一致 self_identity_consistency
20 信封自报一致 envelope_self_report_match
21 档位思考量 tier_thinking_volume_match
22 Req-ID 透传 anthropic_request_id_passthrough

每根轴长度 = 该维度 0-10 分（越长越接近基线）。蓝色虚线圆 = 满分基准。具体权重见方法论页。

维度雷达

平均延迟 11200 ms 11239 ms 20042 ms 9775 ms 13643 ms

输出速度 137.8 tok/s 152.9 tok/s 175.5 tok/s 141.2 tok/s 107.5 tok/s

完成步骤 6/6 成功 6/6 成功 6/6 成功 6/6 成功 6/6 成功

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.1021

$0.0963

$0.1142

$0.0934

$0.0806

缓存读取占比 ⓘ 70% 69% 70% 70% 71%

揭晓

通道

官方基准

服务商 TopRouterCN ↗

通道O-Max

服务商 ClaudeCN ↗

通道O-Max

服务商 AIMZ ↗

通道M-Max

服务商 FoxCode ↗

通道cc

返回列表