模型对比 | RPDiag

测试说明点击展开 5 步 quick-probe-v1 详解

前 4 步同一会话（交互 TUI 多轮），第 5、6 步各自独立新会话，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 1-3 步的延迟在交互进程内发生，让缓存前缀在墙钟里老化）。第 3 步（cutoff）累计跨度 > 5 分钟保住 sliding cache 检测；总跨度 > 6 分钟。第 5 步（知识召回）与第 6 步（档位）都是独立新会话（第 6 步不复用上下文，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

2026/07/02 运行日期

claude-haiku-4-5-20251001 官方基准

全部 ≥ 70 与基线相似度

已揭晓揭晓进度

步骤 / 指标

PackyCode

cc-Zeus

ClaudeCN

O-Max

SAIAi

O-Max

官方基准

sucui

O-Max-NL

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 v2.1.195 claude-cli v2.1.195 claude-cli v2.1.195 claude-cli v2.1.195 claude-cli v2.1.195

偏差标红基于官方基准

步骤 1: ping text

时间 23:06:07 ~ 23:16:08 (599.5s) 23:05:05 ~ 23:14:16 (546.6s) 23:03:44 ~ 23:13:05 (557.4s) 23:06:10 ~ 23:16:46 (633.7s) 23:04:54 ~ 23:14:45 (588.7s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,490 ms 3,550 ms 2,421 ms 1,925 ms 2,251 ms

首文本(SSE delta) 3,085 ms 3,552 ms 2,703 ms 2,645 ms 2,509 ms

总耗时 4,805 ms 3,709 ms 2,719 ms 4,173 ms 4,050 ms

输入 10 10 10 10 10

输出 58 57 47 55 44

缓存创建

6,392

5m: 0 / 1h: 6,392

6,392

5m: 0 / 1h: 6,392

5m: 0 / 1h: 0

15,130

5m: 0 / 1h: 15,130

缓存读取 16,545 16,545 22,937 22,937 0

输出速度 33.7 tok/s - burst 36.0 tok/s 28.6 tok/s

响应

pong

pong

pong

pong

pong

步骤 2: identity text

时间 23:06:07 ~ 23:16:08 (599.5s) 23:05:05 ~ 23:14:16 (546.6s) 23:03:44 ~ 23:13:05 (557.4s) 23:06:10 ~ 23:16:46 (633.7s) 23:04:54 ~ 23:14:45 (588.7s)

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) 2,612 ms 2,718 ms 2,122 ms 2,302 ms 2,310 ms

首文本(SSE delta) 3,336 ms 3,402 ms 2,709 ms 3,300 ms 3,157 ms

总耗时 3,840 ms 4,691 ms 4,950 ms 5,895 ms 4,776 ms

输入 10 10 10 10 10

输出 186 253 295 240 219

缓存创建

251

5m: 0 / 1h: 251

250

5m: 0 / 1h: 250

240

5m: 0 / 1h: 240

248

5m: 0 / 1h: 248

4,424

5m: 0 / 1h: 4,424

缓存读取 22,937 22,937 22,937 22,937 10,905

输出速度 burst 196.3 tok/s 131.6 tok/s 92.5 tok/s 135.3 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

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

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

步骤 3: cutoff text

时间 23:06:07 ~ 23:16:08 (599.5s) 23:05:05 ~ 23:14:16 (546.6s) 23:03:44 ~ 23:13:05 (557.4s) 23:06:10 ~ 23:16:46 (633.7s) 23:04:54 ~ 23:14:45 (588.7s)

提示词

查看本步 Prompt

Knowledge cutoff date? Reply with YYYY-MM only.

HTTP 头(TTFB) 1,683 ms 2,471 ms 2,717 ms 2,458 ms 3,194 ms

首文本(SSE delta) 2,143 ms 3,080 ms 3,113 ms 3,438 ms 3,857 ms

总耗时 2,192 ms 3,336 ms 3,163 ms 3,503 ms 4,323 ms

输入 10 10 10 10 10

输出 62 103 69 77 79

缓存创建

209

5m: 0 / 1h: 209

295

5m: 0 / 1h: 295

318

5m: 0 / 1h: 318

280

5m: 0 / 1h: 280

4,460

5m: 0 / 1h: 4,460

缓存读取 23,188 23,187 23,177 23,185 10,905

输出速度 burst burst - - 169.5 tok/s

响应

2025-02

2025-02

2025-02

2025-02

2025-02

步骤 4: identity_free text

时间 23:06:07 ~ 23:16:08 (599.5s) 23:05:05 ~ 23:14:16 (546.6s) 23:03:44 ~ 23:13:05 (557.4s) 23:06:10 ~ 23:16:46 (633.7s) 23:04:54 ~ 23:14:45 (588.7s)

提示词

查看本步 Prompt

用中文回答：你是谁？由谁开发？50 字以内。

HTTP 头(TTFB) 2,128 ms 3,465 ms 3,724 ms 2,083 ms 2,376 ms

首文本(SSE delta) 2,952 ms 4,072 ms 4,380 ms 3,185 ms 3,769 ms

总耗时 4,953 ms 5,162 ms 5,123 ms 4,765 ms 7,855 ms

输入 10 10 10 10 10

输出 453 201 198 202 342

缓存创建

5m: 0 / 1h: 96

137

5m: 0 / 1h: 137

109

5m: 0 / 1h: 109

111

5m: 0 / 1h: 111

4,497

5m: 0 / 1h: 4,497

缓存读取 23,397 23,482 23,495 23,465 10,905

输出速度 226.4 tok/s 184.4 tok/s burst 127.8 tok/s 83.7 tok/s

响应

ææ¯Claude Codeï¼ç±Anthropicå¼åçAIå©æãåºäºClaude Haiku 4.5æ¨¡åï¼å¯å¸®å©è½¯ä»¶å·¥ç¨ä»»å¡ã

å·¥ä½ã

æ¯ä¸ä¸ªè½»éçº§ä½åè½å®æ´çå¤§è¯è¨æ¨¡åï¼è®¾è®¡ç¨äºå¿«éãé«æå°å¤çåç§ä»»å¡ã

ç å®¡æ¥åææ¯æå¯¼ã

ææ¯Claudeï¼ç±å¸®å©å®æå¤ç§è½¯ä»¶å·¥ç¨ä»»å¡ã

步骤 5: knowledge_recall text

时间 23:19:41 ~ 23:20:26 (43.8s) 23:15:41 ~ 23:16:16 (30.4s) 23:15:47 ~ 23:16:32 (44.4s) 23:19:21 ~ 23:20:11 (32.2s) 23:16:55 ~ 23:17:21 (24.0s)

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) 1,738 ms 3,216 ms 1,331 ms 1,428 ms 2,128 ms

首文本(SSE delta) 2,829 ms 3,629 ms 1,959 ms 2,023 ms 2,732 ms

总耗时 32,279 ms 19,447 ms 34,049 ms 21,337 ms 13,851 ms

输入 10 10 10 10 10

输出 4,461 3,054 3,626 2,288 2,057

缓存创建

6,817

5m: 0 / 1h: 6,817

6,814

5m: 0 / 1h: 6,814

6,815

5m: 0 / 1h: 6,815

5m: 0 / 1h: 0

1,408

5m: 0 / 1h: 1,408

缓存读取 0 0 0 6,815 13,720

输出速度 151.5 tok/s 193.1 tok/s 113.0 tok/s 118.5 tok/s 185.0 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_20

```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

步骤 6: digit_count text

时间 23:27:37 ~ 23:27:57 (15.2s) 23:19:17 ~ 23:19:52 (31.2s) 23:19:29 ~ 23:20:09 (38.6s) 23:27:57 ~ 23:29:22 (31.4s) 23:19:27 ~ 23:19:57 (28.5s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=914999781336790361781716888497526289684288967166993256426272108622391629

HTTP 头(TTFB) 1,243 ms 1,520 ms 1,295 ms 1,034 ms 1,880 ms

首文本(SSE delta) 1,244 ms 1,521 ms 1,297 ms 1,036 ms 2,345 ms

总耗时 14,124 ms 30,162 ms 37,538 ms 30,455 ms 14,492 ms

输入 193 193 193 193 8

输出 2,342 5,104 4,511 5,636 2,323

缓存创建

5m: 0 / 1h: 0

2,110

5m: 0 / 1h: 2,110

缓存读取 0 0 0 0 14,337

输出速度 181.8 tok/s 178.2 tok/s 124.5 tok/s 191.6 tok/s 191.2 tok/s

响应

```json
{"n": 72, "c": [2, 7, 12]}
```

```json
{"n":72,"c":[2,7,12]}
```

```json
{
  "n": 72,
  "c": [2, 7, 12]
}
```

```json
{"n":72,"c":[2,7,12]}
```

I'll count the digits manually:

**String:** `914999781336790361781716888497526289684288967166993256426272108622391629`

Breaking it into chunks of 10 to count systematically:

- `9149997813` → 0s: 0,

总计

总输入(含缓存) 100,075 100,282 100,271 100,221 92,859

总输出 7,562 8,772 8,746 8,498 5,064

总缓存创建

13,765

5m: 0 / 1h: 13,765

13,888

5m: 0 / 1h: 13,888

7,482

5m: 0 / 1h: 7,482

639

5m: 0 / 1h: 639

32,029

5m: 0 / 1h: 32,029

总缓存读取 86,067 86,151 92,546 99,339 60,772

输出速度 158.8 tok/s 183.9 tok/s 119.5 tok/s 154.7 tok/s 163.5 tok/s

总执行时间 40m 56.8s 37m 28.1s 38m 32.4s 43m 18.4s 40m 7.4s

总墙钟时间

21m 49.9s

含步骤间等待

14m 46.6s

含步骤间等待

16m 25.5s

含步骤间等待

23m 12.3s

含步骤间等待

15m 2.8s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.0639

Anthropic: Claude Haiku 4.5

$0.0701

Anthropic: Claude Haiku 4.5

$0.0626

Anthropic: Claude Haiku 4.5

$0.0535

Anthropic: Claude Haiku 4.5

$0.0715

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 one-api (100%) one-api (100%) direct (100%) direct (100%) one-api (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_018B4pbqA5zswmK2oqApTtDF msg_01UXzDAnXev3bwijpNECU3Q5 msg_01Y2irCiek5GxFadF7CMYwEz msg_01TaJ5VMPZ1fzCwKo9TMfBsW msg_01JoV4qVZJXwXg3dmV65YtyD

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
cc-Zeus	via: 1.1 Caddy cf-ray: a14eacfa5bf42f45-LAX server: cloudflare x-oneapi-request-id: 20260702232738647487651hXo4IJQy	id_format: msg_prefix via_chain: ["1.1 Caddy"] 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-rayhdr:viabody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a14eacfa5bf42f45-LAX
O-Max	cf-ray: a14ea0c28a746e50-AMS server: cloudflare x-oneapi-request-id: 20260702231918248131213c9mXxaR4	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	a14ea0c28a746e50-AMS
O-Max	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_011CcdTPhUKVKdVs6YoQLE9P
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_011CcdU6zTAkpGTgVMNGgKtt
O-Max-NL	via: 1.1 Caddy cf-ray: a14ea152fc864d52-FRA server: cloudflare x-new-api-version: v0.12.10 x-oneapi-request-id: 202607021519413563132658268d9d6y69XhLgO	id_format: msg_prefix via_chain: ["1.1 Caddy"] 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-rayhdr:viabody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a14ea152fc864d52-FRA

协议指纹评分（机器自动）

总分 / 100 99 98 100 99 86

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 2.6 /10 ×20

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

延迟基线 10.0 /10 ×15 9.7 /10 ×15 10.0 /10 ×15 10.0 /10 ×15 10.0 /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 10.0 /10 ×8 0.0 /10 ×8

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

知识截止 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

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

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

Req-ID 透传 0.0 /10 ×2 0.0 /10 ×2 10.0 /10 ×2 10.0 /10 ×2 0.0 /10 ×2

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 99 v3.27.0 98 v3.27.0 100 v3.27.0 基准（参考） 86 v3.27.0

雷达图例

共 21 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 信封自报一致 envelope_self_report_match
20 档位思考量 tier_thinking_volume_match
21 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 10366 ms 11085 ms 14590 ms 11688 ms 8225 ms

输出速度 158.8 tok/s 183.9 tok/s 119.5 tok/s 154.7 tok/s 163.5 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 ⓘ

$0.0639

$0.0701

$0.0626

$0.0535

$0.0715

缓存读取占比 ⓘ 86% 86% 92% 99% 65%

揭晓

通道

服务商 PackyCode ↗

通道cc-Zeus

服务商 ClaudeCN ↗

通道O-Max

服务商 SAIAi ↗

通道O-Max

官方基准

服务商 sucui ↗

通道O-Max-NL

返回列表