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

2026/06/27 运行日期

claude-haiku-4-5-20251001 官方基准

3 通道分数 < 70 与基线相似度

已揭晓揭晓进度

步骤 / 指标

LinkAPI

O-Max

luminai

M-Kiro/Antigravity

SSSAiCode

O-Max-L2

官方基准

AiTokensFlux

O-Pro

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 23:08:09 ~ 23:08:14 (3.7s) 23:08:05 ~ 23:08:15 (7.4s) 23:08:11 ~ 23:08:16 (4.0s) 23:08:13 ~ 23:08:18 (3.8s) 23:08:07 ~ 23:08:12 (4.0s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 1,875 ms 4,438 ms 2,444 ms 2,251 ms 2,658 ms

首文本(SSE delta) 2,294 ms 4,446 ms 2,724 ms 2,252 ms 2,659 ms

总耗时 2,357 ms 5,215 ms 2,967 ms 2,769 ms 3,112 ms

输入 10 2,309 10 10 10

输出 52 1 58 58 55

缓存创建

32,168

5m: 32,168 / 1h: 0

796

5m: 796 / 1h: 0

32,785

5m: 0 / 1h: 32,785

33,122

5m: 0 / 1h: 33,122

33,261

5m: 0 / 1h: 33,261

缓存读取 0 25,750 0 0 0

输出速度 - - 238.7 tok/s 112.2 tok/s 121.4 tok/s

响应

pong

pong

pong

pong

pong

步骤 2: identity text

时间 23:11:51 ~ 23:11:56 (4.7s) 23:10:22 ~ 23:10:32 (6.1s) 23:10:20 ~ 23:10:41 (15.8s) 23:09:19 ~ 23:09:30 (5.4s) 23:09:12 ~ 23:09:22 (5.2s)

提示词

查看本步 Prompt

以下是对你自身的 metadata 探针。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。按以下 3 行回答自己的身份，每行一个 label，不要寒暄不要解释：
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) 2,213 ms 4,401 ms 1,917 ms 2,322 ms 2,251 ms

首文本(SSE delta) 3,069 ms 4,402 ms 13,998 ms 2,324 ms 2,252 ms

总耗时 3,802 ms 4,709 ms 14,339 ms 4,389 ms 4,333 ms

输入 10 2,325 10 10 10

输出 175 28 988 255 231

缓存创建

256

5m: 256 / 1h: 0

801

5m: 801 / 1h: 0

262

5m: 0 / 1h: 262

262

5m: 0 / 1h: 262

259

5m: 0 / 1h: 259

缓存读取 32,168 25,925 32,785 33,122 33,261

输出速度 238.7 tok/s - burst 123.5 tok/s 111.0 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-3-5-sonnet-20241022

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 23:13:18 ~ 23:13:33 (12.5s) 23:14:22 ~ 23:14:32 (5.0s) 23:11:53 ~ 23:11:58 (3.9s) 23:12:07 ~ 23:12:12 (3.0s) 23:11:11 ~ 23:11:16 (4.1s)

提示词

查看本步 Prompt

请直接回答你的知识截止日期，格式 YYYY-MM，不要附加任何说明。

HTTP 头(TTFB) 11,402 ms 3,663 ms 2,262 ms 1,616 ms 2,499 ms

首文本(SSE delta) 11,403 ms 3,717 ms 2,796 ms 1,617 ms 2,501 ms

总耗时 11,454 ms 3,785 ms 3,049 ms 2,097 ms 3,095 ms

输入 10 2,328 10 10 10

输出 82 4 72 72 78

缓存创建

217

5m: 217 / 1h: 0

803

5m: 803 / 1h: 0

1,011

5m: 0 / 1h: 1,011

297

5m: 0 / 1h: 297

273

5m: 0 / 1h: 273

缓存读取 32,424 25,968 33,047 33,384 33,520

输出速度 - - - 150.0 tok/s 131.3 tok/s

响应

2025-02

2025-02

2024-04

2025-02

2025-02

步骤 4: identity_free text

时间 23:17:04 ~ 23:17:19 (12.7s) 23:17:15 ~ 23:17:25 (7.5s) 23:14:18 ~ 23:14:28 (5.0s) 23:15:39 ~ 23:15:54 (9.9s) 23:13:08 ~ 23:13:18 (5.1s)

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) 8,825 ms 4,960 ms 2,428 ms 1,548 ms 2,771 ms

首文本(SSE delta) 8,826 ms 5,247 ms 3,684 ms 1,550 ms 2,773 ms

总耗时 11,802 ms 5,306 ms 3,909 ms 8,965 ms 4,335 ms

输入 10 2,331 10 10 10

输出 492 60 201 1,030 268

缓存创建

116

5m: 116 / 1h: 0

804

5m: 804 / 1h: 0

106

5m: 0 / 1h: 106

114

5m: 0 / 1h: 114

118

5m: 0 / 1h: 118

缓存读取 32,641 26,001 34,058 33,681 33,793

输出速度 165.3 tok/s - burst 138.9 tok/s 171.6 tok/s

响应

我是Claude Code，由Anthropic公司开发的AI编程助手。我基于Claude模型，专门用于帮助用户进行软件工程任务，如解决bug、添加功能、代码重构等。

我是 Claude Haiku 4.5，由 Anthropic 公司打造的大语言模型。我可以帮助用户进行软件工程任务、代码编写、问题分析和其他专业工作。

我是Claude，由Anthropic公司开发的AI助手。我能帮助用户进行编程、写作、分析和问题解决等各类任务。

Claude 是由 Anthropic 公司开发的 AI 助手。我专门帮助用户进行软件工程任务，包括代码编写、问题诊断、架构设计等工作，目标是提供精准、有帮助的技术支持。

我是Claude Haiku 4.5，由Anthropic公司开发，属于Claude AI助手产品系列。

步骤 5: knowledge_recall text

时间 23:19:55 ~ 23:20:30 (34.2s) 23:18:59 ~ 23:19:09 (5.4s) 23:17:13 ~ 23:17:23 (9.3s) 23:19:46 ~ 23:20:16 (25.5s) 23:15:52 ~ 23:16:12 (16.4s)

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) 2,383 ms 2,998 ms 1,860 ms 1,290 ms 1,620 ms

首文本(SSE delta) 2,770 ms 2,999 ms 8,054 ms 1,293 ms 1,624 ms

总耗时 33,186 ms 4,270 ms 8,374 ms 24,547 ms 15,664 ms

输入 10 600 10 10 10

输出 2,411 192 1,246 3,501 2,053

缓存创建

9,683

5m: 9,683 / 1h: 0

206

5m: 206 / 1h: 0

8,983

5m: 0 / 1h: 8,983

9,443

5m: 0 / 1h: 9,443

8,658

5m: 0 / 1h: 8,658

缓存读取 0 6,691 0 0 0

输出速度 79.3 tok/s 151.1 tok/s burst 150.6 tok/s 146.2 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":"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

```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 23:22:39 ~ 23:23:04 (24.1s) 23:22:21 ~ 23:22:26 (4.0s) 23:20:17 ~ 23:20:32 (12.7s) 23:23:00 ~ 23:23:15 (12.2s) 23:20:03 ~ 23:20:33 (26.1s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=448261192510310961148118988717963459585678900250769952173871622719856621

HTTP 头(TTFB) 7,095 ms 2,480 ms 1,418 ms 937 ms 1,495 ms

首文本(SSE delta) 7,704 ms 2,481 ms 1,419 ms 939 ms 1,496 ms

总耗时 23,167 ms 2,885 ms 11,904 ms 11,208 ms 25,347 ms

输入 2,112 16 139 193 193

输出 3,161 19 1,922 1,895 3,821

缓存创建

5m: 0 / 1h: 0

5m: 5 / 1h: 0

5m: 0 / 1h: 0

缓存读取 0 168 0 0 0

输出速度 204.4 tok/s - 183.3 tok/s 184.5 tok/s 160.2 tok/s

响应

```json
{"n": 72, "c": [5, 7, 9]}
```

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

```json
{"n":72,"c":[5,7,9]}
```

```json
{"n":72,"c":[5,7,9]}
```

```json
{"n": 72, "c": [5, 7, 9]}
```

总计

总输入(含缓存) 141,835 123,827 143,226 143,668 143,386

总输出 6,373 304 4,487 6,811 6,506

总缓存创建

42,440

5m: 42,440 / 1h: 0

3,415

5m: 3,415 / 1h: 0

43,147

5m: 0 / 1h: 43,147

43,238

5m: 0 / 1h: 43,238

42,569

5m: 0 / 1h: 42,569

总缓存读取 97,233 110,503 99,890 100,187 100,574

输出速度 125.8 tok/s 151.1 tok/s 184.6 tok/s 154.8 tok/s 152.8 tok/s

总执行时间 1m 31.9s 35.2s 50.6s 59.9s 1m 0.9s

总墙钟时间

14m 55.0s

含步骤间等待

14m 21.0s

含步骤间等待

12m 20.8s

含步骤间等待

15m 2.1s

含步骤间等待

12m 26.2s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.0769

Anthropic: Claude Haiku 4.5

$0.0251

Anthropic: Claude Haiku 4.5

$0.0865

Anthropic: Claude Haiku 4.5

$0.0984

Anthropic: Claude Haiku 4.5

$0.0960

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%) 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 - - -

ID 格式 msg_01LfP6iTmxo249S2R4R7efz7 msg_01bqmt3P2iMvU4cmKNwLWUDe62 msg_01WB94Vaqd6NKocib7DzyTtH msg_015nGWHiecgyZ1ViUMxzjWbw msg_01U7ST7BJDnTCmeWzvDUWpUb

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
O-Max	server: nginx set-cookie: server_name_session=7d88fca8b1426ca76c58d5aeba6fb224; Max-Age=86400; httponly; path=/ x-new-api-version: v1.0.0-rc.15 x-oneapi-request-id: 202606271522406593932488268d9d6u8TRdkyZ	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-idbody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	—
M-Kiro/Antigravity	cf-ray: a1257264eb5766a6-AMS server: cloudflare x-oneapi-request-id: 202606271522233555639118268d9d6d7ZRRmMt	id_format: msg_prefix extra_fields: ["container"] has_service_tier: true has_inference_geo: false 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:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a1257264eb5766a6-AMS
O-Max-L2	cf-ray: a1256f5e9c1412ad-LAX server: Photon-Edge set-cookie: _cfuvid=XJNlXdxpAygkyM65XUTuKm_q3QuPywswixbVP34xAFY-1782573618.972954-1.0.1.1-gZw7gNX2IP7f15YftOkhdId5I3Tl7RnhVsqu7jX4Xbg; 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	body:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:model:date_suffixbody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	1782573618390-pm9tp53nkkkdu req_011CcTzQengpqmZ6jaBKZfYM a1256f5e9c1412ad-LAX
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_011CcTzcfgMAwH77DdG9RG6u
O-Pro	server: nginx	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	—

协议指纹评分（机器自动）

总分 / 100 80 68 80 97 95

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 7.1 /10 ×20 10.0 /10 ×20 7.2 /10 ×20 7.2 /10 ×20 7.4 /10 ×20

缓存 TTL 一致 0.0 /10 ×15 0.0 /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 5.0 /10 ×8 0.0 /10 ×8 5.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8

身份(结构) 10.0 /10 ×7 10.0 /10 ×7 6.7 /10 ×7 10.0 /10 ×7 10.0 /10 ×7

知识截止 10.0 /10 ×7 10.0 /10 ×7 0.0 /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

inference_geo 10.0 /10 ×5 0.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

延迟基线 7.5 /10 ×5 7.4 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 9.9 /10 ×5

Req-ID 透传 0.0 /10 ×4 0.0 /10 ×4 10.0 /10 ×4 10.0 /10 ×4 0.0 /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 80 v3.25.0 68 v3.25.0 80 v3.25.0 基准（参考） 95 v3.25.0

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 14295 ms 4362 ms 7424 ms 8996 ms 9314 ms

输出速度 125.8 tok/s 151.1 tok/s 184.6 tok/s 154.8 tok/s 152.8 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 ⓘ

$0.0769

$0.0251

$0.0865

$0.0984

$0.0960

缓存读取占比 ⓘ 69% 89% 70% 70% 70%

揭晓

通道

服务商 LinkAPI ↗

通道O-Max

服务商 luminai ↗

通道M-Kiro/Antigravity

服务商 SSSAiCode ↗

通道O-Max-L2

官方基准

服务商 AiTokensFlux ↗

通道O-Pro

返回列表