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

2026/06/20 运行日期

claude-sonnet-4-6 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

FoxCode

R-super

RunAPI

O-Max

FoxCode

官方基准

ClaudeZZ

R-kiro

基本信息

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

模型 claude-sonnet-4-6 claude-sonnet-4-6 claude-sonnet-4-6 claude-sonnet-4-6 claude-sonnet-4-6

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 01:40:48 ~ 01:40:53 (4.2s) 01:40:52 ~ 01:41:02 (5.2s) 01:40:54 ~ 01:40:59 (4.7s) 01:40:56 ~ 01:41:01 (4.4s) 01:40:50 ~ 01:41:00 (5.9s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 2,474 ms 2,291 ms 3,399 ms 3,161 ms 4,068 ms

首文本(SSE delta) 2,475 ms 2,292 ms 3,400 ms 3,163 ms 4,070 ms

总耗时 3,326 ms 2,578 ms 3,585 ms 3,354 ms 4,508 ms

输入 90 3 3 3 3

输出 15 5 5 5 5

缓存创建

32,926

5m: 32,926 / 1h: 0

32,320

5m: 0 / 1h: 32,320

32,318

5m: 32,318 / 1h: 0

32,318

5m: 0 / 1h: 32,318

21,985

5m: 0 / 1h: 21,985

缓存读取 0 0 0 0 0

响应

pong

pong

pong

pong

pong

步骤 2: identity text

时间 01:43:21 ~ 01:43:31 (6.5s) 01:43:51 ~ 01:43:56 (4.9s) 01:43:07 ~ 01:43:13 (3.8s) 01:43:27 ~ 01:43:32 (3.6s) 01:42:11 ~ 01:42:22 (5.9s)

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) 3,737 ms 2,448 ms 2,476 ms 1,993 ms 4,643 ms

首文本(SSE delta) 3,738 ms 2,449 ms 2,477 ms 1,995 ms 4,646 ms

总耗时 5,691 ms 2,973 ms 3,026 ms 2,472 ms 5,002 ms

输入 45 3 3 3 3

输出 158 22 22 22 22

缓存创建

559

5m: 559 / 1h: 0

191

5m: 0 / 1h: 191

191

5m: 191 / 1h: 0

191

5m: 0 / 1h: 191

198

5m: 0 / 1h: 198

缓存读取 32,926 32,320 32,318 32,318 21,985

输出速度 80.9 tok/s - - - -

响应

vendor: anthropic
brand: claude
model: claude-sonnet-4-6

vendor: anthropic
brand: claude
model: claude-sonnet-4-6

vendor: anthropic
brand: claude
model: claude-sonnet-4-6

vendor: anthropic
brand: claude
model: claude-sonnet-4-6

vendor: anthropic
brand: claude
model: claude-sonnet-4-6

步骤 3: cutoff text

时间 01:46:17 ~ 01:46:22 (4.4s) 01:46:15 ~ 01:46:20 (4.4s) 01:44:29 ~ 01:44:34 (3.3s) 01:45:22 ~ 01:45:27 (3.2s) 01:45:30 ~ 01:45:40 (5.5s)

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) 3,139 ms 1,880 ms 2,233 ms 1,987 ms 4,099 ms

首文本(SSE delta) 3,140 ms 1,881 ms 2,362 ms 2,088 ms 4,100 ms

总耗时 3,554 ms 2,984 ms 2,520 ms 2,188 ms 4,467 ms

输入 91 3 3 3 3

输出 50 8 8 8 8

缓存创建

468

5m: 468 / 1h: 0

5m: 0 / 1h: 55

5m: 57 / 1h: 0

5m: 0 / 1h: 55

5m: 0 / 1h: 79

缓存读取 33,485 32,511 32,509 32,509 22,183

输出速度 120.8 tok/s - - - -

响应

2025-08

2025-08

2025-08

2025-08

2025-08

步骤 4: identity_free text

时间 01:49:16 ~ 01:49:26 (5.2s) 01:48:14 ~ 01:48:19 (4.9s) 01:48:27 ~ 01:48:32 (3.6s) 01:47:28 ~ 01:47:38 (4.9s) 01:48:53 ~ 01:49:03 (5.1s)

提示词

查看本步 Prompt

请用中文介绍你自己是什么产品或助手，由谁开发，50 字以内。

HTTP 头(TTFB) 2,940 ms 2,619 ms 1,925 ms 3,253 ms 3,643 ms

首文本(SSE delta) 3,044 ms 2,621 ms 1,926 ms 3,254 ms 3,645 ms

总耗时 4,415 ms 3,834 ms 2,852 ms 3,952 ms 4,228 ms

输入 46 3 3 3 3

输出 107 57 64 48 26

缓存创建

444

5m: 444 / 1h: 0

5m: 0 / 1h: 39

5m: 43 / 1h: 0

5m: 0 / 1h: 41

5m: 0 / 1h: 45

缓存读取 33,953 32,566 32,566 32,564 22,262

输出速度 78.0 tok/s 47.0 tok/s 69.1 tok/s 68.8 tok/s -

响应

我是 Kiro，一款由 AWS 开发的 AI 编程助手，底层基于 Anthropic 的 Claude 模型，专注于帮助开发者完成软件工程任务。

我是 Claude，由 Anthropic 公司打造的 AI 助手。当前版本为 Claude Sonnet 4.6，专为对话、编程、分析等任务设计。

我是 Claude，由 Anthropic 开发的 AI 助手，当前版本为 claude-sonnet-4-6。我可以帮助完成写作、编程、分析、问答等多种任务。

我叫 Claude，是由 Anthropic 公司开发的 AI 助手。当前使用的模型版本为 claude-sonnet-4-6。

我是 Claude，由 Anthropic 公司开发的 AI 助手。

步骤 5: knowledge_recall text

时间 01:52:16 ~ 01:52:36 (19.4s) 01:50:07 ~ 01:50:22 (14.7s) 01:52:27 ~ 01:52:37 (5.1s) 01:48:50 ~ 01:48:55 (4.5s) 01:52:52 ~ 01:53:02 (6.8s)

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) 1,590 ms 6,752 ms 1,614 ms 1,650 ms 3,298 ms

首文本(SSE delta) 1,592 ms 6,831 ms 1,616 ms 1,652 ms 3,309 ms

总耗时 18,490 ms 13,380 ms 4,103 ms 3,550 ms 5,982 ms

输入 92 3 3 3 3

输出 1,471 695 205 205 205

缓存创建

9,765

5m: 9,765 / 1h: 0

8,051

5m: 0 / 1h: 8,051

8,062

5m: 8,062 / 1h: 0

8,042

5m: 0 / 1h: 8,042

6,052

5m: 0 / 1h: 6,052

缓存读取 0 0 0 0 2,136

输出速度 87.1 tok/s 106.1 tok/s 82.4 tok/s 108.0 tok/s 76.7 tok/s

响应

{"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","nobel

{"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","nobel

{"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","nobel

{"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","nobel

{"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","nobel

步骤 6: digit_count text

时间 01:54:15 ~ 01:54:31 (14.7s) 01:52:14 ~ 01:52:34 (17.4s) 01:54:27 ~ 01:54:42 (14.1s) 01:50:55 ~ 01:51:10 (12.7s) 01:54:29 ~ 01:54:54 (20.4s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=919049445712452521824517981760168164180922008395889515047579324469917679

HTTP 头(TTFB) 2,074 ms 1,282 ms 1,319 ms 1,012 ms 3,610 ms

首文本(SSE delta) 2,075 ms 1,300 ms 1,320 ms 1,014 ms 3,612 ms

总耗时 13,914 ms 12,687 ms 13,263 ms 11,709 ms 19,406 ms

输入 31 164 164 164 3

输出 1,549 923 1,289 1,021 1,627

缓存创建

178

5m: 178 / 1h: 0

5m: 0 / 1h: 0

3,822

5m: 0 / 1h: 3,822

缓存读取 0 0 0 0 2,136

输出速度 130.8 tok/s 81.1 tok/s 107.9 tok/s 95.5 tok/s 103.0 tok/s

响应

{"n":72,"c":[6,7,11]}

```json
{"n":72,"c":[6,7,11]}
```

**Verification:**

String: `919049445712452521824517981760168164180922008395889515047579324469917679`

- **Length**: 72 digits (18 groups of 4)
- **0s** (×6): positi

## Counting digits in s

**s = 919049445712452521824517981760168164180922008395889515047579324469917679**

### Step 1: Length

Breaking into groups of 10:
```
9190494457  → 10
1245252182  → 10
4517981

## Counting digits in s

**s** = `919049445712452521824517981760168164180922008395889515047579324469917679`

### Length
Splitting into groups of 10:
```
9190494457 | 1245252182 | 4517981760 | 16816418

Counting position by position in:
`919049445712452521824517981760168164180922008395889515047579324469917679`

**Length:** 72 characters

**0s** at positions 4, 30, 39, 43, 44, 55 → **6**

**7s** at po

总计

总输入(含缓存) 145,099 138,232 138,243 138,217 102,901

总输出 3,350 1,710 1,593 1,309 1,893

总缓存创建

44,340

5m: 44,340 / 1h: 0

40,656

5m: 0 / 1h: 40,656

40,671

5m: 40,671 / 1h: 0

40,647

5m: 0 / 1h: 40,647

32,181

5m: 0 / 1h: 32,181

总缓存读取 100,364 97,397 97,393 97,391 70,702

输出速度 102.7 tok/s 87.5 tok/s 101.5 tok/s 95.9 tok/s 99.2 tok/s

总执行时间 54.4s 51.4s 34.7s 33.4s 49.5s

总墙钟时间

13m 42.2s

含步骤间等待

11m 42.0s

含步骤间等待

13m 47.9s

含步骤间等待

10m 13.9s

含步骤间等待

14m 3.9s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.1855

Anthropic: Claude Sonnet 4.6

$0.2079

Anthropic: Claude Sonnet 4.6

$0.1490

Anthropic: Claude Sonnet 4.6

$0.2018

Anthropic: Claude Sonnet 4.6

$0.1703

Anthropic: Claude Sonnet 4.6

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 - cloudflare - -

ID 格式 msg_014dNUx3leK2m4OEYXl3qmYA msg_019Xo49eDDuM4T9gjRzMoz2q msg_01XjC8sDzHdEZVR5r9HuHNxm msg_01JytQrBScXdfe9NQKuwxA8S msg_01JKskHqzV6urMLG5bGucTCu

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
R-super	cf-ray: a0e465e67d0ffd4f-NRT server: cloudflare x-new-api-version: v0.0.0 x-oneapi-request-id: 202606191754168697945318268d9d62w0cFscP	id_format: msg_prefix has_service_tier: true has_inference_geo: true model_has_date_suffix: false 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:usage.cache_fieldsupstream:anthropic-direct-from-body	a0e465e67d0ffd4f-NRT
O-Max	server: nginx/1.24.0 (Ubuntu) x-oneapi-request-id: 20260620015219526965568hMowu7ks	id_format: msg_prefix extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: false usage_has_cache_fields: true	hdr:x-oneapi-request-idbody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	—
cc	cf-ray: a0e46630ced2e041-NRT server: cloudflare set-cookie: _cfuvid=Y9SeNNNAeyidtWjiopls_a.BT6MhUenSvddTo98NRb4-1781891669.028598-1.0.1.1-jxXhsnSpWYEwjdy.l4xL9hQTz6UfJZ8aCkKa.C1LmFo; 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: false usage_has_cache_fields: true	hdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	req_011CcD3hBpEbtPPWidvKhgck a0e46630ced2e041-NRT
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: false usage_has_cache_fields: true	body:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	req_011CcD3RYGM9eZNtBDru98nA
R-kiro	via: 1.1 google cf-ray: b260c74e5278ae921e91cff8bc42f4ec-IAD server: nginx	id_format: msg_prefix via_chain: ["1.1 google"] extra_fields: ["stop_details"] has_service_tier: true has_inference_geo: true model_has_date_suffix: false usage_has_cache_fields: true	hdr:viabody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	req_b260c74e5278ae921e91cff8bc42f4ec b260c74e5278ae921e91cff8bc42f4ec-IAD

协议指纹评分（机器自动）

总分 / 100 84 95 91 100 93

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 0.0 /10 ×15 10.0 /10 ×15 0.0 /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 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

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

身份(自由) 0.0 /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 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /10 ×5

流式投递 10.0 /10 ×5 0.8 /10 ×5 10.0 /10 ×5 10.0 /10 ×5 10.0 /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

综合结论

与基线相似度 84 v3.24.0 95 v3.24.0 91 v3.24.0 基准（参考） 93 v3.24.0

雷达图例

共 23 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 流式投递 buffer_dump_match
6 自由身份 identity_free_clean
7 停止原因 stop_reason_present
8 系统提示纯净 system_prompt_clean
9 Service Tier service_tier_present
10 缓存命中比 cache_hit_ratio_match
11 缓存 TTL 一致 cache_ttl_consistency
12 推理地区 inference_geo_present
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 中文遵循 instruction_following_lang
22 档位思考量 tier_thinking_volume_match
23 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 8232 ms 6406 ms 4892 ms 4538 ms 7266 ms

输出速度 102.7 tok/s 87.5 tok/s 101.5 tok/s 95.9 tok/s 99.2 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 ⓘ

$0.1855

$0.2079

$0.1490

$0.2018

$0.1703

缓存读取占比 ⓘ 69% 70% 70% 70% 69%

揭晓

通道

服务商 FoxCode ↗

通道R-super

服务商 RunAPI ↗

通道O-Max

服务商 FoxCode ↗

通道cc

官方基准

服务商 ClaudeZZ ↗

通道R-kiro

返回列表