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

2026/06/17 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

duckcoding

cc专用

DawAPI

Aiide

O-Max

官方基准

FoxCode

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 21:45:03 ~ 21:45:13 (7.4s) 21:45:07 ~ 21:45:12 (4.8s) 21:45:01 ~ 21:45:11 (6.4s) 21:45:09 ~ 21:45:14 (4.1s) 21:45:05 ~ 21:45:10 (4.5s)

提示词

查看本步 Prompt

ping. Reply with the single word: pong

HTTP 头(TTFB) 6,126 ms 3,279 ms 4,481 ms 2,798 ms 3,256 ms

首文本(SSE delta) 6,127 ms 3,281 ms 4,482 ms 2,800 ms 3,263 ms

总耗时 6,328 ms 3,595 ms 4,859 ms 2,968 ms 3,505 ms

输入 3 3 3 3 3

输出 5 5 5 5 5

缓存创建

32,318

5m: 0 / 1h: 32,318

27,260

5m: 27,260 / 1h: 0

32,457

5m: 0 / 1h: 32,457

32,318

5m: 0 / 1h: 32,318

32,318

5m: 32,318 / 1h: 0

缓存读取 0 0 0 0 0

响应

pong

pong

pong

pong

pong

步骤 2: identity text

时间 21:48:55 ~ 21:49:00 (4.9s) 21:48:48 ~ 21:48:58 (6.8s) 21:46:51 ~ 21:47:01 (6.5s) 21:46:53 ~ 21:47:03 (4.2s) 21:47:52 ~ 21:47:57 (3.3s)

提示词

查看本步 Prompt

输出 3 行 metadata 描述你自己（当前 API 模型）。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。禁止任何额外字符：
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) 3,557 ms 4,953 ms 4,084 ms 2,769 ms 1,979 ms

首文本(SSE delta) 3,558 ms 4,955 ms 4,085 ms 2,771 ms 1,980 ms

总耗时 4,161 ms 6,049 ms 5,160 ms 3,095 ms 2,492 ms

输入 3 3 3 3 3

输出 22 22 22 22 22

缓存创建

189

5m: 0 / 1h: 189

189

5m: 189 / 1h: 0

189

5m: 0 / 1h: 189

189

5m: 0 / 1h: 189

189

5m: 189 / 1h: 0

缓存读取 32,318 27,260 32,457 32,318 32,318

响应

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

vendor: anthropic
brand: claude
model: claude-sonnet-4-5

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 21:52:40 ~ 21:52:46 (4.4s) 21:51:03 ~ 21:51:08 (4.7s) 21:49:29 ~ 21:49:39 (5.3s) 21:49:13 ~ 21:49:18 (3.5s) 21:49:15 ~ 21:49:20 (3.2s)

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) 3,456 ms 3,481 ms 3,299 ms 2,269 ms 2,066 ms

首文本(SSE delta) 3,505 ms 3,482 ms 3,732 ms 2,270 ms 2,207 ms

总耗时 3,658 ms 3,826 ms 3,866 ms 2,450 ms 2,340 ms

输入 3 3 3 3 3

输出 8 8 8 8 8

缓存创建

5m: 0 / 1h: 57

5m: 55 / 1h: 0

5m: 0 / 1h: 57

5m: 0 / 1h: 38

5m: 38 / 1h: 0

缓存读取 32,507 27,449 32,646 32,507 32,507

响应

2025-08

2025-04

2025-08

2025-08

2025-08

步骤 4: identity_free text

时间 21:55:55 ~ 21:56:00 (4.4s) 21:53:28 ~ 21:53:38 (5.7s) 21:50:54 ~ 21:51:04 (5.8s) 21:53:04 ~ 21:53:09 (4.3s) 21:52:09 ~ 21:52:14 (4.3s)

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) 2,478 ms 2,985 ms 3,699 ms 2,507 ms 2,375 ms

首文本(SSE delta) 2,479 ms 2,986 ms 4,107 ms 2,509 ms 2,794 ms

总耗时 3,283 ms 4,904 ms 4,653 ms 3,338 ms 3,435 ms

输入 3 3 3 3 3

输出 62 68 44 61 48

缓存创建

5m: 0 / 1h: 43

5m: 43 / 1h: 0

5m: 0 / 1h: 35

5m: 0 / 1h: 43

5m: 41 / 1h: 0

缓存读取 32,564 27,504 32,703 32,545 32,545

输出速度 77.1 tok/s 35.5 tok/s 80.6 tok/s 73.6 tok/s 74.9 tok/s

响应

我是 Claude，由 Anthropic 开发的 AI 助手。我基于大型语言模型构建，能够帮助用户完成写作、分析、编程、问答等各类任务。

我是 Claude，由 Anthropic 开发的 AI 助手。我擅长回答问题、分析代码、写作和多种语言任务，致力于提供安全、有帮助的智能对话服务。

我是 Claude，由 Anthropic 开发的 AI 助手。当前运行的模型版本是 claude-sonnet-4-6。

我是 Claude，由 Anthropic 开发的 AI 助手。我基于大语言模型构建，能够帮助用户完成写作、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。

步骤 5: knowledge_recall text

时间 21:58:47 ~ 21:58:57 (9.5s) 21:55:08 ~ 21:55:18 (6.3s) 21:52:45 ~ 21:52:55 (5.9s) 21:54:59 ~ 21:55:09 (5.1s) 21:56:09 ~ 21:56:19 (5.3s)

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) 5,556 ms 2,698 ms 2,165 ms 1,799 ms 2,231 ms

首文本(SSE delta) 5,557 ms 2,699 ms 2,167 ms 1,801 ms 2,233 ms

总耗时 7,579 ms 5,552 ms 4,090 ms 4,085 ms 4,245 ms

输入 3 3 3 3 3

输出 205 198 205 205 204

缓存创建

8,058

5m: 0 / 1h: 8,058

3,207

5m: 3,207 / 1h: 0

8,032

5m: 0 / 1h: 8,032

8,038

5m: 0 / 1h: 8,038

8,023

5m: 8,023 / 1h: 0

缓存读取 0 0 0 0 0

输出速度 101.4 tok/s 69.4 tok/s 106.6 tok/s 89.8 tok/s 101.4 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 22:02:21 ~ 22:02:41 (16.7s) 21:58:12 ~ 21:58:37 (24.0s) 21:55:39 ~ 21:55:59 (19.0s) 21:57:49 ~ 21:58:09 (15.7s) 21:59:22 ~ 21:59:42 (16.6s)

提示词

查看本步 Prompt

Count digits exactly in s. Return {"n":len(s),"c":[count0,count7,count9]}. s=144355267659673998096042991234369143303624394342342949007523570476586284

HTTP 头(TTFB) 2,293 ms 1,615 ms 3,135 ms 1,567 ms 1,794 ms

首文本(SSE delta) 2,295 ms 20,668 ms 3,686 ms 1,571 ms 1,799 ms

总耗时 15,888 ms 23,213 ms 17,664 ms 14,717 ms 15,683 ms

输入 164 1,001 164 164 164

输出 1,086 2,104 1,257 1,248 777

缓存创建

5m: 0 / 1h: 0

缓存读取 0 0 0 0 0

输出速度 79.9 tok/s burst 89.9 tok/s 94.9 tok/s 56.0 tok/s

响应

I'll work through the string systematically.

**s** = `144355267659673998096042991234369143303624394342342949007523570476586284`

**Length count** (groups of 10):
```
1443552676  → 10
5967399809  → 10

I'll count by splitting into groups of 10:

```
Pos  1-10:  1 4 4 3 5 5 2 6 7 6
Pos 11-20:  5 9 6 7 3 9 9 8 0 9
Pos 21-30:  6 0 4 2 9 9 1 2 3 4
Pos 31-40:  3 6 9 1 4 3 3 0 3 6
Pos 41-50:  2 4 3 9 4 3

## Counting digits in:
`s = 144355267659673998096042991234369143303624394342342949007523570476586284`

### Length
Splitting into groups of 10:
```
1443552676 | 5967399809 | 6042991234 | 3691433036 |
2

I'll carefully parse the string character by character.

**s = `144355267659673998096042991234369143303624394342342949007523570476586284`**

---

### Step 1 — Length

Splitting into groups of 10:

```

```json
{"n":72,"c":[6,5,10]}
```

**Verification:**

| Digit | Positions (1-indexed) | Count |
|---|---|---|
| **0** | 19, 22, 38, 55, 56, 63 | **6** |
| **7** | 9, 14, 57, 62, 65 | **5** |
| **9** |

总计

总输入(含缓存) 138,233 113,983 138,755 138,175 138,158

总输出 1,388 2,405 1,541 1,549 1,064

总缓存创建

40,665

5m: 0 / 1h: 40,665

30,754

5m: 30,754 / 1h: 0

40,770

5m: 0 / 1h: 40,770

40,626

5m: 0 / 1h: 40,626

40,609

5m: 40,609 / 1h: 0

总缓存读取 97,389 82,213 97,806 97,370 97,370

输出速度 82.4 tok/s 55.8 tok/s 91.6 tok/s 93.1 tok/s 62.2 tok/s

总执行时间 47.3s 52.4s 48.9s 36.8s 37.4s

总墙钟时间

17m 38.4s

含步骤间等待

13m 30.0s

含步骤间等待

10m 58.0s

含步骤间等待

12m 59.9s

含步骤间等待

14m 37.2s

含步骤间等待

按官方价目重估

同等内容若直发 Anthropic 的估算 ⓘ

$0.2031

Anthropic: Claude Sonnet 4.6

$0.1359

Anthropic: Claude Sonnet 4.6

$0.2059

Anthropic: Claude Sonnet 4.6

$0.2053

Anthropic: Claude Sonnet 4.6

$0.1409

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%) one-api (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_01RGc9KPPpCJTdv2hXNsHw7Q msg_01XrEyWtH68ccpWGFq59er84 msg_014EaGRqWRmummL3DZ52Kon7 msg_01SbTNHz9f4iiKERyyoFV1wQ msg_01Y7bgnnZRZUrgvRZitKbZZG

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专用	server: Nginx x-oneapi-request-id: 202606171402226753671308268d9d6rVfaNQ7s	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	server: cdn x-new-api-version: v1.0.0-rc.11 x-oneapi-request-id: 202606171358129573702478268d9d6srOp0p0W	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-new-api-versionhdr:x-oneapi-request-idbody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	—
O-Max	cf-ray: a0d28da29e2f2fda-AMS server: cloudflare x-new-api-version: 0.12.11 x-oneapi-request-id: 202606171355418460641358268d9d6Ue5oZDn5	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-new-api-versionhdr:x-oneapi-request-idhdr:server:cloudflarehdr:cf-raybody:id:msg_prefixbody:usage.service_tierbody:usage.inference_geobody:usage.cache_fieldsbody:extra_fieldsupstream:anthropic-direct-from-body	a0d28da29e2f2fda-AMS
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_011Cc8x2jLN9xLMg72SMV3hm
cc	cf-ray: a0d293129fb2e041-NRT server: cloudflare set-cookie: _cfuvid=lN3ivc6ftcxf_jZYSjzNkheDQoV3i.yUUysmWN2DLeo-1781704763.5231044-1.0.1.1-jai.hSHjtNAYJWuLmfywdnB76Ufv10Nxumdp42_P3II; 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_011Cc8x9akscdYHyoSaY4mNw a0d293129fb2e041-NRT

协议指纹评分（机器自动）

总分 / 100 98 73 98 100 91

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 0.0 /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 0.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8 10.0 /10 ×8

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

知识截止 10.0 /10 ×7 5.0 /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

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

Req-ID 透传 0.0 /10 ×4 0.0 /10 ×4 0.0 /10 ×4 10.0 /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 98 v3.22.0 73 v3.22.0 98 v3.22.0 基准（参考） 91 v3.22.0

雷达图例

共 20 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 自由身份 identity_free_clean
5 停止原因 stop_reason_present
6 系统提示纯净 system_prompt_clean
7 Service Tier service_tier_present
8 缓存命中比 cache_hit_ratio_match
9 缓存 TTL 一致 cache_ttl_consistency
10 推理地区 inference_geo_present
11 缓存连续 cache_continuity_intra
12 知识召回 knowledge_recall_match
13 延迟基线 latency_baseline_match
14 原生 msg-ID anthropic_msg_id_format
15 Sliding 缓存 cache_sliding_correctness
16 结构化身份 identity_structured_match
17 信封自报一致 envelope_self_report_match
18 中文遵循 instruction_following_lang
19 档位思考量 tier_thinking_volume_match
20 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 6816 ms 7857 ms 6715 ms 5109 ms 5283 ms

输出速度 82.4 tok/s 55.8 tok/s 91.6 tok/s 93.1 tok/s 62.2 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 ⓘ

$0.2031

$0.1359

$0.2059

$0.2053

$0.1409

缓存读取占比 ⓘ 70% 72% 70% 70% 70%

揭晓

通道

服务商 duckcoding ↗

通道cc专用

服务商 DawAPI ↗

通道cc

服务商 Aiide ↗

通道O-Max

官方基准

服务商 FoxCode ↗

通道cc

返回列表