AIHOT — List recent public AI items
Start here for feeds, widgets and 'what is new' views. Covers the last 7 days only. Send If-None-Match and you get a 304 with an empty body whenever nothing changed. To follow new items, page back with cursor only until you reach an id you already have. Do not use this to maintain a complete local copy of the selected set: it is windowed, so anything older than 7 days silently falls out. Use /api/v1/selected/snapshot plus /api/v1/selected/changes for that.
- Selected price
- $0 / callPublished pricing
- Providers / implementations
- 1 / 1
- Requests · 30d
- —Loading...
- Success rate · 30d
- —Loading...
| Provider | Price / call | Requests · 30d | Performance | Access |
|---|---|---|---|---|
aihotCurrent AIHOT — List recent public AI items · GET | $0 / call | — | —successP50— |
Loading...
Statistics use persisted gateway logs from the last 30 days up to now, including today.
Success rate = successful requests / all requests;
P50 = median latency of successful requests.
Prices reflect the published API contract. Contract revision: 2. Price update time: not supplied.
Playground
Run sends a real API request. Charges follow the published API contract.
Request example
curl \
'https://api.openany.si/v1/agent-apis/aihot/api/v1/items?limit=5&mode=selected&window=7d' \
-X GET \
-H "Authorization: Bearer $OPENANY_API_KEY" \
-H 'Content-Type: application/json' \
-H 'Accept: application/json' \
-H 'User-Agent: OpenAny-API-Verification/1.0'- Method
- GET
- Endpoint
https://api.openany.si/v1/agent-apis/aihot/api/v1/items- Content type
- application/json
- Authentication
Authorization: Bearer $OPENANY_API_KEY
Request example
curl \
'https://api.openany.si/v1/agent-apis/aihot/api/v1/items?limit=5&mode=selected&window=7d' \
-X GET \
-H "Authorization: Bearer $OPENANY_API_KEY" \
-H 'Content-Type: application/json' \
-H 'Accept: application/json' \
-H 'User-Agent: OpenAny-API-Verification/1.0'Input parameters
Fields in this listing; additional options and input encoding can vary by provider.
| Parameter | Location | Type | Required | Description |
|---|---|---|---|---|
mode | URL query parametersquery | string | No | enum: "selected", "all" |
category | URL query parametersquery | string | No | Current values: ai-models, ai-products, industry, paper, tip, opinion. Use tip for tutorials and opinion for opinions; these match the website categories. |
window | URL query parametersquery | string | No | enum: "24h", "7d" |
by | URL query parametersquery | string | No | Which timeline defines the window and ordering. 'timeline' (default) matches the site's published timeline: historical or explicitly backfilled items can retain their source publication date, and items first found more than 72h after publication retain that date unless the editors admit them as current news, at their admission time. Ordinary new items use discovery time; selected representatives follow their reading group's first appearance. 'published' uses the source publication time, falling back to receipt time when that date is unknown. Every item returns publishedAt (null when unknown) and discoveredAt (receipt time); these attribution timestamps do not replace the opaque pagination cursor. enum: "timeline", "published" |
q | URL query parametersquery | string | No | Leading and trailing whitespace is removed before validation; the remaining value must contain 2 to 200 Unicode code points. minLength: 2 · maxLength: 200 |
limit | URL query parametersquery | integer | No | minimum: 1 · maximum: 100 |
cursor | URL query parametersquery | string | No | Opaque, query-bound keyset cursor for the rolling window. It carries no issue time and does not expire on a timer, but the window keeps moving: once the cursor's own anchor has dropped out of the requested 24h or 7d window it is rejected with invalid_cursor, so restart the query from the first page instead of persisting a cursor across days. Older rows may also naturally leave the window between requests. Use selected snapshot + changes for an exact mirror. |
User-Agent | Request headersheaders | string | No | Keep the client's normal User-Agent and optionally append `aihot-actor/<uuid-v4>` for pseudonymous cross-channel deduplication. It is analytics only, never authentication or authorization. Browsers that cannot set User-Agent remain fully supported but cannot participate in exact Actor deduplication. maxLength: 1024 |
If-None-Match | Request headersheaders | string | No | Previously received ETag for this exact URL. A match returns 304 without a response body. |
Required markers inside a nested object or variant apply when that object or variant is used.
Sample response
Published response example · Documented HTTP 200; not a live result. Published documentation example. Verify the actual response after an approved call.
Documentation example
{
"items": [
{
"attribution": {
"name": "AIHOT",
"url": "https://aihot.news/items/f6dxzur6d4pwjdhvm1x6m5rfp"
},
"category": "industry",
"discoveredAt": "2026-11-01T00:31:11.801Z",
"id": "f6dxzur6d4pwjdhvm1x6m5rfp",
"links": {
"aihot": "https://aihot.news/items/f6dxzur6d4pwjdhvm1x6m5rfp",
"original": "https://mp.weixin.qq.com/s?__biz=MzIyMzA5NjEyMA%3D%3D&mid=2647688028&idx=1&sn=e509269da2e0e0b4d4dfbb121b42204b"
},
"originalTitle": "ChatGPT和Codex要共用额度了，无限聊天的时代结束了。",
"publishedAt": "2026-11-01T00:22:41.000Z",
"reason": "作者以重度用户视角梳理额度合并对聊天和编码习惯的实际冲击，并回溯按条数与按 Token 计费的机制差异，便于理解订阅策略变化的影响。",
"score": 70,
"selected": true,
"source": {
"name": "公众号：数字生命卡兹克"
},
"summary": "作者引述OpenAI凌晨更新的帮助文档称，从12月开始Plus和Pro用户的ChatGPT聊天与Codex用量将合并为同一Token额度，仅Instant聊天不受影响。作者回顾此前按条数计费的历史、一个月内Codex Pro额度先降后恢复的运营反复，以及社区在GitHub上提issue抗议的反应，认为合并与IPO预期下的算力成本压力有关。",
"title": "OpenAI 12月起将ChatGPT与Codex合并为统一Token额度"
},
{
"attribution": {
"name": "AIHOT",
"url": "https://aihot.news/items/yww15c701iat30p8ttjf029ij"
},
"category": "tip",
"discoveredAt": "2026-11-01T00:27:06.100Z",
"id": "yww15c701iat30p8ttjf029ij",
"links": {
"aihot": "https://aihot.news/items/yww15c701iat30p8ttjf029ij",
"original": "https://openrouter.ai/blog/tutorials/ai-code-review/"
},
"originalTitle": "Build an AI Code Reviewer with OpenRouter",
"publishedAt": "2026-11-01T00:00:00.000Z",
"reason": "教程给出在沙箱中运行代码验证 bug 的完整脚本与四模型实测数据，读者可照搬接入 pre-push 钩子或 GitHub Actions。",
"score": 75,
"selected": true,
"source": {
"name": "OpenRouter：Announcements（RSS）"
},
"summary": "OpenRouter 发布教程，介绍一个 233 行、仅用标准库的 review.py，通过 Responses API 组合 Files API、Shell 沙箱工具和 Apply Patch 工具，把变更文件上传到托管 Linux 沙箱，让模型实际运行检查确认 bug 并返回 V4A 补丁。",
"title": "OpenRouter 教程：用 Responses API 构建可在 Linux 沙箱验证 bug 的 AI 代码审查脚本"
},
{
"attribution": {
"name": "AIHOT",
"url": "https://aihot.news/items/dpm21l66z2iizblehsdg09c8t"
},
"category": "opinion",
"discoveredAt": "2026-10-31T23:36:45.752Z",
"id": "dpm21l66z2iizblehsdg09c8t",
"links": {
"aihot": "https://aihot.news/items/dpm21l66z2iizblehsdg09c8t",
"original": "https://www.ithome.com/1/020/633.htm"
},
"originalTitle": "美国白宫科学与技术顾问会议主席：Anthropic 很可能成为资本主义历史最伟大企业",
"publishedAt": "2026-10-31T22:56:28.467Z",
"reason": "萨克斯基于 S-1 财务数据分析 Anthropic 的现金储备与 IPO 融资需求，读者可借此了解其看多逻辑和资本效率论点。",
"score": 79,
"selected": true,
"source": {
"name": "IT之家·人工智能"
},
"summary": "美国白宫科学与技术顾问会议主席戴维·萨克斯在 All-In 播客分析 Anthropic 的 S-1 文件，称其很可能成为资本主义历史上最伟大企业，也可能是回报最高的风险投资项目。",
"title": "美国白宫科技顾问萨克斯称 Anthropic 可能成为资本主义史上最伟大企业"
},
{
"attribution": {
"name": "AIHOT",
"url": "https://aihot.news/items/htfc0ler37j2h4hoqll6jewz3"
},
"category": "industry",
"discoveredAt": "2026-10-31T16:24:39.611Z",
"id": "htfc0ler37j2h4hoqll6jewz3",
"links": {
"aihot": "https://aihot.news/items/htfc0ler37j2h4hoqll6jewz3",
"original": "https://www.ithome.com/1/020/632.htm"
},
"originalTitle": "AI 基建掀起军备竞赛：微软、谷歌、甲骨文等巨头承诺投入超 3 万亿美元",
"publishedAt": "2026-10-31T15:56:00.987Z",
"reason": "原文汇总五巨头财报披露的支出承诺构成和自由现金流变化，读者可以据此看清各家AI基建投入的规模差异与 回收压力。",
"score": 79,
"selected": true,
"source": {
"name": "IT之家·人工智能"
},
"summary": "据彭博社10月31日报道，Alphabet、Meta、微软、亚马逊和甲骨文五大巨头承诺未来数年在数据中心等领域投入超过3万亿美元（约20.01万亿元人民币）。其中谷歌支出承诺超1万亿美元、接近一年前的八倍，Meta超8,000亿美元且近半用于最长分30年支付的租约；甲骨文是首家因投资AI数据中心而自由现金流转负的大型科技公司，预计到2028年恢复正自由现金流。",
"title": "彭博社统计：Alphabet、Meta、微软、亚马逊、甲骨文承诺投入超3万亿美元建AI基础设施"
},
{
"attribution": {
"name": "AIHOT",
"url": "https://aihot.news/items/yqblvh40gus1ssc0rjvawh6fu"
},
"category": "industry",
"discoveredAt": "2026-10-31T03:52:15.963Z",
"id": "yqblvh40gus1ssc0rjvawh6fu",
"links": {
"aihot": "https://aihot.news/items/yqblvh40gus1ssc0rjvawh6fu",
"original": "https://www.ithome.com/1/020/444.htm"
},
"originalTitle": "Anthropic 未来“隐性债务”规模近 9000 亿美元，人类史上最大 IPO 招股文件暗藏细节",
"publishedAt": "2026-10-31T03:25:09.697Z",
"reason": "报道披露了 Anthropic 招股文件中的表外债务细节，可帮助读者理解 AI 基建支出与资产负债表之间的差距。",
"score": 77,
"selected": true,
"source": {
"name": "IT之家·人工智能"
},
"summary": "Anthropic 近日提交 IPO 招股文件，彭博社报道其计划未来在服务器、建筑和电力等领域投入近 9,000 亿美元债务。该公司资产负债表显示 1,175 亿美元负债和 1,120 亿美元现金，而租赁合同及数据中心、电力和 GPU 采购协议等表外义务未直接体现；Anthropic 计划通过增加收入和筹集资金支付这些负债。",
"title": "Anthropic IPO 招股文件披露近 9000 亿美元隐性债务"
}
],
"page": {
"count": 5,
"hasMore": true,
"nextCursor": "it3.eyJhIjoxNzkzNDE4NzM1OTYzLCJpIjoieXFibHZoNDBndXMxc3NjMHJqdmF3aDZmdSIsImMiOiI5MmE3Y2NjYTBmMzkifQ"
},
"query": {
"by": "timeline",
"category": null,
"mode": "selected",
"ordering": "timelineDesc",
"q": null,
"window": "7d"
},
"schemaVersion": 1
}Agent integration
Copy the resource contract without sharing an API key.
View API Markdown
API Markdown
# AIHOT — List recent public AI items
Start here for feeds, widgets and 'what is new' views. Covers the last 7 days only. Send If-None-Match and you get a 304 with an empty body whenever nothing changed. To follow new items, page back with cursor only until you reach an id you already have. Do not use this to maintain a complete local copy of the selected set: it is windowed, so anything older than 7 days silently falls out. Use /api/v1/selected/snapshot plus /api/v1/selected/changes for that.
Documentation: https://openany.si/apis/c15e3897-b4dc-47a7-abf8-a641b9c1b825
Method: GET
Endpoint: https://api.openany.si/v1/agent-apis/aihot/api/v1/items
Price: $0 / call
Provider: aihot
Contract revision: 2
Price source: selected implementation in the OpenAny public API catalog. Price update time: not supplied.
Use OPENANY_API_KEY from the environment. API Key calls use your shared balance.
## Prepared request
```bash
curl \
'https://api.openany.si/v1/agent-apis/aihot/api/v1/items?limit=5&mode=selected&window=7d' \
-X GET \
-H "Authorization: Bearer $OPENANY_API_KEY" \
-H 'Content-Type: application/json' \
-H 'Accept: application/json' \
-H 'User-Agent: OpenAny-API-Verification/1.0'
```
## API contract
```json
{
"resource_type": "api",
"name": "AIHOT — List recent public AI items",
"endpoint": "https://api.openany.si/v1/agent-apis/aihot/api/v1/items",
"method": "GET",
"content_type": "none",
"execution_mode": "sync",
"authentication": {
"type": "bearer",
"environment_variable": "OPENANY_API_KEY"
},
"inputs": [
{
"description": "",
"enum_values": [
"selected",
"all"
],
"location": "query",
"name": "mode",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "Current values: ai-models, ai-products, industry, paper, tip, opinion. Use tip for tutorials and opinion for opinions; these match the website categories.",
"location": "query",
"name": "category",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "",
"enum_values": [
"24h",
"7d"
],
"location": "query",
"name": "window",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "Which timeline defines the window and ordering. 'timeline' (default) matches the site's published timeline: historical or explicitly backfilled items can retain their source publication date, and items first found more than 72h after publication retain that date unless the editors admit them as current news, at their admission time. Ordinary new items use discovery time; selected representatives follow their reading group's first appearance. 'published' uses the source publication time, falling back to receipt time when that date is unknown. Every item returns publishedAt (null when unknown) and discoveredAt (receipt time); these attribution timestamps do not replace the opaque pagination cursor.",
"enum_values": [
"timeline",
"published"
],
"location": "query",
"name": "by",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "Leading and trailing whitespace is removed before validation; the remaining value must contain 2 to 200 Unicode code points.",
"location": "query",
"max_length": 200,
"min_length": 2,
"name": "q",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "",
"location": "query",
"maximum": "100",
"minimum": "1",
"name": "limit",
"nullable": false,
"required": false,
"type": "integer"
},
{
"description": "Opaque, query-bound keyset cursor for the rolling window. It carries no issue time and does not expire on a timer, but the window keeps moving: once the cursor's own anchor has dropped out of the requested 24h or 7d window it is rejected with invalid_cursor, so restart the query from the first page instead of persisting a cursor across days. Older rows may also naturally leave the window between requests. Use selected snapshot + changes for an exact mirror.",
"location": "query",
"name": "cursor",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "Keep the client's normal User-Agent and optionally append `aihot-actor/<uuid-v4>` for pseudonymous cross-channel deduplication. It is analytics only, never authentication or authorization. Browsers that cannot set User-Agent remain fully supported but cannot participate in exact Actor deduplication.",
"location": "header",
"max_length": 1024,
"name": "User-Agent",
"nullable": false,
"required": false,
"type": "string"
},
{
"description": "Previously received ETag for this exact URL. A match returns 304 without a response body.",
"location": "header",
"name": "If-None-Match",
"nullable": false,
"required": false,
"type": "string"
}
],
"billing": {
"currency": "USD",
"mode": "fixed",
"priceMicroUsd": "0",
"rounding": null,
"unit": "call",
"unitQuantity": null
},
"examples": [
{
"http_status": 200,
"name": "Documentation example",
"request": {
"body": null,
"headers": {
"Accept": "application/json",
"User-Agent": "OpenAny-API-Verification/1.0"
},
"path": {},
"query": {
"limit": 5,
"mode": "selected",
"window": "7d"
}
},
"response_body": {
"items": [
{
"attribution": {
"name": "AIHOT",
"url": "https://aihot.news/items/f6dxzur6d4pwjdhvm1x6m5rfp"
},
"category": "industry",
"discoveredAt": "2026-11-01T00:31:11.801Z",
"id": "f6dxzur6d4pwjdhvm1x6m5rfp",
"links": {
"aihot": "https://aihot.news/items/f6dxzur6d4pwjdhvm1x6m5rfp",
"original": "https://mp.weixin.qq.com/s?__biz=MzIyMzA5NjEyMA%3D%3D&mid=2647688028&idx=1&sn=e509269da2e0e0b4d4dfbb121b42204b"
},
"originalTitle": "ChatGPT和Codex要共用额度了，无限聊天的时代结束了。",
"publishedAt": "2026-11-01T00:22:41.000Z",
"reason": "作者以重度用户视角梳理额度合并对聊天和编码习惯的实际冲击，并回溯按条数与按 Token 计费的机制差异，便于理解订阅策略变化的影响。",
"score": 70,
"selected": true,
"source": {
"name": "公众号：数字生命卡兹克"
},
"summary": "作者引述OpenAI凌晨更新的帮助文档称，从12月开始Plus和Pro用户的ChatGPT聊天与Codex用量将合并为同一Token额度，仅Instant聊天不受影响。作者回顾此前按条数计费的历史、一个月内Codex Pro额度先降后恢复的运营反复，以及社区在GitHub上提issue抗议的反应，认为合并与IPO预期下的算力成本压力有关。",
"title": "OpenAI 12月起将ChatGPT与Codex合并为统一Token额度"
},
{
"attribution": {
"name": "AIHOT",
"url": "https://aihot.news/items/yww15c701iat30p8ttjf029ij"
},
"category": "tip",
"discoveredAt": "2026-11-01T00:27:06.100Z",
"id": "yww15c701iat30p8ttjf029ij",
"links": {
"aihot": "https://aihot.news/items/yww15c701iat30p8ttjf029ij",
"original": "https://openrouter.ai/blog/tutorials/ai-code-review/"
},
"originalTitle": "Build an AI Code Reviewer with OpenRouter",
"publishedAt": "2026-11-01T00:00:00.000Z",
"reason": "教程给出在沙箱中运行代码验证 bug 的完整脚本与四模型实测数据，读者可照搬接入 pre-push 钩子或 GitHub Actions。",
"score": 75,
"selected": true,
"source": {
"name": "OpenRouter：Announcements（RSS）"
},
"summary": "OpenRouter 发布教程，介绍一个 233 行、仅用标准库的 review.py，通过 Responses API 组合 Files API、Shell 沙箱工具和 Apply Patch 工具，把变更文件上传到托管 Linux 沙箱，让模型实际运行检查确认 bug 并返回 V4A 补丁。",
"title": "OpenRouter 教程：用 Responses API 构建可在 Linux 沙箱验证 bug 的 AI 代码审查脚本"
},
{
"attribution": {
"name": "AIHOT",
"url": "https://aihot.news/items/dpm21l66z2iizblehsdg09c8t"
},
"category": "opinion",
"discoveredAt": "2026-10-31T23:36:45.752Z",
"id": "dpm21l66z2iizblehsdg09c8t",
"links": {
"aihot": "https://aihot.news/items/dpm21l66z2iizblehsdg09c8t",
"original": "https://www.ithome.com/1/020/633.htm"
},
"originalTitle": "美国白宫科学与技术顾问会议主席：Anthropic 很可能成为资本主义历史最伟大企业",
"publishedAt": "2026-10-31T22:56:28.467Z",
"reason": "萨克斯基于 S-1 财务数据分析 Anthropic 的现金储备与 IPO 融资需求，读者可借此了解其看多逻辑和资本效率论点。",
"score": 79,
"selected": true,
"source": {
"name": "IT之家·人工智能"
},
"summary": "美国白宫科学与技术顾问会议主席戴维·萨克斯在 All-In 播客分析 Anthropic 的 S-1 文件，称其很可能成为资本主义历史上最伟大企业，也可能是回报最高的风险投资项目。",
"title": "美国白宫科技顾问萨克斯称 Anthropic 可能成为资本主义史上最伟大企业"
},
{
"attribution": {
"name": "AIHOT",
"url": "https://aihot.news/items/htfc0ler37j2h4hoqll6jewz3"
},
"category": "industry",
"discoveredAt": "2026-10-31T16:24:39.611Z",
"id": "htfc0ler37j2h4hoqll6jewz3",
"links": {
"aihot": "https://aihot.news/items/htfc0ler37j2h4hoqll6jewz3",
"original": "https://www.ithome.com/1/020/632.htm"
},
"originalTitle": "AI 基建掀起军备竞赛：微软、谷歌、甲骨文等巨头承诺投入超 3 万亿美元",
"publishedAt": "2026-10-31T15:56:00.987Z",
"reason": "原文汇总五巨头财报披露的支出承诺构成和自由现金流变化，读者可以据此看清各家AI基建投入的规模差异与回收压力。",
"score": 79,
"selected": true,
"source": {
"name": "IT之家·人工智能"
},
"summary": "据彭博社10月31日报道，Alphabet、Meta、微软、亚马逊和甲骨文五大巨头承诺未来数年在数据中心等领域投入超过3万亿美元（约20.01万亿元人民币）。其中谷歌支出承诺超1万亿美元、接近一年前的八倍，Meta超8,000亿美元且近半用于最长分30年支付的租约；甲骨文是首家因投资AI数据中心而自由现金流转负的大型科技公司，预计到2028年恢复正自由现金流。",
"title": "彭博社统计：Alphabet、Meta、微软、亚马逊、甲骨文承诺投入超3万亿美元建AI基础设施"
},
{
"attribution": {
"name": "AIHOT",
"url": "https://aihot.news/items/yqblvh40gus1ssc0rjvawh6fu"
},
"category": "industry",
"discoveredAt": "2026-10-31T03:52:15.963Z",
"id": "yqblvh40gus1ssc0rjvawh6fu",
"links": {
"aihot": "https://aihot.news/items/yqblvh40gus1ssc0rjvawh6fu",
"original": "https://www.ithome.com/1/020/444.htm"
},
"originalTitle": "Anthropic 未来“隐性债务”规模近 9000 亿美元，人类史上最大 IPO 招股文件暗藏细节",
"publishedAt": "2026-10-31T03:25:09.697Z",
"reason": "报道披露了 Anthropic 招股文件中的表外债务细节，可帮助读者理解 AI 基建支出与资产负债表之间的差距。",
"score": 77,
"selected": true,
"source": {
"name": "IT之家·人工智能"
},
"summary": "Anthropic 近日提交 IPO 招股文件，彭博社报道其计划未来在服务器、建筑和电力等领域投入近 9,000 亿美元债务。该公司资产负债表显示 1,175 亿美元负债和 1,120 亿美元现金，而租赁合同及数据中心、电力和 GPU 采购协议等表外义务未直接体现；Anthropic 计划通过增加收入和筹集资金支付这些负债。",
"title": "Anthropic IPO 招股文件披露近 9000 亿美元隐性债务"
}
],
"page": {
"count": 5,
"hasMore": true,
"nextCursor": "it3.eyJhIjoxNzkzNDE4NzM1OTYzLCJpIjoieXFibHZoNDBndXMxc3NjMHJqdmF3aDZmdSIsImMiOiI5MmE3Y2NjYTBmMzkifQ"
},
"query": {
"by": "timeline",
"category": null,
"mode": "selected",
"ordering": "timelineDesc",
"q": null,
"window": "7d"
},
"schemaVersion": 1
}
}
]
}
```Error handling
| Status | Next step |
|---|---|
400 | Check the offering and request fields. |
401 / 403 | Verify your credentials and access permissions. |
402 | Inspect the selected access mode and returned payment requirements. |
429 | Respect the returned rate limit and retry guidance. |
5xx | Inspect the error and usage record before retrying a paid operation. |
Documentation example
Published documentation example. Verify the actual response after an approved call.
Prepare your environment
Use a terminal with cURL installed.
Use an OpenAny API key with shared-balance access. Confirm availability and price before running; a call may charge your balance.
Set the key in your terminal using the hidden prompt below. Keep its value out of source files and logs.
Terminal · macOS / Linuxprintf 'OpenAny API key: ' read -r -s OPENANY_API_KEY export OPENANY_API_KEY printf '\n'Run the request
Paste the complete command below into your terminal.
Values to replace before running 9
Review these request fields before running. Keep the published provider and request method unchanged.
modecategory- Current values: ai-models, ai-products, industry, paper, tip, opinion. Use tip for tutorials and opinion for opinions; these match the website categories.
windowby- Which timeline defines the window and ordering. 'timeline' (default) matches the site's published timeline: historical or explicitly backfilled items can retain their source publication date, and items first found more than 72h after publication retain that date unless the editors admit them as current news, at their admission time. Ordinary new items use discovery time; selected representatives follow their reading group's first appearance. 'published' uses the source publication time, falling back to receipt time when that date is unknown. Every item returns publishedAt (null when unknown) and discoveredAt (receipt time); these attribution timestamps do not replace the opaque pagination cursor.
q- Leading and trailing whitespace is removed before validation; the remaining value must contain 2 to 200 Unicode code points.
limitcursor- Opaque, query-bound keyset cursor for the rolling window. It carries no issue time and does not expire on a timer, but the window keeps moving: once the cursor's own anchor has dropped out of the requested 24h or 7d window it is rejected with invalid_cursor, so restart the query from the first page instead of persisting a cursor across days. Older rows may also naturally leave the window between requests. Use selected snapshot + changes for an exact mirror.
User-Agent- Keep the client's normal User-Agent and optionally append `aihot-actor/<uuid-v4>` for pseudonymous cross-channel deduplication. It is analytics only, never authentication or authorization. Browsers that cannot set User-Agent remain fully supported but cannot participate in exact Actor deduplication.
If-None-Match- Previously received ETag for this exact URL. A match returns 304 without a response body.
Terminal · cURLcurl \ 'https://api.openany.si/v1/agent-apis/aihot/api/v1/items?limit=5&mode=selected&window=7d' \ -X GET \ -H "Authorization: Bearer $OPENANY_API_KEY" \ -H 'Content-Type: application/json' \ -H 'Accept: application/json' \ -H 'User-Agent: OpenAny-API-Verification/1.0'Check the response
Published response example · Documented HTTP 200; not a live result.
Sample response · not a live result{ "items": [ { "attribution": { "name": "AIHOT", "url": "https://aihot.news/items/f6dxzur6d4pwjdhvm1x6m5rfp" }, "category": "industry", "discoveredAt": "2026-11-01T00:31:11.801Z", "id": "f6dxzur6d4pwjdhvm1x6m5rfp", "links": { "aihot": "https://aihot.news/items/f6dxzur6d4pwjdhvm1x6m5rfp", "original": "https://mp.weixin.qq.com/s?__biz=MzIyMzA5NjEyMA%3D%3D&mid=2647688028&idx=1&sn=e509269da2e0e0b4d4dfbb121b42204b" }, "originalTitle": "ChatGPT和Codex要共用额度了，无限聊天的时代结束了。", "publishedAt": "2026-11-01T00:22:41.000Z", "reason": "作者以重度用户视角梳理额度合并对聊天和编码习惯的实际冲击，并回溯按条数与按 Token 计费的机制差异，便于理解订阅策略变化的影响。", "score": 70, "selected": true, "source": { "name": "公众号：数字生命卡兹克" }, "summary": "作者引述OpenAI凌晨更新的帮助文档称，从12月开始Plus和Pro用户的ChatGPT聊天与Codex用量将合并为同一Token额度，仅Instant聊天不受影响。作者回顾此前按条数计费的历史、一个月内Codex Pro额度先降后恢复的运营反复，以及社区在GitHub上提issue抗议的反应，认为合并与IPO预期下的算力成本压力有关。", "title": "OpenAI 12月起将ChatGPT与Codex合并为统一Token额度" }, { "attribution": { "name": "AIHOT", "url": "https://aihot.news/items/yww15c701iat30p8ttjf029ij" }, "category": "tip", "discoveredAt": "2026-11-01T00:27:06.100Z", "id": "yww15c701iat30p8ttjf029ij", "links": { "aihot": "https://aihot.news/items/yww15c701iat30p8ttjf029ij", "original": "https://openrouter.ai/blog/tutorials/ai-code-review/" }, "originalTitle": "Build an AI Code Reviewer with OpenRouter", "publishedAt": "2026-11-01T00:00:00.000Z", "reason": "教程给出在沙箱中运行代码验证 bug 的完整脚本与四模型实测数据，读者可照搬接入 pre-push 钩子或 GitHub Actions。", "score": 75, "selected": true, "source": { "name": "OpenRouter：Announcements（RSS）" }, "summary": "OpenRouter 发布教程，介绍一个 233 行、仅用标准库的 review.py，通过 Responses API 组合 Files API、Shell 沙箱工具和 Apply Patch 工具，把变更文件上传到托管 Linux 沙箱，让模型实际运行检查确认 bug 并返回 V4A 补丁。", "title": "OpenRouter 教程：用 Responses API 构建可在 Linux 沙箱验证 bug 的 AI 代码审查脚本" }, { "attribution": { "name": "AIHOT", "url": "https://aihot.news/items/dpm21l66z2iizblehsdg09c8t" }, "category": "opinion", "discoveredAt": "2026-10-31T23:36:45.752Z", "id": "dpm21l66z2iizblehsdg09c8t", "links": { "aihot": "https://aihot.news/items/dpm21l66z2iizblehsdg09c8t", "original": "https://www.ithome.com/1/020/633.htm" }, "originalTitle": "美国白宫科学与技术顾问会议主席：Anthropic 很可能成为资本主义历史最伟大企业", "publishedAt": "2026-10-31T22:56:28.467Z", "reason": "萨克斯基于 S-1 财务数据分析 Anthropic 的现金储备与 IPO 融资需求，读者可借此了解其看多逻辑和资本效率论点。", "score": 79, "selected": true, "source": { "name": "IT之家·人工智能" }, "summary": "美国白宫科学与技术顾问会议主席戴维·萨克斯在 All-In 播客分析 Anthropic 的 S-1 文件，称其很可能成为资本主义历史上最伟大企业，也可能是回报最高的风险投资项目。", "title": "美国白宫科技顾问萨克斯称 Anthropic 可能成为资本主义史上最伟大企业" }, { "attribution": { "name": "AIHOT", "url": "https://aihot.news/items/htfc0ler37j2h4hoqll6jewz3" }, "category": "industry", "discoveredAt": "2026-10-31T16:24:39.611Z", "id": "htfc0ler37j2h4hoqll6jewz3", "links": { "aihot": "https://aihot.news/items/htfc0ler37j2h4hoqll6jewz3", "original": "https://www.ithome.com/1/020/632.htm" }, "originalTitle": "AI 基建掀起军备竞赛：微软、谷歌、甲骨文等巨头承诺投入超 3 万亿美元", "publishedAt": "2026-10-31T15:56:00.987Z", "reason": "原文汇总五巨头财报披露的支出承诺构成和自由现金流变化，读者可以据此看清各家AI基建投入的规模差异与回收压力。", "score": 79, "selected": true, "source": { "name": "IT之家·人工智能" }, "summary": "据彭博社10月31日报道，Alphabet、Meta、微软、亚马逊和甲骨文五大巨头承诺未来数年在数据中心等领域投入超过3万亿美元（约20.01万亿元人民币）。其中谷歌支出承诺超1万亿美元、接近一年前的八倍，Meta超8,000亿美元且近半用于最长分30年支付的租约；甲骨文是首家因投资AI数据中心而自由现金流转负的大型科技公司，预计到2028年恢复正自由现金流。", "title": "彭博社统计：Alphabet、Meta、微软、亚马逊、甲骨文承诺投入超3万亿美元建AI基础设施" }, { "attribution": { "name": "AIHOT", "url": "https://aihot.news/items/yqblvh40gus1ssc0rjvawh6fu" }, "category": "industry", "discoveredAt": "2026-10-31T03:52:15.963Z", "id": "yqblvh40gus1ssc0rjvawh6fu", "links": { "aihot": "https://aihot.news/items/yqblvh40gus1ssc0rjvawh6fu", "original": "https://www.ithome.com/1/020/444.htm" }, "originalTitle": "Anthropic 未来“隐性债务”规模近 9000 亿美元，人类史上最大 IPO 招股文件暗藏细节", "publishedAt": "2026-10-31T03:25:09.697Z", "reason": "报道披露了 Anthropic 招股文件中的表外债务细节，可帮助读者理解 AI 基建支出与资产负债表之间的差距。", "score": 77, "selected": true, "source": { "name": "IT之家·人工智能" }, "summary": "Anthropic 近日提交 IPO 招股文件，彭博社报道其计划未来在服务器、建筑和电力等领域投入近 9,000 亿美元债务。该公司资产负债表显示 1,175 亿美元负债和 1,120 亿美元现金，而租赁合同及数据中心、电力和 GPU 采购协议等表外义务未直接体现；Anthropic 计划通过增加收入和筹集资金支付这些负债。", "title": "Anthropic IPO 招股文件披露近 9000 亿美元隐性债务" } ], "page": { "count": 5, "hasMore": true, "nextCursor": "it3.eyJhIjoxNzkzNDE4NzM1OTYzLCJpIjoieXFibHZoNDBndXMxc3NjMHJqdmF3aDZmdSIsImMiOiI5MmE3Y2NjYTBmMzkifQ" }, "query": { "by": "timeline", "category": null, "mode": "selected", "ordering": "timelineDesc", "q": null, "window": "7d" }, "schemaVersion": 1 }
Loading related APIs…
Common questions
Do I need a separate key for every provider?
Use your OpenAny API key for standard API access. Read it from OPENANY_API_KEY in your environment and keep it out of prompts, source code and logs.
Are these providers interchangeable?
No. Each offering has its own inputs, pricing and response contract. Selecting a catalog offering does not establish automatic routing or fallback. Confirm the service contract before calling.
How is this API billed?
API-key calls use your shared balance at the selected implementation's published rate. Check the billing unit and request-specific pricing rules before making a paid call. Recorded usage determines the final charge under that contract.
Where do the price and contract come from?
The selected implementation publishes its provider, request contract, revision and billing rules through OpenAny's public API catalog. A revision number identifies a contract version, not a price update date. A price update timestamp is not supplied; do not treat a page date as one.
How do OpenAny Balance and x402 differ?
OpenAny Balance uses an API key and one shared balance. Card, USDC and x402 top-ups, card auto top-up and USDC subscriptions fund that balance; available routes appear on the Credits page. Direct x402 is a separate pay-per-request flow, available only on listings that show it and requiring an authorized payment client.
Does Playground send a paid request?
Yes. After you sign in, Run sends a real API request using an active OpenAny API key. Charges follow the published API contract and use your shared balance. Selecting an implementation, editing inputs and viewing sample responses do not send requests.