# tensorfeed.ai Emerging AI Research Keywords

> tensorfeed.ai Emerging AI Research Keywords is a paid API for AI agents from tensorfeed.ai, paid per call via x402, $0.020000/call, status unknown (last checked 2026-09-15).

Returns the top 50 trending multi-word keyphrases from recent arXiv AI abstracts, ranked by frequency lift over the past 30 days versus a 90-day baseline, with example paper IDs for each phrase.

## Facts

- Endpoint: GET https://tensorfeed.ai/api/premium/research/emerging-keywords
- Price: $0.020000/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tensorfeed-ai-756af7d9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_eFGqNa5_kMMlLdUWxYJxm

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability tensorfeed-ai-756af7d9
```

Example prompt: What AI research terms and multi-word phrases have been surging in arXiv abstracts over the last 30 days compared to baseline — give me the top trending keyphrases with example paper IDs so I can dig into the actual work?

## When to prefer this

Choose this endpoint when you need to identify which new AI research vocabulary, concepts, or techniques are gaining momentum right now — specifically multi-word technical phrases rising above their historical baseline. Prefer this over general paper search when the goal is trend detection and vocabulary surfacing rather than retrieving papers on a known topic. Also useful as a first step before querying for papers on specific themes.

## Known failure modes

- API returns 402 if payment header is missing or USDC balance is insufficient
- Stale data if the daily refresh pipeline has not yet run
- Empty or low-signal results during periods of low arXiv submission volume
- Rate limiting if called too frequently from the same agent
- Keyphrase list may reflect indexing lag for very recent preprints (last 24–48 hours)

## How this service works

Top 50 multi-word keyphrases across recent arXiv AI abstracts ranked by recent-vs-baseline lift (last 30 days frequency over prior 90 days, smoothed). Each keyphrase carries 2-5 example arxiv_ids so an agent can drill into the underlying work. The trend-spotter feed for AI research vocabulary.

## Output

A ranked list of the top 50 trending multi-word keyphrases from arXiv AI abstracts, each with a recent-vs-baseline lift score (30-day frequency divided by smoothed 90-day baseline) and 2–5 example arxiv_ids linking to the underlying papers that use the phrase.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "type": "string",
     "enum": [
      "GET"
     ]
    },
    "queryParams": {
     "type": "object"
    }
   },
   "required": [
    "type",
    "method"
   ],
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   },
   "required": [
    "type"
   ]
  }
 },
 "required": [
  "input"
 ]
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tensorfeed-ai-756af7d9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tensorfeed.ai](https://www.zero.xyz/host/tensorfeed.ai/llms.txt)