> Source: https://ashareapi.com/en/docs/endpoints/agent-research/  ·  Markdown version for LLMs / AI agents

Pro endpoint · Pro

# Async research task (submit · cited report · BYOK) API
 ⭐ Deep research: submit a task, get a task_id, then poll for the result. Flow: POST to submit → receive task_id → poll GET /v1/agent-research/{task_id}. ⭐ Polling does not consume quota (status checks only verify identity — no double billing). Depth tiers (depth): fast — 30–90s, budget 5 calls · standard (default) — 2–5min, budget 12 calls · deep — 5–15min, budget 25 calls. ⚠️ Budget = cap on tool calls (data fetches); the actual value is echoed in the response. 🔑 BYOK — same request-header convention as /v1/agent-ask. ⚠️ Paid tier — Standard (¥29.9) and above.
 Pro `POST /v1/agent-research`
 Signature
```
POST /v1/agent-research?q=%E5%A4%AA%E6%9E%81%E5%AE%9E%E4%B8%9A&depth=standard
```
 One-liner

```
curl "https://api.ashareapi.com/v1/agent-research?q=%E5%A4%AA%E6%9E%81%E5%AE%9E%E4%B8%9A&depth=standard&key=YOUR_KEY"
```
 Parameters: `q * · depth` * = required

## Quick start
 Replace the key below with yours (free endpoints need no key):
 curl

```
# 注：q 的值已做 URL 编码（含 [ ] 空格 等）
# 推荐：Authorization 头（密钥不进日志）
curl -H "Authorization: Bearer YOUR_KEY" \
 "https://api.ashareapi.com/v1/agent-research?q=%E5%A4%AA%E6%9E%81%E5%AE%9E%E4%B8%9A&depth=standard"

# 快速测试：直接浏览器打开（?key= 会留在日志/历史里，别用于生产）
curl "https://api.ashareapi.com/v1/agent-research?q=%E5%A4%AA%E6%9E%81%E5%AE%9E%E4%B8%9A&depth=standard&key=YOUR_KEY"
```
 Python

```
import requests

r = requests.get(
 "https://api.ashareapi.com/v1/agent-research",
 headers={"Authorization": "Bearer YOUR_KEY"},
 params={"q": "太极实业"},
 timeout=30,
)
print(r.json())
```
 JavaScript

```
const r = await fetch("https://api.ashareapi.com/v1/agent-research?q=%E5%A4%AA%E6%9E%81%E5%AE%9E%E4%B8%9A&depth=standard", {
 headers: { Authorization: "Bearer YOUR_KEY" },
});
console.log(await r.json());
```

## Parameters
 |
| | Parameter | Type | Required | Description

| | q | string | Yes | Keyword: a stock name (Chinese works) or a code

| | depth | string | No | Depth: fast / standard (default) / deep — controls the time and tool-call budget.

 `q` string Yes
 Keyword: a stock name (Chinese works) or a code

 `depth` string
 Depth: fast / standard (default) / deep — controls the time and tool-call budget.

## Response fields
 The table below is captured from **real API calls** (not inferred): each row gives the field name, its type and one real sample value, so you can align your parser.
 Located in: `data` Envelope: `ok / endpoint / tier / elapsed_ms / source` Probed: `2026-10-20`
 |
| | Field | Type | Real sample value

| | task_id | str | rs_6e4892f5b72c466f

| | status | str | queued

| | depth | str | standard

 Response
 Unified envelope: `{ ok, endpoint, tier, elapsed_ms, source, data }`
 Rows live in `data`; when upstream returns nothing you get `ok:false` and **the call is not counted**.

 Rate limits & quota
 Free endpoints need no key (anonymous 5/min — 250 bars per request, 100k rows per day; solve one PoW challenge for 15/min). Paid tiers: Trial 30 · Standard 120 · Pro 300 · Unlimited 600 per minute; buyout packs are capped by total calls and never expire.
[See the error code table →](/en/docs/errors)

## FAQ

### General (applies to every endpoint)
 Do these endpoints need an API key?
 **Free endpoints do not**: health, challenge, quote, kline, hot, market-overview and changedist work anonymously. **Paid endpoints do**: send `Authorization: Bearer `. ⚠️ The anonymous allowance is **tiered by caller type**: browsers (humans) get **5/min**; scripts, SDKs and AI Agents (curl, requests, axios, openai user-agent strings) get **2/min** — automated traffic is easier to abuse. Solving one PoW challenge (`GET /v1/challenge`, then send the `X-PoW` header) raises it to **15/min** regardless of type. ⚠️ Also, anonymous calls are capped at **250 bars per request and 100k rows per day** — use an API key for the full 1212 bars or unlimited daily volume.

 Am I charged when the upstream returns nothing or errors?
 **No.** When the upstream fails or returns nothing you get `ok:false` and the charge for that call is **refunded** (total_calls / usage_log / ep_log are rolled back together). Only calls that actually returned data count.

 How fresh is the data?
 Quotes (quote / kline / orderbook / changedist) are **real-time or current session**; financials, shareholders, dividends and events are **within T+1 of upstream disclosure**. The `source` field in every response tells you which data channel actually served it.

 Can I request several stocks in one call?
 **No.** `code` is a single-value parameter — one stock per call. For batches, issue concurrent calls and respect your tier per-minute limit.

 How do I use this from Claude / Cursor / ChatGPT?
 Set up MCP once, then just ask the AI — it calls the endpoint itself. MCP exposes 39 tools covering quotes, financials, screening, sectors and macro.

## Related endpoints
 [Natural-language search with evidence chain (for your own orchestration)](/en/docs/endpoints/agent-search)[Natural-language Q&A with inline citations (BYOK — bring your own model key)](/en/docs/endpoints/agent-ask)[Full-history K-line (10y daily · raw + adjustment factors)](/en/docs/endpoints/kline-full)[Whole-market single-day K-line (all A-shares, 5,000+ in one call)](/en/docs/endpoints/market-kline)[Quant backtest (single-stock live / portfolio precomputed)](/en/docs/endpoints/backtest)[Quant strategy list (20 single-stock + 9 portfolio, with measured performance)](/en/docs/endpoints/strategies)[IP allow-list (lock a key to fixed IPs)](/en/docs/endpoints/ip-whitelist)[Batch backtest (many stocks × many strategies)](/en/docs/endpoints/backtest-batch)

 Use it from an AI Agent?
 Set up MCP once, then just ask the AI — it calls the endpoint itself.

 [MCP setup](/en/mcp)[Pricing](/en/pricing)

 [← Back to the full endpoint reference](/en/endpoints)