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

Pro endpoint · Pro

# OpenAI Responses API (compatible, BYOK) API
 ⭐ OpenAI Responses-compatible: input accepts a string or message array; instructions is discarded so the data rules cannot be overridden. apiKey = ct-...:sk-...; stream=true returns the 9 standard Responses SSE events (streaming: upstream tokens are forwarded as generated; stream=false returns the full JSON). ⭐ Stock Screener (scanner Agent): model=ashare/scanner@deepseek-flash (Pro ¥99+) returns x_tool_trace. ⚠️ Server-side previous_response_id is not implemented in v1 — put context in input. Paid tier — Pro (¥99) and above.
 Pro `POST /v1/responses`
 Signature
```
POST /v1/responses
```
 One-liner

```
curl "https://api.ashareapi.com/v1/responses?key=YOUR_KEY"
```
 Parameters: `none` * = required

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

```
# 推荐：Authorization 头（密钥不进日志）
curl -H "Authorization: Bearer YOUR_KEY" \
 "https://api.ashareapi.com/v1/responses"

# 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/responses?key=YOUR_KEY"
```
 Python

```
import requests

r = requests.get(
 "https://api.ashareapi.com/v1/responses",
 headers={"Authorization": "Bearer YOUR_KEY"},
 params={},
 timeout=30,
)
print(r.json())
```
 JavaScript

```
const r = await fetch("https://api.ashareapi.com/v1/responses", {
 headers: { Authorization: "Bearer YOUR_KEY" },
});
console.log(await r.json());
```

## 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: `output` Envelope: `id / object / created_at / status / model / output / parallel_tool_calls / tool_choice / tools / temperature / top_p / max_output_tokens / previous_response_id / instructions / metadata / error / incomplete_details / truncation / usage / x_citations / x_citation_check / x_notice` Probed: `2026-10-27`
 |
| | Field | Type | Real sample value

| | id | str | resp_abc123

| | object | str | response

| | status | str | completed

| | model | str | ashare/deepseek-flash

| | output | array | [{"type":"message","role":"assistant","content":[{"type":"output_text","text":"..."}]}]

| | usage | object | {"input_tokens": 6911, "output_tokens": 141, "total_tokens": 7052}

 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)[Anthropic Messages API (compatible)](/en/docs/endpoints/messages)[Scanner snapshots for the current key (read-only; no scanner quota charge)](/en/docs/endpoints/scanner-snapshots)[Stock Screener (scanner Agent): natural-language conditions - + citations + tool trace (BYOK)](/en/docs/endpoints/scanner)[OpenAI Chat Completions (compatible, BYOK)](/en/docs/endpoints/chat-completions)[Async research task (submit · cited report · BYOK)](/en/docs/endpoints/agent-research)[Full-history K-line (10y daily · raw + adjustment factors)](/en/docs/endpoints/kline-full)

 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)