Ask Microsoft Copilot (answer with citations)

Sends your prompt to Microsoft Copilot Search (AI Mode on bing.com) as a logged-out visitor and returns its answer as markdown and plain text, with the sources it read and cited (citations: title, url, source, snippet) and the model feed when shown. search_queries is null and related_questions empty: Copilot Search does not show them to logged-out visitors. Some prompts (often shopping) get plain search results instead of an AI answer; those calls fail with 502 and are not charged. Each call is a new conversation. The prompt is sent as-is (max 2,000 characters). Answers take about 15-30 s. Every response includes credits_used: the credits this call cost.

Parameters

Every endpoint also takes fresh, raw, fields (see lean responses and caching).

Example

curl "https://api.api.sh/copilot/v1/ask?prompt=What+is+the+tallest+building+in+Europe%3F" \
  -H "x-api-key: $APISH_KEY"

import os, requests

res = requests.get(
    "https://api.api.sh/copilot/v1/ask",
    params={"prompt": "What is the tallest building in Europe?"},
    headers={"x-api-key": os.environ["APISH_KEY"]},
    timeout=120,
)
res.raise_for_status()
data = res.json()

const url = new URL("https://api.api.sh/copilot/v1/ask");
url.searchParams.set("prompt", "What is the tallest building in Europe?");

const res = await fetch(url, { headers: { "x-api-key": process.env.APISH_KEY } });
if (!res.ok) throw new Error(`${res.status} ${await res.text()}`);
const data = await res.json();

Response

A JSON object with the fields described above, plus raw (the source's own data), cached, fetched_at and credits_used. Errors return {"success": false, "error": "…"} with the HTTP status (see errors). A lookup that ran but found nothing (404) costs the price above; refused calls and errors on our side are free (what's charged).