Skip to content

Exa · Flight and hotel search with live prices

Jinko

Jinko data through the Exa Agent: live round-trip flight fares for a route and dates, hotel rooms and rates for a destination or specific properties, and destination discovery across date windows, cabin classes and budgets. Known limits (verified 2026-09-04): one-way flight searches return no offers from Jinko, so always ask for a round trip; the fare comes back without airline, times or baggage when Jinko's detailed offer lookup is unavailable. Ask in natural language and, for structured output, pass output_schema naming the fields you want from Jinko. Examples: "Cheapest round-trip flights Paris to Tokyo, departing 2026-10-10 and returning 2026-10-24, economy, with airline, fare and baggage." "Hotels in Lisbon for 2026-11-03 to 2026-11-06 under 180 EUR per night, with rates." Price: Exa effort (minimal $0.012, low $0.025, medium $0.10, high $0.50 per run) plus $0.005 per Jinko call; the cost Exa reports is billed, up to max_cost_usd (default $0.125). Usually answers inline within a minute; otherwise returns a run id to read with exa/agent-run-get.

Usage based ExaResearchexa/jinkoListed

Activation pending; your agent will see it as unavailable until then.

Use this tool with your agent

Give this to your agent
Use my connected Agentik MCP server. I want to use the tool exa/jinko (Jinko via Exa: flight and hotel search with live prices). Call inspect_tool with {"tool_id": "exa/jinko"} first and tell me the price before anything runs. Ask me for the inputs it needs; never invent values, IDs or file URLs. When I confirm, call run_tool with tool_id "exa/jinko" and my inputs, follow it with get_run if it is still running, and give me the result and the price Agentik reports. If the tool is unavailable, say so and use discover_tools to propose an alternative.
Show the prompt

Paste it into Claude, ChatGPT or Codex: your agent takes it from there, and shows the price before it runs.

Parameters

NameTypeRequiredDescription
querystringYesWhat you want from Jinko, in natural language. Be explicit about the entities (domains, tickers, company names, routes, dates) and the fields you expect.
output_schemaobjectNoOptional JSON Schema for the structured answer (returned in output.structured). Name each field after the Jinko data you want, e.g. {"type":"object","required":["domain","monthlyVisits"],"properties":{"domain":{"type":"string"},"monthlyVisits":{"type":"number","description":"from Jinko"}}}.
effortstringNoExa Agent effort: minimal $0.012 (one quick lookup), low $0.025 (default), medium $0.10, high $0.50, plus partner calls. Options: minimal, low, medium, high.
max_cost_usdnumberNoCeiling reserved for this run, effort plus Jinko calls (default $0.125, at most $5). The real cost Exa reports is billed, never more than this.

How your agent calls it

First inspect_tool for the current schema and price, then run_tool with the published example after confirming your inputs:

{
  "tool_id": "exa/jinko",
  "input": {
    "query": "Cheapest round-trip economy fare Paris to Lisbon, departing 2027-03-10 and returning 2027-03-17, from Jinko, with the fare in EUR.",
    "effort": "minimal"
  }
}

Price and billing

Price
Usage based
Model
Usage based
Detail
Billed at the cost the provider reports for the call, never above $5. Your agent sees the maximum before running.
  • The provider’s price, 0% markup.
  • One prepaid balance for every provider; your agent sees the price before it runs.
  • Pay for measured usage; unused reservations are released.