v1
latestOpenAPI 3.1.02026-07-2359362475.0 KBAgent
Interact with the Nansen Research Agent in "fast" mode
Ask the Nansen AI agent a research question and receive a streamed answer backed by on-chain data. The fast variant uses a lighter model optimised for low-latency responses.
What it helps to answer:
- Which tokens are smart money accumulating right now?
- What is the current narrative driving activity in DeFi?
- Which wallets are connected to a specific address?
- What is the on-chain story behind a recent price move?
SSE event types:
The response is a text/event-stream with the following JSON event types:
| type | payload | description |
|---|---|---|
| delta | {"type": "delta", "text": "…"} | Incremental text chunk of the agent's answer. |
| tool_call | {"type": "tool_call", "name": "…"} | Emitted once per unique Nansen tool the agent invokes. |
| finish | {"type": "finish", "conversation_id": "…", "tool_calls": [...]} | Final event. Contains the conversation_id for follow-up requests and the full list of tools used. |
| error | {"type": "error", "error": "…", "status_code": …} | Emitted if the upstream agent service is unavailable or times out. |
The stream terminates with a data: [DONE] sentinel.
Fast vs Expert: Use /agent/fast for quick factual lookups and simple questions. Use /agent/expert when you need deeper multi-step analysis or synthesis across multiple data sources.
post/api/v1/agent/fast
Request body
Response
Server-Sent Events stream. Each event is a data: {json} line. See endpoint description for event schema.
{"stackTrail":"paths:/api/v1/agent/fast:post:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}