---
title: "Interact with the Nansen Research Agent in \"fast\" mode"
method: POST
path: "/api/v1/agent/fast"
tags: ["Agent"]
---

# Interact with the Nansen Research Agent in "fast" mode

`POST /api/v1/agent/fast`

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:**

1. **Which tokens are smart money accumulating right now?**
2. **What is the current narrative driving activity in DeFi?**
3. **Which wallets are connected to a specific address?**
4. **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.

## Request body

- AgentResearchRequest — Request model for Agent Research endpoints (fast and expert).
  - `text` string, required — Research query or question for the Nansen AI agent.
  - `conversation_id` string — Optional conversation ID for multi-turn interactions. Returned in the finish event of a previous response. Omit to start a new conversation.

## Response `200`

Server-Sent Events stream. Each event is a `data: {json}` line. See endpoint description for event schema.

- unknown

## Other responses

- `400` — Bad Request - Invalid request parameters or malformed request
- `401` — Authentication error - No API key found in request
- `402` — Payment Required - This endpoint supports pay-per-request via x402 and MPP. x402 responses advertise payment options in `Payment-Required`; MPP responses advertise a fresh `WWW-Authenticate: Payment ...` challenge. Successful MPP responses may include `Payment-Receipt`.
- `403` — Forbidden - User does not have required subscription tier or has exceeded credit limit
- `404` — Not Found - The requested resource was not found
- `422` — Validation error - Invalid request parameters
- `429` — Too Many Requests - Rate limit exceeded
- `500` — Internal Server Error - An unexpected error occurred

---

[API](https://skmtc.net/nansen/apis/nansen-api.md) · [All operations](https://skmtc.net/nansen/apis/nansen-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/nansen/nansen-api/revisions/02a4d2e7d827/schema)