# Nansen AI Agent (Fast)

> Nansen AI Agent (Fast) is a paid API for AI agents from api.nansen.ai, paid per call via x402, $2/call, status unknown (last checked 2026-09-14).

Streams AI-generated research answers backed by Nansen's on-chain data, using a low-latency model optimised for fast responses

## Facts

- Endpoint: GET https://api.nansen.ai/api/v1/agent/fast
- Price: $2/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/nansen-c88c4221
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hCYz5u_4lwfh0g1aMcgM7

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability nansen-c88c4221
```

Example prompt: Ask Nansen which tokens smart money wallets have been accumulating over the last 48 hours, using the fast model for a quick answer.

## When to prefer this

Use this fast variant when you need rapid on-chain research answers with lower latency and can accept a lighter model. Prefer this over the standard agent endpoint when response speed matters more than maximum depth of analysis. Choose Nansen specifically when the question requires wallet labelling, smart money flow data, or DeFi narrative intelligence backed by Nansen's proprietary on-chain dataset.

## Known failure modes

- Invalid or malformed research question returns an error SSE event
- Network timeout during streaming may truncate the response mid-stream
- Rate limiting or payment failure (x402) returns a 402 response before streaming begins
- Ambiguous queries may produce a low-confidence or incomplete answer
- Missing conversation_id for a follow-up may break context continuity

## How this service works

Interact with the Nansen Research Agent in "fast" mode

## Output

A server-sent event (SSE) stream consisting of: incremental delta text chunks forming the AI answer, tool_call events naming each Nansen data tool the agent used, and a final finish event containing the conversation_id for follow-up requests and a full list of all tools invoked. On failure, an error event is emitted with details.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "title": "AgentResearchRequest",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string",
   "title": "Text",
   "examples": [
    "Which tokens are whales accumulating on Ethereum this week?"
   ],
   "minLength": 1,
   "description": "Research query or question for the Nansen AI agent."
  },
  "conversation_id": {
   "anyOf": [
    {
     "type": "string"
    }
   ],
   "title": "Conversation Id",
   "examples": [
    "conv_abc123"
   ],
   "description": "Optional conversation ID for multi-turn interactions. Returned in the finish event of a previous response. Omit to start a new conversation."
  }
 },
 "description": "Request model for Agent Research endpoints (fast and expert)."
}
```

## Response schema (JSON Schema)

```json
{}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nansen-c88c4221/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.nansen.ai](https://www.zero.xyz/host/api.nansen.ai/llms.txt)