# Agent

## Fast Research Agent

> 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.

```json
{"openapi":"3.1.0","info":{"title":"Nansen API","version":"1.0.0"},"servers":[{"url":"https://api.nansen.ai"}],"security":[{"ApiKeyAuth":[]}],"components":{"securitySchemes":{"ApiKeyAuth":{"type":"apiKey","in":"header","name":"apiKey","description":"API key for authentication"}},"schemas":{"AgentResearchRequest":{"properties":{"text":{"type":"string","minLength":1,"title":"Text","description":"Research query or question for the Nansen AI agent."},"conversation_id":{"anyOf":[{"type":"string"}],"title":"Conversation Id","description":"Optional conversation ID for multi-turn interactions. Returned in the finish event of a previous response. Omit to start a new conversation."}},"type":"object","required":["text"],"title":"AgentResearchRequest","description":"Request model for Agent Research endpoints (fast and expert)."}},"headers":{"XNansenCreditsUsed":{"description":"Number of credits consumed by this API request","schema":{"type":"string"}},"XNansenCreditsRemaining":{"description":"Total credits remaining in the user's account after this request","schema":{"type":"string"}},"PaymentReceipt":{"description":"Base64url-encoded MPP receipt returned on successful paid requests via Authorization: Payment","schema":{"type":"string"}},"RateLimitLimit":{"description":"Combined rate limit across all configured time windows","schema":{"type":"string"}},"RateLimitRemaining":{"description":"Number of requests remaining in the current limiting window","schema":{"type":"string"}},"RateLimitReset":{"description":"Time in seconds until the rate limit window resets","schema":{"type":"string"}},"XRateLimitLimitSecond":{"description":"Maximum requests allowed per second","schema":{"type":"string"}},"XRateLimitRemainingSecond":{"description":"Requests remaining in the current second","schema":{"type":"string"}},"XRateLimitLimitMinute":{"description":"Maximum requests allowed per minute","schema":{"type":"string"}},"XRateLimitRemainingMinute":{"description":"Requests remaining in the current minute","schema":{"type":"string"}},"PaymentRequired":{"description":"Base64-encoded x402 payment options returned on 402 responses for x402 clients","schema":{"type":"string"}},"WWWAuthenticatePayment":{"description":"MPP payment challenge returned on 402 responses, for example `Payment id=\"...\", realm=\"api.nansen.ai\", method=\"tempo\", intent=\"charge\", request=\"...\"`","schema":{"type":"string"}},"RetryAfter":{"description":"Number of seconds to wait before making a new request","schema":{"type":"string"}}},"responses":{"BadRequestError":{"description":"Bad Request - Invalid request parameters or malformed request","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"string"}}}}}},"UnauthorizedError":{"description":"Authentication error - No API key found in request","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"string"}}}}}},"PaymentRequiredError":{"description":"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`.","headers":{"Payment-Required":{"$ref":"#/components/headers/PaymentRequired"},"WWW-Authenticate":{"$ref":"#/components/headers/WWWAuthenticatePayment"}},"content":{"application/json":{"schema":{"type":"object","description":"Problem-details body for x402 or MPP payment challenges."}}}},"ForbiddenError":{"description":"Forbidden - User does not have required subscription tier or has exceeded credit limit","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"string"}}}}}},"NotFoundError":{"description":"Not Found - The requested resource was not found","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"string"}}}}}},"ValidationError":{"description":"Validation error - Invalid request parameters","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"array","items":{"type":"object","properties":{"loc":{"type":"array","items":{"type":"string"}},"msg":{"type":"string"},"type":{"type":"string"}}}}}}}}},"TooManyRequestsError":{"description":"Too Many Requests - Rate limit exceeded","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"string"},"retry_after":{"type":"integer","description":"Seconds to wait before retrying"}}}}},"headers":{"Retry-After":{"$ref":"#/components/headers/RetryAfter"}}},"InternalServerError":{"description":"Internal Server Error - An unexpected error occurred","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"string"}}}}}}}},"paths":{"/api/v1/agent/fast":{"post":{"tags":["Agent"],"summary":"Fast Research Agent","description":"Ask the Nansen AI agent a research question and receive a streamed answer backed by on-chain data. The **fast** variant uses a lighter model optimised for low-latency responses.\n\n**What it helps to answer:**\n\n1. **Which tokens are smart money accumulating right now?**\n2. **What is the current narrative driving activity in DeFi?**\n3. **Which wallets are connected to a specific address?**\n4. **What is the on-chain story behind a recent price move?**\n\n**SSE event types:**\n\nThe response is a `text/event-stream` with the following JSON event types:\n\n| type | payload | description |\n|---|---|---|\n| `delta` | `{\"type\": \"delta\", \"text\": \"…\"}` | Incremental text chunk of the agent's answer. |\n| `tool_call` | `{\"type\": \"tool_call\", \"name\": \"…\"}` | Emitted once per unique Nansen tool the agent invokes. |\n| `finish` | `{\"type\": \"finish\", \"conversation_id\": \"…\", \"tool_calls\": [...]}` | Final event. Contains the `conversation_id` for follow-up requests and the full list of tools used. |\n| `error` | `{\"type\": \"error\", \"error\": \"…\", \"status_code\": …}` | Emitted if the upstream agent service is unavailable or times out. |\n\nThe stream terminates with a `data: [DONE]` sentinel.\n\n**Fast vs Expert:** Use `/agent/fast` for quick factual lookups and simple questions. Use `/agent/expert` when you need deeper multi-step analysis or synthesis across multiple data sources.","operationId":"agent_fast_api_v1_agent_fast_post","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/AgentResearchRequest"}}},"required":true},"responses":{"200":{"description":"Server-Sent Events stream. Each event is a `data: {json}` line. See endpoint description for event schema.","content":{"application/json":{"schema":{}},"text/event-stream":{}},"headers":{"X-Nansen-Credits-Used":{"$ref":"#/components/headers/XNansenCreditsUsed"},"X-Nansen-Credits-Remaining":{"$ref":"#/components/headers/XNansenCreditsRemaining"},"Payment-Receipt":{"$ref":"#/components/headers/PaymentReceipt"},"RateLimit-Limit":{"$ref":"#/components/headers/RateLimitLimit"},"RateLimit-Remaining":{"$ref":"#/components/headers/RateLimitRemaining"},"RateLimit-Reset":{"$ref":"#/components/headers/RateLimitReset"},"X-RateLimit-Limit-Second":{"$ref":"#/components/headers/XRateLimitLimitSecond"},"X-RateLimit-Remaining-Second":{"$ref":"#/components/headers/XRateLimitRemainingSecond"},"X-RateLimit-Limit-Minute":{"$ref":"#/components/headers/XRateLimitLimitMinute"},"X-RateLimit-Remaining-Minute":{"$ref":"#/components/headers/XRateLimitRemainingMinute"}}},"400":{"description":"Bad Request","$ref":"#/components/responses/BadRequestError"},"401":{"description":"Unauthorized","$ref":"#/components/responses/UnauthorizedError"},"402":{"description":"Payment Required","$ref":"#/components/responses/PaymentRequiredError"},"403":{"description":"Forbidden","$ref":"#/components/responses/ForbiddenError"},"404":{"description":"Not Found","$ref":"#/components/responses/NotFoundError"},"422":{"description":"Unprocessable Content","$ref":"#/components/responses/ValidationError"},"429":{"description":"Too Many Requests","$ref":"#/components/responses/TooManyRequestsError"},"500":{"description":"Internal Server Error","$ref":"#/components/responses/InternalServerError"}}}}}}
```

## Expert Research Agent

> Ask the Nansen AI agent a research question and receive a streamed answer backed by on-chain data. The \*\*expert\*\* variant uses a more capable model for deeper, multi-step analysis.\
> \
> \*\*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.

```json
{"openapi":"3.1.0","info":{"title":"Nansen API","version":"1.0.0"},"servers":[{"url":"https://api.nansen.ai"}],"security":[{"ApiKeyAuth":[]}],"components":{"securitySchemes":{"ApiKeyAuth":{"type":"apiKey","in":"header","name":"apiKey","description":"API key for authentication"}},"schemas":{"AgentResearchRequest":{"properties":{"text":{"type":"string","minLength":1,"title":"Text","description":"Research query or question for the Nansen AI agent."},"conversation_id":{"anyOf":[{"type":"string"}],"title":"Conversation Id","description":"Optional conversation ID for multi-turn interactions. Returned in the finish event of a previous response. Omit to start a new conversation."}},"type":"object","required":["text"],"title":"AgentResearchRequest","description":"Request model for Agent Research endpoints (fast and expert)."}},"headers":{"XNansenCreditsUsed":{"description":"Number of credits consumed by this API request","schema":{"type":"string"}},"XNansenCreditsRemaining":{"description":"Total credits remaining in the user's account after this request","schema":{"type":"string"}},"PaymentReceipt":{"description":"Base64url-encoded MPP receipt returned on successful paid requests via Authorization: Payment","schema":{"type":"string"}},"RateLimitLimit":{"description":"Combined rate limit across all configured time windows","schema":{"type":"string"}},"RateLimitRemaining":{"description":"Number of requests remaining in the current limiting window","schema":{"type":"string"}},"RateLimitReset":{"description":"Time in seconds until the rate limit window resets","schema":{"type":"string"}},"XRateLimitLimitSecond":{"description":"Maximum requests allowed per second","schema":{"type":"string"}},"XRateLimitRemainingSecond":{"description":"Requests remaining in the current second","schema":{"type":"string"}},"XRateLimitLimitMinute":{"description":"Maximum requests allowed per minute","schema":{"type":"string"}},"XRateLimitRemainingMinute":{"description":"Requests remaining in the current minute","schema":{"type":"string"}},"PaymentRequired":{"description":"Base64-encoded x402 payment options returned on 402 responses for x402 clients","schema":{"type":"string"}},"WWWAuthenticatePayment":{"description":"MPP payment challenge returned on 402 responses, for example `Payment id=\"...\", realm=\"api.nansen.ai\", method=\"tempo\", intent=\"charge\", request=\"...\"`","schema":{"type":"string"}},"RetryAfter":{"description":"Number of seconds to wait before making a new request","schema":{"type":"string"}}},"responses":{"BadRequestError":{"description":"Bad Request - Invalid request parameters or malformed request","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"string"}}}}}},"UnauthorizedError":{"description":"Authentication error - No API key found in request","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"string"}}}}}},"PaymentRequiredError":{"description":"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`.","headers":{"Payment-Required":{"$ref":"#/components/headers/PaymentRequired"},"WWW-Authenticate":{"$ref":"#/components/headers/WWWAuthenticatePayment"}},"content":{"application/json":{"schema":{"type":"object","description":"Problem-details body for x402 or MPP payment challenges."}}}},"ForbiddenError":{"description":"Forbidden - User does not have required subscription tier or has exceeded credit limit","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"string"}}}}}},"NotFoundError":{"description":"Not Found - The requested resource was not found","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"string"}}}}}},"ValidationError":{"description":"Validation error - Invalid request parameters","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"array","items":{"type":"object","properties":{"loc":{"type":"array","items":{"type":"string"}},"msg":{"type":"string"},"type":{"type":"string"}}}}}}}}},"TooManyRequestsError":{"description":"Too Many Requests - Rate limit exceeded","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"string"},"retry_after":{"type":"integer","description":"Seconds to wait before retrying"}}}}},"headers":{"Retry-After":{"$ref":"#/components/headers/RetryAfter"}}},"InternalServerError":{"description":"Internal Server Error - An unexpected error occurred","content":{"application/json":{"schema":{"type":"object","properties":{"detail":{"type":"string"}}}}}}}},"paths":{"/api/v1/agent/expert":{"post":{"tags":["Agent"],"summary":"Expert Research Agent","description":"Ask the Nansen AI agent a research question and receive a streamed answer backed by on-chain data. The **expert** variant uses a more capable model for deeper, multi-step analysis.\n\n**What it helps to answer:**\n\n1. **Which tokens are smart money accumulating right now?**\n2. **What is the current narrative driving activity in DeFi?**\n3. **Which wallets are connected to a specific address?**\n4. **What is the on-chain story behind a recent price move?**\n\n**SSE event types:**\n\nThe response is a `text/event-stream` with the following JSON event types:\n\n| type | payload | description |\n|---|---|---|\n| `delta` | `{\"type\": \"delta\", \"text\": \"…\"}` | Incremental text chunk of the agent's answer. |\n| `tool_call` | `{\"type\": \"tool_call\", \"name\": \"…\"}` | Emitted once per unique Nansen tool the agent invokes. |\n| `finish` | `{\"type\": \"finish\", \"conversation_id\": \"…\", \"tool_calls\": [...]}` | Final event. Contains the `conversation_id` for follow-up requests and the full list of tools used. |\n| `error` | `{\"type\": \"error\", \"error\": \"…\", \"status_code\": …}` | Emitted if the upstream agent service is unavailable or times out. |\n\nThe stream terminates with a `data: [DONE]` sentinel.\n\n**Fast vs Expert:** Use `/agent/fast` for quick factual lookups and simple questions. Use `/agent/expert` when you need deeper multi-step analysis or synthesis across multiple data sources.","operationId":"agent_expert_api_v1_agent_expert_post","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/AgentResearchRequest"}}},"required":true},"responses":{"200":{"description":"Server-Sent Events stream. Each event is a `data: {json}` line. See endpoint description for event schema.","content":{"application/json":{"schema":{}},"text/event-stream":{}},"headers":{"X-Nansen-Credits-Used":{"$ref":"#/components/headers/XNansenCreditsUsed"},"X-Nansen-Credits-Remaining":{"$ref":"#/components/headers/XNansenCreditsRemaining"},"Payment-Receipt":{"$ref":"#/components/headers/PaymentReceipt"},"RateLimit-Limit":{"$ref":"#/components/headers/RateLimitLimit"},"RateLimit-Remaining":{"$ref":"#/components/headers/RateLimitRemaining"},"RateLimit-Reset":{"$ref":"#/components/headers/RateLimitReset"},"X-RateLimit-Limit-Second":{"$ref":"#/components/headers/XRateLimitLimitSecond"},"X-RateLimit-Remaining-Second":{"$ref":"#/components/headers/XRateLimitRemainingSecond"},"X-RateLimit-Limit-Minute":{"$ref":"#/components/headers/XRateLimitLimitMinute"},"X-RateLimit-Remaining-Minute":{"$ref":"#/components/headers/XRateLimitRemainingMinute"}}},"400":{"description":"Bad Request","$ref":"#/components/responses/BadRequestError"},"401":{"description":"Unauthorized","$ref":"#/components/responses/UnauthorizedError"},"402":{"description":"Payment Required","$ref":"#/components/responses/PaymentRequiredError"},"403":{"description":"Forbidden","$ref":"#/components/responses/ForbiddenError"},"404":{"description":"Not Found","$ref":"#/components/responses/NotFoundError"},"422":{"description":"Unprocessable Content","$ref":"#/components/responses/ValidationError"},"429":{"description":"Too Many Requests","$ref":"#/components/responses/TooManyRequestsError"},"500":{"description":"Internal Server Error","$ref":"#/components/responses/InternalServerError"}}}}}}
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.nansen.ai/api/agent.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.