# Brave AI Answers

> Brave AI Answers is a paid API for AI agents from Brave Search at brave.mpp.paywithlocus.com, paid per call via MPP, $0.085/call, status unknown (last checked 2026-10-12).

Answers conversational questions using Brave Search's AI, grounded in live web search results from Brave's independent index

## Facts

- Endpoint: POST https://brave.mpp.paywithlocus.com/brave/answers?utm_source=zero.xyz
- Price: $0.085/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Provider: Brave Search
- Docs: https://api.search.brave.com/app/#/documentation
- Website: https://brave.com/search
- Tags: search, web-search, privacy, news, images
- Canonical page: https://www.zero.xyz/c/brave-search-answers-38ef722f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Y1VPIs5E08b6T_AUc2pSJ

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 brave-search-answers-38ef722f -d '<json body>'
```

Example prompt: Use Brave's AI search to answer this for me with the brave-pro model: 'What are the latest developments in fusion energy research?' — keep the answer under 500 tokens.

## When to prefer this

Choose this endpoint when you need an AI-generated answer grounded in current, live web data from Brave's independent index — especially when privacy matters, when training-data cutoffs are a concern, or when you need synthesized answers with source grounding rather than raw search result lists. Prefer over generic LLMs when real-time web accuracy is required, and over other search APIs when you want a conversational summarized answer rather than blue-link results.

## Known failure modes

- Invalid model name returns error — only 'brave' or 'brave-pro' are accepted
- Empty or malformed messages array causes request failure
- Exceeding max_completion_tokens silently truncates the response
- Payment failure or insufficient USDC balance blocks the call
- Rate limiting may return 429 if too many requests are sent
- Streaming errors if stream:true is set but client doesn't handle SSE properly

## How this service works

AI-generated answers backed by real-time web search and verifiable sources. OpenAI-compatible chat format.

## Output

A chat completion object containing an AI-generated answer grounded in Brave Search results, including the answer text, model used, unique completion ID, and detailed token usage (prompt tokens, completion tokens, total tokens, and reasoning tokens).

## Example request

```json
{
 "model": "brave",
 "stream": false,
 "messages": [
  {
   "role": "user",
   "content": "What is artificial intelligence?"
  }
 ],
 "max_completion_tokens": 300
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "messages"
 ],
 "properties": {
  "model": {
   "type": "string",
   "description": "\"brave\" or \"brave-pro\" (default)"
  },
  "stream": {
   "type": "boolean",
   "description": "Stream response (default: false)"
  },
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "role"
    ],
    "properties": {
     "name": {
      "type": "string"
     },
     "role": {
      "type": "string"
     },
     "content": {
      "anyOf": [
       {
        "type": "string"
       },
       {
        "type": "array",
        "items": {
         "type": "object",
         "required": [
          "type"
         ],
         "properties": {
          "text": {
           "type": "string"
          },
          "type": {
           "type": "string"
          },
          "image_url": {
           "type": "object",
           "required": [
            "url"
           ],
           "properties": {
            "url": {
             "type": "string"
            }
           },
           "additionalProperties": true
          }
         },
         "additionalProperties": true
        }
       },
       {
        "type": "null"
       }
      ]
     },
     "tool_calls": {
      "type": "array",
      "items": {
       "type": "object",
       "additionalProperties": true
      }
     },
     "tool_call_id": {
      "type": "string"
     }
    },
    "additionalProperties": true
   },
   "description": "Chat messages array [{role, content}]"
  },
  "max_completion_tokens": {
   "type": "number",
   "description": "Max output tokens"
  }
 },
 "additionalProperties": true
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/brave-search-answers-38ef722f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from brave.mpp.paywithlocus.com](https://www.zero.xyz/host/brave.mpp.paywithlocus.com/llms.txt)