# AIsa Brave LLM Context > AIsa Brave LLM Context is a paid API for AI agents from AIsa MPP Data APIs at api.aisa.one, paid per call via MPP, $0.005/call, status unknown (last checked 2026-10-18). Runs a web search query via Brave and returns LLM-ready summarized context with sources, snippets, and metadata ## Facts - Endpoint: POST https://api.aisa.one/apis/v1/brave/llm/context?utm_source=zero.xyz - Price: $0.005/call - Payment: MPP - Status: unknown - Last checked: 2026-10-18 - Activations on Zero: 0 - Provider: AIsa MPP Data APIs - Website: https://aisa.one - Tags: web-search, financial-data, prediction-markets, weather, travel, data, search - Canonical page: https://www.zero.xyz/c/aisa-mpp-data-apis-aisa-brave-llm-context-53ac8fe6 - Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_S1Rci4gtR31bDOAUpvCMy 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 aisa-mpp-data-apis-aisa-brave-llm-context-53ac8fe6 -d '' ``` Example prompt: Search the web for 'best treatments for type 2 diabetes in 2024' using Brave's LLM context API, returning up to 20 results from the US, filtered to pages from the last month. ## When to prefer this Choose this endpoint when you need web search results pre-formatted for LLM ingestion with rich source metadata (snippets, titles, favicons, ages) rather than raw HTML or full page content. Prefer it over generic search APIs when building RAG pipelines, agentic reasoning loops, or citation-grounded AI responses. It is particularly strong when you need freshness filtering, country-specific results, or Brave's Goggles re-ranking for custom result sets. ## Known failure modes - Empty query (q is blank) returns validation error - Query exceeding 600 characters or 75 words is rejected - Unsupported country code returns error - Count value outside 1-50 range is rejected - Invalid freshness date range format causes error - No results found for obscure or malformed queries returns empty sources map ## How this service works Published reference price: $0.005 USD per successful request. Account-specific pricing and final settlement may differ. ## Output A JSON object containing a 'sources' map keyed by URL, where each source includes the page title, hostname, site name, a query-relevant snippet, favicon URL, thumbnail image info, and page age details (formatted date, ISO timestamp, relative age). Designed to be fed directly into an LLM as grounded context with citations. ## Request schema (JSON Schema) ```json { "type": "object", "title": "LLMContextParameters", "required": [ "q" ], "properties": { "q": { "type": "string", "title": "Q", "maxLength": 600, "minLength": 1, "description": "The user’s search query term. Query can not be empty. Maximum of 600 characters and 75 words in the query." }, "count": { "type": "integer", "title": "Count", "default": 20, "maximum": 50, "minimum": 1, "description": "The maximum number of search results considered to select the LLM context data. The default is 20 and the maximum is 50." }, "country": { "allOf": [ { "enum": [ "AR", "AU", "AT", "BE", "BR", "CA", "CL", "DK", "FI", "FR", "DE", "GR", "HK", "IN", "ID", "IT", "JP", "KR", "MY", "MX", "NL", "NZ", "NO", "CN", "PL", "PT", "PH", "RU", "SA", "ZA", "ES", "SE", "CH", "TW", "TR", "GB", "US", "ALL" ], "type": "string", "title": "SearchCountry" }, { "default": "US" } ], "description": "The search query country, where the results come from. The country string is limited to 2 character country codes of supported countries." }, "goggles": { "anyOf": [ { "type": "string" }, { "type": "array", "items": { "type": "string" } }, { "type": "null" } ], "title": "Goggles", "description": "Goggles act as a custom re-ranking on top of Brave’s search index. The parameter supports both a url where the Goggle is hosted or the definition of the Goggle. For more details, see the Goggles documentation. The parameter can be a single Goggle or a list of up to 3 Goggles." }, "freshness": { "type": "string", "title": "Freshness", "default": "", "examples": [ "", "pm", "2022-04-01to2022-07-30" ], "description": "

Filters search results by page age. The age of a page is determined by the most relevant date reported by the content, such as its published or last modified date. The following values are supported:

\n