API reference · Brave

brave/llm-context

Integrate this model through SandBase's unified API, with production-ready schemas and examples.

APISynchronousOpen model

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/api/brave/llm-context

Model IDbrave/llm-context

Input Schema

16 parameters · 1 required · 15 optional

Parameter	Type	Required	Description
`q`	string	Required	The user’s search query term. Query can not be empty. Maximum of 600 characters and 75 words in the query.
`count`	integer	Optional	The maximum number of search results considered to select the LLM context data. The default is 20 and the maximum is 50. · Min: 1 · Max: 50 · Default: 20
`country`	string	Optional	The search query country, where the results come from. The country string is limited to 2 character country codes of supported countries. · Options: 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 · Default: "US" ARAUATBEBRCACLDKFIFRDEGRHKINIDITJPKRMYMXNLNZNOCNPLPTPHRUSAZAESSECHTWTRGBUSALL
`goggles`	string	Optional	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`	string	Optional	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: pd - Pages aged 24 hours or less. pw - Pages aged 7 days or less. pm - Pages aged 31 days or less. p · Default: ""
`safesearch`	string	Optional	Filters results for adult content. The following values are supported: off - No filtering is done. moderate - Drops adult content from the results used for context. strict - Drops all adult content from the results used for context. When not set, no filtering is applied — except for local recall, wh · Options: off, moderate, strict offmoderatestrict
`spellcheck`	boolean	Optional	Whether to enable spellcheck on the query. · Default: true
`search_lang`	string	Optional	The search language preference. The 2 or more character language code for which the search results are provided. · Options: ar, eu, bn, bg, ca, zh-hans, zh-hant, hr, cs, da, nl, en, en-gb, et, fi, fr, gl, de, el, gu, he, hi, hu, is, it, ja, jp, kn, ko, lv, lt, ms, ml, mr, nb, pl, pt-br, pt-pt, pa, ro, ru, sr, sk, sl, es, sv, ta, te, th, tr, uk, vi · Default: "en" areubnbgcazh-hanszh-hanthrcsdanlenen-gbetfifrgldeelguhehihuisitjajpknkolvltmsmlmrnbplpt-brpt-ptparorusrskslessvtatethtrukvi
`enable_local`	boolean	Optional	Whether to enable local recall. Not setting this value means auto-detect: local recall is used if a location is provided ( X-Loc-Lat with X-Loc-Long , or X-Loc-City ).
`context_threshold_mode`	string	Optional	The mode to use to determine the threshold for including content in context. · Options: disabled, strict, lenient, balanced disabledstrictlenientbalanced
`enable_source_metadata`	boolean	Optional	Enable source metadata enrichment (site_name, favicon, thumbnail, description, fetched_content_timestamp) in the sources attribute of the response. · Default: false
`maximum_number_of_urls`	integer	Optional	Maximum number of different URLs to include in LLM context. · Min: 1 · Max: 50 · Default: 20
`maximum_number_of_tokens`	integer	Optional	Approximate maximum number of tokens to include in context. The default is 8192 and maximum is 32768 . · Min: 1024 · Max: 32768 · Default: 8192
`maximum_number_of_snippets`	integer	Optional	Maximum number of different snippets (or chunks of text) to include in LLM context. The default is 50 and maximum is 256 . · Min: 1 · Max: 256 · Default: 50
`maximum_number_of_tokens_per_url`	integer	Optional	Maximum number of tokens to include per URL. The default is 4096 and maximum is 8192 . · Min: 512 · Max: 8192 · Default: 4096
`maximum_number_of_snippets_per_url`	integer	Optional	Maximum number of snippets to include per URL. The default is 50 and maximum is 100 . · Min: 1 · Max: 100 · Default: 50

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Code Examples

Ready-to-run snippets

const apiKey = process.env.SANDBASE_API_KEY;
const response = await fetch("https://api.sandbase.ai/v1/api/brave/llm-context", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "count": 20,
    "country": "US",
    "freshness": "",
    "spellcheck": true,
    "search_lang": "en",
    "enable_source_metadata": false,
    "maximum_number_of_urls": 20,
    "maximum_number_of_tokens": 8192,
    "maximum_number_of_snippets": 50,
    "maximum_number_of_tokens_per_url": 4096,
    "maximum_number_of_snippets_per_url": 50
  }),
});

if (!response.ok) throw new Error(await response.text());
console.log(await response.json());

← Back to Brave LLM Context