USE FOR AI-grounded answers via OpenAI-compatible /chat/completions. Two modes: single-search (fast) or deep research (enable_research=true, thorough multi-search). Streaming/blocking. Citations.

Answers — AI Grounding Requires API Key : Get one at https://api.search.brave.com Plan : Included in the Answers plan. See https://api dashboard.search.brave.com/app/subscriptions/subscribe When to Use Use Case Skill Why Quick factual answer (raw context) llm context Single search, returns raw context for YOUR LLM Fast AI answer with citations answers (single search) streaming, citations Thorough multi search deep research answers (research mode) Iterative deep research, synthesized cited answer This endpoint ( /res/v1/chat/completions ) supports two modes: Single search (default): Fast AI grounded answer from a single search. Supports enable citations . Research ( enable research=true ): Multi iteration deep research with progress events and synthesized cited answer. Quick Start (cURL) Blocking (Single Search) Streaming with Citations (Single Search) Research Mode Endpoint Authentication : X Subscription Token: <API KEY header (or Authorization: Bearer <API KEY ) SDK Compatible : Works with OpenAI SDK via base url="https://api.search.brave.com/res/v1" Two Modes Feature Single Search (default) Research ( enable research=true ) Speed Fast Slow Searches 1 Multiple (iterative) Streaming Optional ( stream=true/false ) Required ( stream=true ) Citations enable citations=true (streaming only) Built in (in <answer tag) Progress events No Yes ( <progress tags) Blocking response Yes ( stream=false ) No Parameters Standard Parameters Parameter Type Required Default Description messages array Yes Single user message (exactly 1 message) stream bool No true Enable SSE streaming country string No "US" Search country (2 letter country code or ALL ) language string No "en" Response language safesearch string No "moderate" Search safety level ( off , moderate , strict ) max completion tokens int No null Upper bound on completion tokens enable citations bool No false Include inline citation tags (single search streaming only) web search options object No null OpenAI compatible; search context size : low , medium , high Research Parameters Parameter Type Required Default Description enable research bool No false Enable research mode research allow thinking bool No true Enable extended thinking research maximum number of tokens per query int No 8192 Max tokens per query (1024 16384) research maximum number of queries int No 20 Max total search queries (1 50) research maximum number of iterations int No 4 Max research iterations (1 5) research maximum number of seconds int No 180 Time budget in seconds (1 300) research maximum number of results per query int No 60 Results per search query (1 60) Constraints (IMPORTANT) Constraint Error enable research=true requires stream=true "Blocking response doesn't support 'enable research' option" enable research=true incompatible with enable citations=true "Research mode doesn't support 'enable citations' option" enable citations=true requires stream=true "Blocking response doesn't support 'enable citations' option" OpenAI SDK Usage Blocking (Single Search) Streaming with Citations (Single Search) Research Mode Response Format Blocking Response ( stream=false , single search only) Standard OpenAI compatible JSON: Streaming Response SSE response with OpenAI compatible chunks: Streaming Tags by Mode Single Search (with enable citations=true ) Tag Purpose <citation Inline citation references <usage JSON cost/billing data Research Mode Tag Purpose Keep? <queries Generated search queries Debug <analyzing URL counts (verbose) Debug <thinking URL selection reasoning Debug <progress Stats: time, iterations, queries, URLs analyzed, tokens Monitor <blindspots Knowledge gaps identified Yes <answer Final synthesized answer (only the final answer is emitted; intermediate drafts are dropped) Yes <usage JSON cost/billing data (included at end of streaming response) Yes Usage Tag Format The <usage tag contains JSON stringified cost and token data: Use Cases Chat interface integration : Drop in OpenAI SDK replacement with web grounded answers. Set base url="https://api.search.brave.com/res/v1" . Deep research / comprehensive topic research : Use research mode ( enable research=true ) for complex questions needing multi source synthesis (e.g., "Compare approaches to nuclear fusion"). OpenAI SDK drop in : Same SDK, same streaming format — just change base url and api key . Works with both sync and async clients. Cited answers : Enable enable citations=true in single search mode for inline citation tags, or use research mode which automatically includes citations in its answer. Notes Timeout : Set client timeout to at least 30s for single search, 300s (5 min) for research Single message : The messages array must contain exactly 1 user message Cost monitoring : Parse the <usage tag from streaming responses to track costs