Answers — AI Grounding

Paid Answers proxy via x402 pay-per-use (HTTP 402).

Prerequisites: This skill requires x402-payment. Complete the setup steps before first use.

Service URLs

Role	Domain
API Provider	https://www.cpbox.io
Facilitator

https://www.cppay.finance |

Endpoint (Agent Interface)

CODEBLOCK0

Payment Flow (x402 Protocol)

1. 1. First request (no PAYMENT-SIGNATURE) -> 402 Payment Required with requirements JSON
2. Client signs (EIP-712) -> INLINECODE2
3. Retry with PAYMENT-SIGNATURE -> Server settles and returns response

With @springmint/x402-payment or x402-sdk-go, payment is automatic.

When to Use

Use Case	Skill	Why
Quick factual answer (raw context)	INLINECODE6	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)

CODEBLOCK1

Streaming with Citations (Single-Search)

CODEBLOCK2

Research Mode

CODEBLOCK3

Using with x402-payment

CLI (AI Agent)

CODEBLOCK4

Payload/Response

OpenAI-compatible chat.completions JSON + SSE streaming (pass-through).

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
INLINECODE20	array	Yes	-	Single user message (exactly 1 message)
INLINECODE21

string | Yes | - | Use "default" | | 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
INLINECODE38	bool	No	INLINECODE39	Enable research mode
INLINECODE40

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
INLINECODE52 requires INLINECODE53	"Blocking response doesn't support 'enableresearch' option"
INLINECODE54 incompatible with INLINECODE55

"Research mode doesn't support 'enablecitations' option" | | enable_citations=true requires stream=true | "Blocking response doesn't support 'enable_citations' option" |

Notes for Agent Usage

• - Use x402-payment to handle the payment handshake automatically, especially for streaming (stream=true).

Response Format

Blocking Response (stream=false, single-search only)

Standard OpenAI-compatible JSON:

CODEBLOCK5

Streaming Response

SSE response with OpenAI-compatible chunks:

CODEBLOCK6

Streaming Tags by Mode

Single-Search (with enable_citations=true)

Tag	Purpose
INLINECODE62	Inline citation references
INLINECODE63

JSON cost/billing data |

Research Mode

Tag	Purpose	Keep?
INLINECODE64	Generated search queries	Debug
INLINECODE65

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:

CODEBLOCK7

Use Cases

• - Chat interface integration: Use this endpoint to get a web-grounded answer payload in OpenAI-compatible format.
• 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