Catalog
webPOSTlive

Search-grounded answer

Get a search-grounded answer for a question.

h402 score
$0.01
per call
Success
100%
p50 latency
5.12s
p95 latency
8.00s
Calls (30d)
2

Canonical contract

Proxy path
/api/proxy/web/answer
Method
POST
Selected provider
stableenrich-exa
Settlement
Base USDC · x402

Quickstart

cURL
curl -X POST https://h402-test.hunt.town/api/proxy/web/answer
CLI
h402 call web/answer --json '{ ... }'

Sample input

requiredoptional
{
  "query": "What is retrieval augmented generation?"
}

Sample output

Redacted, from a paid call
{
  "answer": "Retrieval-augmented generation is a pattern where a system retrieves relevant external information before asking a language model to produce an answer, making responses more current and grounded.",
  "citations": [
    {
      "id": "https://en.wikipedia.org/wiki/Retrieval-augmented_generation",
      "title": "Retrieval-augmented generation",
      "url": "https://en.wikipedia.org/wiki/Retrieval-augmented_generation"
    },
    {
      "id": "https://research.ibm.com/blog/retrieval-augmented-generation-RAG",
      "title": "What is retrieval-augmented generation (RAG)? - IBM Research",
      "url": "https://research.ibm.com/blog/retrieval-augmented-generation-RAG"
    },
    {
      "id": "https://github.blog/ai-and-ml/generative-ai/what-is-retrieval-augmented-generation-and-what-does-it-do-for-generative-ai",
      "title": "What is retrieval-augmented generation, and what does it do for generative AI? - The GitHub Blog",
      "url": "https://github.blog/ai-and-ml/generative-ai/what-is-retrieval-augmented-generation-and-what-does-it-do-for-generative-ai"
    }
  ],
  "meta": {
    "provider": "stableenrich-exa",
    "requestId": "redacted"
  }
}

Providers

Candidates competing behind this task. h402 routes each call to the best quality-adjusted option.

stableenrich-exaselected
x402mpptempo
Success
100%
p50
5.12s
Calls
2
100%
$0.01$0.010/call
Last successful call: 11d ago· Aggregated by h402 — not the source provider