API Reference

Complete reference for the Context Link API.

Base URL

https://context-link.ai/api/v1

Authentication

All requests require an API key in the Authorization header:

Authorization: your-api-key-here

Get your API key from Settings.

Endpoints

Context

Query your connected knowledge sources.

GET /api/v1/context?query=your-topic&mode=optional-mode&connection_type=optional-comma-separated-types&response_format=structured

Set response_format=structured to receive the retrieved chunks with citation metadata alongside the rendered markdown. If the parameter is absent or has any other value, the existing markdown response is unchanged.

View full documentation →

Question

Ask a question and receive a concise, cited answer (Pro plan).

GET /api/v1/question?query=your-question&mode=optional-mode&connection_type=optional-comma-separated-types&response_format=structured

Set response_format=structured to receive the generated answer and its cited sources in the same structured schema as /context. If the parameter is absent or has any other value, the existing response is unchanged.

View full documentation →

Save

Save content to Context Link's memory for later retrieval.

POST /api/v1/context/save?namespace=your-namespace

View full documentation →

Custom Connections

Push content from any external service into Context Link (write/push direction). Your AI fetches data, converts it to markdown, and upserts it by uid. Requires a separate bearer token.

View full documentation →

Common responses

Success response (query)

For /context, by default and for every response_format value other than structured:

{
    "message": "Response content",
    "format": "markdown"
}

Both /context and /question use this schema with response_format=structured:

{
  "format": "structured",
  "query": "ticket deflection benchmarks",
  "markdown": "## Support benchmarks\n\nTeams using guided self-service deflect 42% of repeat tickets.",
  "results": [
    {
      "content": "Teams using guided self-service deflect 42% of repeat tickets.",
      "position": 3,
      "rank": 1,
      "score": 0.82,
      "content_sha": "f09d847fc7a20ac8598c5042abd58663ee52d3878bca7693416bb5d4124d5151",
      "sources": [
        {
          "citation": null,
          "uid": "support-benchmarks-2026",
          "title": "Support benchmarks",
          "url": "https://docs.example.com/support-benchmarks",
          "source_updated_at": "2026-08-12T03:14:15Z",
          "connection": {
            "uid": "support-site",
            "type": "Site",
            "name": "docs.example.com",
            "logo_url": "https://context-link.ai/assets/connections/website.svg"
          }
        }
      ]
    }
  ]
}

For /context, markdown is the same string returned as message by default, and results contains the retrieved chunks, each with one source. For /question, markdown is the generated answer returned as answer by default, and results contains at most one result whose content is that answer and whose sources contains its cited sources.

Success response (save)

{
    "message": "Saved",
    "namespace": "your-namespace"
}

Error response

{
    "message": "Error description"
}

Status codes

Code	Description
200	Request successful
201	Content saved successfully
400	Bad request - missing required parameters
401	Unauthorized - invalid or missing API key
402	Payment required - Pro plan needed (question endpoint only)
404	Not found - invalid API key or resource
422	Unprocessable entity - empty request body
429	Too many requests - rate limit or monthly LLM allowance exceeded