Output formats
Three formats
An answer can come back in up to three forms. Each has its own use:
| Field | What it holds | Use it for |
|---|---|---|
text | The answer as plain text, always present on answer engines. | Search, brand matching, diffs between runs. |
markdown | The same answer with its headings, lists, tables, bold and links. | Showing the answer as the user saw it, reading tables row by row. |
html | A link to a snapshot of the page the answer was read from. | Evidence and audits: what the page looked like at that moment. |
Structured parts of an answer, such as sources, citationPills and shoppingCards, are
fields of their own in every format. You don't need to parse them out of the text.
Which engine returns which
| Engine | markdown | html |
|---|---|---|
| ChatGPT | With include.markdown | With include.html: a link to the page |
| Gemini | With include.markdown | Not available (400) |
| Google News | No answer text: results are fields | Not available (400) |
Gemini and Google News have no HTML snapshot: a request that sets include.html on them is refused with a 400 before
anything runs, and nothing is billed. The paused engines' formats are on their
engine pages. The full list of flags per engine is in engine features.
Markdown
markdown keeps the answer's structure: headings, bullet and numbered lists, bold text, links and tables as
Markdown tables. text is derived from it with the markup removed, so the two always hold the same words.
Request it with "include": { "markdown": true }.
HTML snapshots
With include.html, result.html is a link to a copy of the page the answer was read from, taken
when the answer finished. The link needs no API key, so share it only with people who may see the result. Snapshots are
kept as long as the task result, about four days; save a copy if you need it for longer.
Cost
include.markdown and include.html are free on every engine: the request costs the same with or
without them. See credits and billing.