API Reference

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Responses

Create a grounded response

POST/v1/responses

ModelsExpand Collapse

CollectedSourceSummary = object { author, favicon, image, 14 more } or object { artifact_id, author, content_type, 17 more }

One of the following:

UnionMember0 = object { author, favicon, image, 14 more }

author: string

favicon: string

image: string

published_date: string

query_index: number

query_indices: array of number

result_index: number

score: number

source_type: "web"

Source came from web search.

title: string

url: string

domain_credibility: optional object { label, score }

Domain credibility assessment (1-10 score with label). Separate from LLM-assigned quality score.

label: string

score: number

minimum1

maximum10

explanation: optional string

What this source is, why it is relevant, and why it got its quality score.

meta: optional array of object { kind, model, api_ms, 13 more } or object { kind, model, api_ms, 12 more }

Per-source extraction attempts for admin debug view. One entry per LLM call.

One of the following:

UnionMember0 = object { kind, model, api_ms, 13 more }

kind: "text"

model: string

api_ms: optional number

cache_read_input_tokens: optional number

error: optional string

explanation: optional string

failed_verification_count: optional number

failed_verification_samples: optional array of object { reason, text, score }

reason: string

text: string

score: optional number

input_tokens: optional number

n_snippets: optional number

nonempty_snippet_count: optional number

output_tokens: optional number

quality: optional number

raw_snippet_count: optional number

skipped_for_limit_count: optional number

verified_snippet_count: optional number

UnionMember1 = object { kind, model, api_ms, 12 more }

kind: "image_context"

model: string

api_ms: optional number

cache_read_input_tokens: optional number

error: optional string

failed_verification_count: optional number

failed_verification_samples: optional array of object { reason, text, score }

reason: string

text: string

score: optional number

fetch_ms: optional number

fetched_content_type: optional string

input_tokens: optional number

markitdown_ms: optional number

n_snippets: optional number

output_tokens: optional number

raw_image_context_count: optional number

verified_image_context_count: optional number

model: optional string

Model that produced the final snippets for this source.

providers: optional array of string

Provider names that returned this URL (admin-only).

quality: optional number

Source quality score 0-10 (10 = best). 10 = current primary source (e.g. SEC filing, enacted statute, binding court opinion). 5-6 = secondary/pending (e.g. pending bill, law firm alert). 0 = irrelevant or unreliable (no snippets extracted).

minimum0

maximum10

UnionMember1 = object { artifact_id, author, content_type, 17 more }

artifact_id: string

Artifact ID for uploaded file sources.

author: string

content_type: string

Content type for uploaded file sources.

favicon: string

filename: string

Original filename for uploaded file sources.

image: string

published_date: string

query_index: number

query_indices: array of number

result_index: number

score: number

source_type: "file"

Source came from an uploaded file.

title: string

url: string

domain_credibility: optional object { label, score }

Domain credibility assessment (1-10 score with label). Separate from LLM-assigned quality score.

label: string

score: number

minimum1

maximum10

explanation: optional string

What this source is, why it is relevant, and why it got its quality score.

meta: optional array of object { kind, model, api_ms, 13 more } or object { kind, model, api_ms, 12 more }

Per-source extraction attempts for admin debug view. One entry per LLM call.

One of the following:

UnionMember0 = object { kind, model, api_ms, 13 more }

kind: "text"

model: string

api_ms: optional number

cache_read_input_tokens: optional number

error: optional string

explanation: optional string

failed_verification_count: optional number

failed_verification_samples: optional array of object { reason, text, score }

reason: string

text: string

score: optional number

input_tokens: optional number

n_snippets: optional number

nonempty_snippet_count: optional number

output_tokens: optional number

quality: optional number

raw_snippet_count: optional number

skipped_for_limit_count: optional number

verified_snippet_count: optional number

UnionMember1 = object { kind, model, api_ms, 12 more }

kind: "image_context"

model: string

api_ms: optional number

cache_read_input_tokens: optional number

error: optional string

failed_verification_count: optional number

failed_verification_samples: optional array of object { reason, text, score }

reason: string

text: string

score: optional number

fetch_ms: optional number

fetched_content_type: optional string

input_tokens: optional number

markitdown_ms: optional number

n_snippets: optional number

output_tokens: optional number

raw_image_context_count: optional number

verified_image_context_count: optional number

model: optional string

Model that produced the final snippets for this source.

providers: optional array of string

Provider names that returned this URL (admin-only).

quality: optional number

Source quality score 0-10 (10 = best). 10 = current primary source (e.g. SEC filing, enacted statute, binding court opinion). 5-6 = secondary/pending (e.g. pending bill, law firm alert). 0 = irrelevant or unreliable (no snippets extracted).

minimum0

maximum10

Snippet = object { source_index, text, type, 3 more } or object { end_index, num, source_index, 2 more } or object { caption, context, image_url, 9 more }

One of the following:

UnionMember0 = object { source_index, text, type, 3 more }

source_index: number

text: string

The relevant passage extracted from the source.

type: "text"

verified: boolean

Whether the snippet text was verified as a substring of the source document.

num: optional number

Sequential number assigned to verified snippets (1-based). Unverified snippets have no num.

source_offset: optional number

Character offset of the snippet within the source document. Used for ordering snippets by position.

UnionMember1 = object { end_index, num, source_index, 2 more }

end_index: number

End character offset into source.full_text (exclusive).

num: number

Sequential number assigned to this snippet (1-based). Always present for index snippets.

source_index: number

start_index: number

Start character offset into source.full_text.

type: "index"

UnionMember2 = object { caption, context, image_url, 9 more }

caption: string

The image caption or alt text copied from the source.

context: string

Nearby explanatory context copied verbatim from the source.

image_url: string

The image URL extracted from the source.

source_index: number

type: "image"

verified: boolean

Whether both the caption and context were verified against the source document.

caption_end_index: optional number

End character offset of the verified caption in source.full_text (exclusive).

caption_start_index: optional number

Start character offset of the verified caption in source.full_text.

content_length: optional number

Image file size in bytes, if the reachability probe returned a Content-Length (or Content-Range total).

minimum0

context_end_index: optional number

End character offset of the verified context in source.full_text (exclusive).

context_start_index: optional number

Start character offset of the verified context in source.full_text.

num: optional number

Sequential number assigned to verified snippets (1-based). Unverified snippets have no num.