Answer
curl --request POST \
--url https://tako.com/api/v1/answer \
--header 'Content-Type: application/json' \
--header 'X-API-Key: <api-key>' \
--data '
{
"query": "Intel vs Nvidia headcount since 2013",
"effort": "fast",
"sources": {
"data": {
"count": 10,
"include_contents": false,
"mode": "inline",
"content_format": "json_compact",
"max_rows": 100,
"node_ids": [
"<string>"
],
"strict": false
},
"web": {
"count": 10,
"include_contents": false,
"include_domains": [
"<string>"
],
"exclude_domains": [
"<string>"
],
"snippet_max_chars": 10000,
"highlights": false,
"article_content_max_chars": 30000,
"published_after": "2023-12-25",
"published_before": "2023-12-25"
}
},
"location": {
"latitude": 0,
"longitude": 0
},
"country_code": "US",
"locale": "en-US",
"timezone": "<string>",
"output_settings": {
"image_dark_mode": true,
"force_refresh": false
},
"include_related": 10,
"output_schema": {}
}
'import requests
url = "https://tako.com/api/v1/answer"
payload = {
"query": "Intel vs Nvidia headcount since 2013",
"effort": "fast",
"sources": {
"data": {
"count": 10,
"include_contents": False,
"mode": "inline",
"content_format": "json_compact",
"max_rows": 100,
"node_ids": ["<string>"],
"strict": False
},
"web": {
"count": 10,
"include_contents": False,
"include_domains": ["<string>"],
"exclude_domains": ["<string>"],
"snippet_max_chars": 10000,
"highlights": False,
"article_content_max_chars": 30000,
"published_after": "2023-12-25",
"published_before": "2023-12-25"
}
},
"location": {
"latitude": 0,
"longitude": 0
},
"country_code": "US",
"locale": "en-US",
"timezone": "<string>",
"output_settings": {
"image_dark_mode": True,
"force_refresh": False
},
"include_related": 10,
"output_schema": {}
}
headers = {
"X-API-Key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
query: 'Intel vs Nvidia headcount since 2013',
effort: 'fast',
sources: {
data: {
count: 10,
include_contents: false,
mode: 'inline',
content_format: 'json_compact',
max_rows: 100,
node_ids: ['<string>'],
strict: false
},
web: {
count: 10,
include_contents: false,
include_domains: ['<string>'],
exclude_domains: ['<string>'],
snippet_max_chars: 10000,
highlights: false,
article_content_max_chars: 30000,
published_after: '2023-12-25',
published_before: '2023-12-25'
}
},
location: {latitude: 0, longitude: 0},
country_code: 'US',
locale: 'en-US',
timezone: '<string>',
output_settings: {image_dark_mode: true, force_refresh: false},
include_related: 10,
output_schema: {}
})
};
fetch('https://tako.com/api/v1/answer', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://tako.com/api/v1/answer",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'query' => 'Intel vs Nvidia headcount since 2013',
'effort' => 'fast',
'sources' => [
'data' => [
'count' => 10,
'include_contents' => false,
'mode' => 'inline',
'content_format' => 'json_compact',
'max_rows' => 100,
'node_ids' => [
'<string>'
],
'strict' => false
],
'web' => [
'count' => 10,
'include_contents' => false,
'include_domains' => [
'<string>'
],
'exclude_domains' => [
'<string>'
],
'snippet_max_chars' => 10000,
'highlights' => false,
'article_content_max_chars' => 30000,
'published_after' => '2023-12-25',
'published_before' => '2023-12-25'
]
],
'location' => [
'latitude' => 0,
'longitude' => 0
],
'country_code' => 'US',
'locale' => 'en-US',
'timezone' => '<string>',
'output_settings' => [
'image_dark_mode' => true,
'force_refresh' => false
],
'include_related' => 10,
'output_schema' => [
]
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"X-API-Key: <api-key>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://tako.com/api/v1/answer"
payload := strings.NewReader("{\n \"query\": \"Intel vs Nvidia headcount since 2013\",\n \"effort\": \"fast\",\n \"sources\": {\n \"data\": {\n \"count\": 10,\n \"include_contents\": false,\n \"mode\": \"inline\",\n \"content_format\": \"json_compact\",\n \"max_rows\": 100,\n \"node_ids\": [\n \"<string>\"\n ],\n \"strict\": false\n },\n \"web\": {\n \"count\": 10,\n \"include_contents\": false,\n \"include_domains\": [\n \"<string>\"\n ],\n \"exclude_domains\": [\n \"<string>\"\n ],\n \"snippet_max_chars\": 10000,\n \"highlights\": false,\n \"article_content_max_chars\": 30000,\n \"published_after\": \"2023-12-25\",\n \"published_before\": \"2023-12-25\"\n }\n },\n \"location\": {\n \"latitude\": 0,\n \"longitude\": 0\n },\n \"country_code\": \"US\",\n \"locale\": \"en-US\",\n \"timezone\": \"<string>\",\n \"output_settings\": {\n \"image_dark_mode\": true,\n \"force_refresh\": false\n },\n \"include_related\": 10,\n \"output_schema\": {}\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-API-Key", "<api-key>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://tako.com/api/v1/answer")
.header("X-API-Key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"query\": \"Intel vs Nvidia headcount since 2013\",\n \"effort\": \"fast\",\n \"sources\": {\n \"data\": {\n \"count\": 10,\n \"include_contents\": false,\n \"mode\": \"inline\",\n \"content_format\": \"json_compact\",\n \"max_rows\": 100,\n \"node_ids\": [\n \"<string>\"\n ],\n \"strict\": false\n },\n \"web\": {\n \"count\": 10,\n \"include_contents\": false,\n \"include_domains\": [\n \"<string>\"\n ],\n \"exclude_domains\": [\n \"<string>\"\n ],\n \"snippet_max_chars\": 10000,\n \"highlights\": false,\n \"article_content_max_chars\": 30000,\n \"published_after\": \"2023-12-25\",\n \"published_before\": \"2023-12-25\"\n }\n },\n \"location\": {\n \"latitude\": 0,\n \"longitude\": 0\n },\n \"country_code\": \"US\",\n \"locale\": \"en-US\",\n \"timezone\": \"<string>\",\n \"output_settings\": {\n \"image_dark_mode\": true,\n \"force_refresh\": false\n },\n \"include_related\": 10,\n \"output_schema\": {}\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://tako.com/api/v1/answer")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"query\": \"Intel vs Nvidia headcount since 2013\",\n \"effort\": \"fast\",\n \"sources\": {\n \"data\": {\n \"count\": 10,\n \"include_contents\": false,\n \"mode\": \"inline\",\n \"content_format\": \"json_compact\",\n \"max_rows\": 100,\n \"node_ids\": [\n \"<string>\"\n ],\n \"strict\": false\n },\n \"web\": {\n \"count\": 10,\n \"include_contents\": false,\n \"include_domains\": [\n \"<string>\"\n ],\n \"exclude_domains\": [\n \"<string>\"\n ],\n \"snippet_max_chars\": 10000,\n \"highlights\": false,\n \"article_content_max_chars\": 30000,\n \"published_after\": \"2023-12-25\",\n \"published_before\": \"2023-12-25\"\n }\n },\n \"location\": {\n \"latitude\": 0,\n \"longitude\": 0\n },\n \"country_code\": \"US\",\n \"locale\": \"en-US\",\n \"timezone\": \"<string>\",\n \"output_settings\": {\n \"image_dark_mode\": true,\n \"force_refresh\": false\n },\n \"include_related\": 10,\n \"output_schema\": {}\n}"
response = http.request(request)
puts response.read_body{
"answer": "<string>",
"request_id": "<string>",
"cards": [
{
"card_id": "<string>",
"title": "<string>",
"description": "<string>",
"semantic_description": "<string>",
"webpage_url": "<string>",
"image_url": "<string>",
"embed_url": "<string>",
"sources": [
{
"source_index": "data",
"source_name": "S&P Global",
"source_description": "<string>",
"url": "https://xignite.com",
"source_text": "<string>"
}
],
"methodologies": [
{
"methodology_name": "Where the Data Comes From - S&P Global",
"methodology_description": "Financial metrics standardized by S&P Global from company regulatory filings, press releases, and restatements."
}
],
"source_indexes": [
"data"
],
"card_type": "<string>",
"relevance": "High",
"content": {
"content_format": "csv",
"cost": 0,
"data": "<string>",
"records": [
{}
],
"dataset": {
"columns": [
{
"name": "<string>",
"type": "string",
"unit": "<string>"
}
],
"rows": [
[
"<string>"
]
],
"total_rows": 123,
"truncated": true,
"ref": "<string>",
"sources": [
{
"name": "<string>",
"index": "data"
}
],
"provenance": "query",
"redacted_cells": {}
},
"card_data": {},
"card_data_schema": {},
"url": "<string>",
"expires_at": "<string>",
"total_rows": 123,
"truncated": false,
"export_pricing": {
"baseline_usd": 123,
"row_cpm_usd": 123,
"max_rows_ceiling": 123,
"premium_row_cpm_usd": {},
"free_rows": 0
},
"manifest": [
{
"name": "<string>",
"metric": "<string>",
"entity": "<string>",
"unit": "<string>",
"dtype": "string",
"premium_class": "person_contact"
}
],
"premium": false,
"premium_rows": {},
"redacted_cells": {}
},
"exportable": false,
"relevance_score": 123,
"nodes": [
{
"id": "<string>",
"type": "metric",
"name": "<string>",
"description": "<string>"
}
],
"metric_definitions": [
{
"name": "Gross Domestic Product (current US$)",
"definition": "<string>"
}
],
"data_freshness": {
"coverage_end": "2026",
"data_as_of": "2026-10-01",
"last_updated": "2026-07-14"
}
}
],
"web_results": [
{
"title": "<string>",
"url": "<string>",
"snippet": "<string>",
"source_name": "<string>",
"publish_date": "<string>",
"content": {
"content_format": "csv",
"cost": 0,
"data": "<string>",
"records": [
{}
],
"dataset": {
"columns": [
{
"name": "<string>",
"type": "string",
"unit": "<string>"
}
],
"rows": [
[
"<string>"
]
],
"total_rows": 123,
"truncated": true,
"ref": "<string>",
"sources": [
{
"name": "<string>",
"index": "data"
}
],
"provenance": "query",
"redacted_cells": {}
},
"card_data": {},
"card_data_schema": {},
"url": "<string>",
"expires_at": "<string>",
"total_rows": 123,
"truncated": false,
"export_pricing": {
"baseline_usd": 123,
"row_cpm_usd": 123,
"max_rows_ceiling": 123,
"premium_row_cpm_usd": {},
"free_rows": 0
},
"manifest": [
{
"name": "<string>",
"metric": "<string>",
"entity": "<string>",
"unit": "<string>",
"dtype": "string",
"premium_class": "person_contact"
}
],
"premium": false,
"premium_rows": {},
"redacted_cells": {}
}
}
],
"usage": {
"total_cost_usd": 123,
"compute": {
"cost_usd": 123
},
"data": {
"cost_usd": 123,
"datasets": 123,
"data_points": 123
}
},
"structured_output": {},
"structured_output_error": {
"code": "arbiter_failed",
"message": "<string>"
}
}{
"error_message": "<string>",
"error_type": "BAD_REQUEST"
}{
"error_message": "<string>",
"error_type": "BAD_REQUEST"
}{
"error_message": "<string>",
"error_type": "BAD_REQUEST"
}{
"error_message": "<string>",
"error_type": "BAD_REQUEST"
}Search Tools
Answer
Get a written answer grounded in Tako knowledge cards and the web
POST
/
v1
/
answer
Answer
curl --request POST \
--url https://tako.com/api/v1/answer \
--header 'Content-Type: application/json' \
--header 'X-API-Key: <api-key>' \
--data '
{
"query": "Intel vs Nvidia headcount since 2013",
"effort": "fast",
"sources": {
"data": {
"count": 10,
"include_contents": false,
"mode": "inline",
"content_format": "json_compact",
"max_rows": 100,
"node_ids": [
"<string>"
],
"strict": false
},
"web": {
"count": 10,
"include_contents": false,
"include_domains": [
"<string>"
],
"exclude_domains": [
"<string>"
],
"snippet_max_chars": 10000,
"highlights": false,
"article_content_max_chars": 30000,
"published_after": "2023-12-25",
"published_before": "2023-12-25"
}
},
"location": {
"latitude": 0,
"longitude": 0
},
"country_code": "US",
"locale": "en-US",
"timezone": "<string>",
"output_settings": {
"image_dark_mode": true,
"force_refresh": false
},
"include_related": 10,
"output_schema": {}
}
'import requests
url = "https://tako.com/api/v1/answer"
payload = {
"query": "Intel vs Nvidia headcount since 2013",
"effort": "fast",
"sources": {
"data": {
"count": 10,
"include_contents": False,
"mode": "inline",
"content_format": "json_compact",
"max_rows": 100,
"node_ids": ["<string>"],
"strict": False
},
"web": {
"count": 10,
"include_contents": False,
"include_domains": ["<string>"],
"exclude_domains": ["<string>"],
"snippet_max_chars": 10000,
"highlights": False,
"article_content_max_chars": 30000,
"published_after": "2023-12-25",
"published_before": "2023-12-25"
}
},
"location": {
"latitude": 0,
"longitude": 0
},
"country_code": "US",
"locale": "en-US",
"timezone": "<string>",
"output_settings": {
"image_dark_mode": True,
"force_refresh": False
},
"include_related": 10,
"output_schema": {}
}
headers = {
"X-API-Key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
query: 'Intel vs Nvidia headcount since 2013',
effort: 'fast',
sources: {
data: {
count: 10,
include_contents: false,
mode: 'inline',
content_format: 'json_compact',
max_rows: 100,
node_ids: ['<string>'],
strict: false
},
web: {
count: 10,
include_contents: false,
include_domains: ['<string>'],
exclude_domains: ['<string>'],
snippet_max_chars: 10000,
highlights: false,
article_content_max_chars: 30000,
published_after: '2023-12-25',
published_before: '2023-12-25'
}
},
location: {latitude: 0, longitude: 0},
country_code: 'US',
locale: 'en-US',
timezone: '<string>',
output_settings: {image_dark_mode: true, force_refresh: false},
include_related: 10,
output_schema: {}
})
};
fetch('https://tako.com/api/v1/answer', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://tako.com/api/v1/answer",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'query' => 'Intel vs Nvidia headcount since 2013',
'effort' => 'fast',
'sources' => [
'data' => [
'count' => 10,
'include_contents' => false,
'mode' => 'inline',
'content_format' => 'json_compact',
'max_rows' => 100,
'node_ids' => [
'<string>'
],
'strict' => false
],
'web' => [
'count' => 10,
'include_contents' => false,
'include_domains' => [
'<string>'
],
'exclude_domains' => [
'<string>'
],
'snippet_max_chars' => 10000,
'highlights' => false,
'article_content_max_chars' => 30000,
'published_after' => '2023-12-25',
'published_before' => '2023-12-25'
]
],
'location' => [
'latitude' => 0,
'longitude' => 0
],
'country_code' => 'US',
'locale' => 'en-US',
'timezone' => '<string>',
'output_settings' => [
'image_dark_mode' => true,
'force_refresh' => false
],
'include_related' => 10,
'output_schema' => [
]
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"X-API-Key: <api-key>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://tako.com/api/v1/answer"
payload := strings.NewReader("{\n \"query\": \"Intel vs Nvidia headcount since 2013\",\n \"effort\": \"fast\",\n \"sources\": {\n \"data\": {\n \"count\": 10,\n \"include_contents\": false,\n \"mode\": \"inline\",\n \"content_format\": \"json_compact\",\n \"max_rows\": 100,\n \"node_ids\": [\n \"<string>\"\n ],\n \"strict\": false\n },\n \"web\": {\n \"count\": 10,\n \"include_contents\": false,\n \"include_domains\": [\n \"<string>\"\n ],\n \"exclude_domains\": [\n \"<string>\"\n ],\n \"snippet_max_chars\": 10000,\n \"highlights\": false,\n \"article_content_max_chars\": 30000,\n \"published_after\": \"2023-12-25\",\n \"published_before\": \"2023-12-25\"\n }\n },\n \"location\": {\n \"latitude\": 0,\n \"longitude\": 0\n },\n \"country_code\": \"US\",\n \"locale\": \"en-US\",\n \"timezone\": \"<string>\",\n \"output_settings\": {\n \"image_dark_mode\": true,\n \"force_refresh\": false\n },\n \"include_related\": 10,\n \"output_schema\": {}\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-API-Key", "<api-key>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://tako.com/api/v1/answer")
.header("X-API-Key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"query\": \"Intel vs Nvidia headcount since 2013\",\n \"effort\": \"fast\",\n \"sources\": {\n \"data\": {\n \"count\": 10,\n \"include_contents\": false,\n \"mode\": \"inline\",\n \"content_format\": \"json_compact\",\n \"max_rows\": 100,\n \"node_ids\": [\n \"<string>\"\n ],\n \"strict\": false\n },\n \"web\": {\n \"count\": 10,\n \"include_contents\": false,\n \"include_domains\": [\n \"<string>\"\n ],\n \"exclude_domains\": [\n \"<string>\"\n ],\n \"snippet_max_chars\": 10000,\n \"highlights\": false,\n \"article_content_max_chars\": 30000,\n \"published_after\": \"2023-12-25\",\n \"published_before\": \"2023-12-25\"\n }\n },\n \"location\": {\n \"latitude\": 0,\n \"longitude\": 0\n },\n \"country_code\": \"US\",\n \"locale\": \"en-US\",\n \"timezone\": \"<string>\",\n \"output_settings\": {\n \"image_dark_mode\": true,\n \"force_refresh\": false\n },\n \"include_related\": 10,\n \"output_schema\": {}\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://tako.com/api/v1/answer")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"query\": \"Intel vs Nvidia headcount since 2013\",\n \"effort\": \"fast\",\n \"sources\": {\n \"data\": {\n \"count\": 10,\n \"include_contents\": false,\n \"mode\": \"inline\",\n \"content_format\": \"json_compact\",\n \"max_rows\": 100,\n \"node_ids\": [\n \"<string>\"\n ],\n \"strict\": false\n },\n \"web\": {\n \"count\": 10,\n \"include_contents\": false,\n \"include_domains\": [\n \"<string>\"\n ],\n \"exclude_domains\": [\n \"<string>\"\n ],\n \"snippet_max_chars\": 10000,\n \"highlights\": false,\n \"article_content_max_chars\": 30000,\n \"published_after\": \"2023-12-25\",\n \"published_before\": \"2023-12-25\"\n }\n },\n \"location\": {\n \"latitude\": 0,\n \"longitude\": 0\n },\n \"country_code\": \"US\",\n \"locale\": \"en-US\",\n \"timezone\": \"<string>\",\n \"output_settings\": {\n \"image_dark_mode\": true,\n \"force_refresh\": false\n },\n \"include_related\": 10,\n \"output_schema\": {}\n}"
response = http.request(request)
puts response.read_body{
"answer": "<string>",
"request_id": "<string>",
"cards": [
{
"card_id": "<string>",
"title": "<string>",
"description": "<string>",
"semantic_description": "<string>",
"webpage_url": "<string>",
"image_url": "<string>",
"embed_url": "<string>",
"sources": [
{
"source_index": "data",
"source_name": "S&P Global",
"source_description": "<string>",
"url": "https://xignite.com",
"source_text": "<string>"
}
],
"methodologies": [
{
"methodology_name": "Where the Data Comes From - S&P Global",
"methodology_description": "Financial metrics standardized by S&P Global from company regulatory filings, press releases, and restatements."
}
],
"source_indexes": [
"data"
],
"card_type": "<string>",
"relevance": "High",
"content": {
"content_format": "csv",
"cost": 0,
"data": "<string>",
"records": [
{}
],
"dataset": {
"columns": [
{
"name": "<string>",
"type": "string",
"unit": "<string>"
}
],
"rows": [
[
"<string>"
]
],
"total_rows": 123,
"truncated": true,
"ref": "<string>",
"sources": [
{
"name": "<string>",
"index": "data"
}
],
"provenance": "query",
"redacted_cells": {}
},
"card_data": {},
"card_data_schema": {},
"url": "<string>",
"expires_at": "<string>",
"total_rows": 123,
"truncated": false,
"export_pricing": {
"baseline_usd": 123,
"row_cpm_usd": 123,
"max_rows_ceiling": 123,
"premium_row_cpm_usd": {},
"free_rows": 0
},
"manifest": [
{
"name": "<string>",
"metric": "<string>",
"entity": "<string>",
"unit": "<string>",
"dtype": "string",
"premium_class": "person_contact"
}
],
"premium": false,
"premium_rows": {},
"redacted_cells": {}
},
"exportable": false,
"relevance_score": 123,
"nodes": [
{
"id": "<string>",
"type": "metric",
"name": "<string>",
"description": "<string>"
}
],
"metric_definitions": [
{
"name": "Gross Domestic Product (current US$)",
"definition": "<string>"
}
],
"data_freshness": {
"coverage_end": "2026",
"data_as_of": "2026-10-01",
"last_updated": "2026-07-14"
}
}
],
"web_results": [
{
"title": "<string>",
"url": "<string>",
"snippet": "<string>",
"source_name": "<string>",
"publish_date": "<string>",
"content": {
"content_format": "csv",
"cost": 0,
"data": "<string>",
"records": [
{}
],
"dataset": {
"columns": [
{
"name": "<string>",
"type": "string",
"unit": "<string>"
}
],
"rows": [
[
"<string>"
]
],
"total_rows": 123,
"truncated": true,
"ref": "<string>",
"sources": [
{
"name": "<string>",
"index": "data"
}
],
"provenance": "query",
"redacted_cells": {}
},
"card_data": {},
"card_data_schema": {},
"url": "<string>",
"expires_at": "<string>",
"total_rows": 123,
"truncated": false,
"export_pricing": {
"baseline_usd": 123,
"row_cpm_usd": 123,
"max_rows_ceiling": 123,
"premium_row_cpm_usd": {},
"free_rows": 0
},
"manifest": [
{
"name": "<string>",
"metric": "<string>",
"entity": "<string>",
"unit": "<string>",
"dtype": "string",
"premium_class": "person_contact"
}
],
"premium": false,
"premium_rows": {},
"redacted_cells": {}
}
}
],
"usage": {
"total_cost_usd": 123,
"compute": {
"cost_usd": 123
},
"data": {
"cost_usd": 123,
"datasets": 123,
"data_points": 123
}
},
"structured_output": {},
"structured_output_error": {
"code": "arbiter_failed",
"message": "<string>"
}
}{
"error_message": "<string>",
"error_type": "BAD_REQUEST"
}{
"error_message": "<string>",
"error_type": "BAD_REQUEST"
}{
"error_message": "<string>",
"error_type": "BAD_REQUEST"
}{
"error_message": "<string>",
"error_type": "BAD_REQUEST"
}Notes
- To authenticate, you’ll need a Tako API key. It’s best practice to store it as an environment variable to avoid hardcoding sensitive credentials in your code.
- Answer retrieves the same results as Search and adds a written
answergrounded in them. It takes the same request body as Search — the response adds the synthesizedansweralongside the cards and web results. - Use Answer when you want prose to show a user; use Search when you only need the underlying cards and web results.
Answer replaces the legacy Grounding endpoint. New integrations should use
POST /v1/answer.Choosing sources
sources controls where the answer is grounded — an object whose keys are the sources to ground in. A source is used only if its key is present; omit sources to use the default (both sources, 5 results each):
{ "data": {} }— grounded in Tako’s curated knowledge graph.{ "web": {} }— grounded in the live web.{ "data": {}, "web": {} }— both (same as omittingsources).
tako is accepted as a synonym for data.
Each source takes optional per-source settings: count (1–20, default 5) and include_contents (inline the underlying data).Authorizations
Body
application/json
Request for POST /api/v1/answer.
Natural language search query.
Minimum string length:
1Pattern:
\SExample:
"Intel vs Nvidia headcount since 2013"
Search effort level: 'fast', 'instant', or 'deep'.
Available options:
fast, instant, deep Per-source settings. The search includes an index only if its key is present. Omit it and Tako searches data and web with no counts set. Tako accepts the legacy key 'tako' as a synonym for 'data'.
Show child attributes
Show child attributes
Optional coordinates of the end user. Resolves the location for implicit-location queries (for example, weather) and, when timezone is absent, the timezone Tako renders preview images in. An explicit location in the query overrides these coordinates.
Show child attributes
Show child attributes
ISO 3166-1 alpha-2 country code for localization.
BCP-47 locale tag for language and formatting.
IANA timezone (for example, 'America/New_York') Tako renders preview images in. Defaults to the zone at location when you send coordinates. Card text keeps each surface's own timezone.
Settings that control the response shape.
Show child attributes
Show child attributes
Applies to POST /v3/search only. Return follow-up query suggestions in related. Omit this field to disable them. The value sets the maximum number of suggestions, from 1 to 20. POST /v1/answer accepts this field but ignores it: the answer response has no related field.
Required range:
1 <= x <= 20JSON Schema for structured output. Tako fills it from the same evidence it uses to write answer, and returns it in structured_output. Requires effort 'fast' or 'deep'; on 'instant' the request returns 400. Supported subset: the object, array, string, number, integer, and boolean types, plus items, enum, required, description, and additionalProperties: false. A type may be nullable as ["number", "null"], which is how you let Tako signal 'no evidence' rather than filling a zero. title, examples, format, and default are accepted and ignored — they constrain nothing. Caps: 16KB total, depth 5, 64 properties, 512 characters per description. Violations return 400. If Tako can't fill the schema, structured_output is absent and structured_output_error says why — the answer and the cards still return.
Response
Synthesized answer grounded in Tako results, web results, or both
Response for POST /api/v1/answer: the synthesized answer plus the retrieval behind it.
Synthesized text answer.
Tako cards backing the answer; cards[0] is the lead card — the best one to show alongside the answer.
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Usage for one metered request. total_cost_usd is always present (the
total quoted charge). compute and data are the additive breakdown;
each appears only where it applies. total_cost_usd always equals the sum
of the components that appear.
Show child attributes
Show child attributes
Your output_schema, filled. Absent when the request carried no output_schema, or when Tako couldn't fill it — check structured_output_error.
Why structured_output is absent. Present only on a structured request that failed.
Show child attributes
Show child attributes