Vision
Text read of a frame (what's on screen)
Gemini text-only read of a frame. Returns { summary, visible[], affordances[], exits[] } (NO bounding boxes, so use /v1/ground/* for clickable geometry). Metered perceive. Use it to discover what objects are present before choosing anchor labels.
POST
/
v1
/
perceive
Text read of a frame (what's on screen)
curl --request POST \
--url https://api.alakazam.gg/v1/perceive \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"frame_b64": "<string>",
"room_name": "<string>",
"room_description": "<string>"
}
'import requests
url = "https://api.alakazam.gg/v1/perceive"
payload = {
"frame_b64": "<string>",
"room_name": "<string>",
"room_description": "<string>"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({frame_b64: '<string>', room_name: '<string>', room_description: '<string>'})
};
fetch('https://api.alakazam.gg/v1/perceive', 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://api.alakazam.gg/v1/perceive",
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([
'frame_b64' => '<string>',
'room_name' => '<string>',
'room_description' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($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://api.alakazam.gg/v1/perceive"
payload := strings.NewReader("{\n \"frame_b64\": \"<string>\",\n \"room_name\": \"<string>\",\n \"room_description\": \"<string>\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
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://api.alakazam.gg/v1/perceive")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"frame_b64\": \"<string>\",\n \"room_name\": \"<string>\",\n \"room_description\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.alakazam.gg/v1/perceive")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"frame_b64\": \"<string>\",\n \"room_name\": \"<string>\",\n \"room_description\": \"<string>\"\n}"
response = http.request(request)
puts response.read_body{
"summary": "<string>",
"visible": [
"<string>"
],
"affordances": [
"<string>"
],
"exits": [
"<string>"
],
"mock": true
}{
"detail": "<string>",
"errors": [
"<string>"
],
"schemaVersion": "<string>"
}{
"detail": "<string>",
"errors": [
"<string>"
],
"schemaVersion": "<string>"
}{
"detail": "<string>",
"errors": [
"<string>"
],
"schemaVersion": "<string>"
}{
"detail": "<string>",
"errors": [
"<string>"
],
"schemaVersion": "<string>"
}{
"detail": "<string>",
"errors": [
"<string>"
],
"schemaVersion": "<string>"
}{
"detail": "<string>",
"errors": [
"<string>"
],
"schemaVersion": "<string>"
}Authorizations
An app API key, e.g. Authorization: Bearer sk_live_…. Secret (sk_) for writes/sessions; publishable (pk_) is read-only (browser-safe).
Previous
Closed-vocab hotspot detection (pin choices to objects)Detect bounding boxes for the given `expected_choices` labels so you can pin each choice to the object it names. `bbox` is `[x,y,w,h]` in 0-1000 normalized image space. Metered `ground`: one unit per label (capped at 6, the backend's box cap).
Next
⌘I
Text read of a frame (what's on screen)
curl --request POST \
--url https://api.alakazam.gg/v1/perceive \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"frame_b64": "<string>",
"room_name": "<string>",
"room_description": "<string>"
}
'import requests
url = "https://api.alakazam.gg/v1/perceive"
payload = {
"frame_b64": "<string>",
"room_name": "<string>",
"room_description": "<string>"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({frame_b64: '<string>', room_name: '<string>', room_description: '<string>'})
};
fetch('https://api.alakazam.gg/v1/perceive', 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://api.alakazam.gg/v1/perceive",
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([
'frame_b64' => '<string>',
'room_name' => '<string>',
'room_description' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($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://api.alakazam.gg/v1/perceive"
payload := strings.NewReader("{\n \"frame_b64\": \"<string>\",\n \"room_name\": \"<string>\",\n \"room_description\": \"<string>\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
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://api.alakazam.gg/v1/perceive")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"frame_b64\": \"<string>\",\n \"room_name\": \"<string>\",\n \"room_description\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.alakazam.gg/v1/perceive")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"frame_b64\": \"<string>\",\n \"room_name\": \"<string>\",\n \"room_description\": \"<string>\"\n}"
response = http.request(request)
puts response.read_body{
"summary": "<string>",
"visible": [
"<string>"
],
"affordances": [
"<string>"
],
"exits": [
"<string>"
],
"mock": true
}{
"detail": "<string>",
"errors": [
"<string>"
],
"schemaVersion": "<string>"
}{
"detail": "<string>",
"errors": [
"<string>"
],
"schemaVersion": "<string>"
}{
"detail": "<string>",
"errors": [
"<string>"
],
"schemaVersion": "<string>"
}{
"detail": "<string>",
"errors": [
"<string>"
],
"schemaVersion": "<string>"
}{
"detail": "<string>",
"errors": [
"<string>"
],
"schemaVersion": "<string>"
}{
"detail": "<string>",
"errors": [
"<string>"
],
"schemaVersion": "<string>"
}
