VGGT-1B
Integracija
vggt-1b
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/vggt-1b?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/vggt-1b?wait=20", {
method: "POST",
headers,
body: JSON.stringify({}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/vggt-1b", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/sl/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.com/v1/mcp \
--header "Authorization: Bearer $DOITONG_API_KEY"
# 2. Your agent calls the "run" tool with:
{
"model_id": "vggt-1b",
"input": {}
}
Pokličite model VGGT-1B (vggt-1b) prek Doitong API. Dokumentacija za agente: https://doitong.com/sl/developers/models/vggt-1b.md
POST https://api.doitong.com/v1/run/vggt-1b?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{}
Če je stanje odgovora "queued" ali "running", pošiljajte poizvedbe GET https://api.doitong.com/v1/requests/REQUEST_ID?wait=20, dokler ni "succeeded"; datoteke so v outputs[].url. POST https://api.doitong.com/v1/quote/vggt-1b z enakim telesom vrne natančno ceno pred zagonom.
Do 1,755 $ na zagon zaračuna se dejanska uporaba, preostanek se vrne Zaženi na tej strani
Vaš novi ključ API. Prikazan je samo zdaj in je že v kodi ter v spodnjem polju ključa API. Hranite ga kot skrivnost: nikoli ga ne vključite v kodo, ki se izvaja v brskalniku.
Tukaj bo vaš prvi rezultat
Spodaj sestavite zahtevo in jo zaženite s svojim ključem API. Izhodi se kopirajo v našo shrambo, kjer se hranijo za vedno ali 7 dni brezplačno.
Ustvari zahtevo
Kontrolniki se ustvarijo iz sheme modela. Koda in cena se posodobita, ko ju spreminjate.
/run/vggt-1b?wait=20
cena → 1,755 $
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/vggt-1b?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/vggt-1b?wait=20", {
method: "POST",
headers,
body: JSON.stringify({}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/vggt-1b", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "run",
"arguments": {
"model_id": "vggt-1b",
"input": {},
"wait_seconds": 20
}
}
}
Zaženi to zahtevo
Vaš ključ ostane v tem brskalniku: pošlje se samo v Doitong API in shrani v localStorage samo, če označite možnost Zapomni si. Pridobi ključ API
O modelu VGGT-1B
Oceni geometrijo iz več pogledov. V `image_urls` podajte največ 48 slik, po želji pa dodajte `video_url`, vzorčen na vsakih `frame_sampling_rate` kadrov. Vrne globinske zemljevide za vsak kader, zunanje in notranje parametre kamere, neobdelane datoteke napovedi ter oblak točk GLB s stožci kamer. `confidence_percentile` in `max_points` določata gostoto oblaka točk.
Parametri
Pošlji kanonično ali izvorno ime, ne obeh. Kanonična imena
image_urlsneobvezno
images
video_urlneobvezno
video
frame_sampling_rateneobvezno
alpha_blend_ontoneobvezno
export_prediction_dataneobvezno
export_depth_mapsneobvezno
export_point_cloudneobvezno
array_encodingneobvezno
exclude_keysneobvezno
confidence_percentileneobvezno
max_pointsneobvezno
enable_safety_checkerneobvezno
Parametri datotek sprejmejo javni https:// URL, podatkovni URI data: do 10 MB ali file_url naložene datoteke. Datoteke
Izhod
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "vggt-1b",
"status": "succeeded",
"created_at": "2026-10-20T12:00:00Z",
"started_at": "2026-10-20T12:00:02Z",
"completed_at": "2026-10-20T12:00:09Z",
"queue_position": null,
"cost": {
"credits": 1755,
"usd": "1.755",
"charged": 1755,
"refunded": 0
},
"input": {},
"output": {
"point_cloud": {
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
"content_type": "image/jpeg",
"file_name": "0-output.jpeg",
"file_size": 1843200
},
"depth_maps": [
{
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
"content_type": "image/jpeg",
"file_name": "0-output.jpeg",
"file_size": 1843200,
"width": 1024,
"height": 768
}
],
"prediction_data": [
{
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
"content_type": "image/jpeg",
"file_name": "0-output.jpeg",
"file_size": 1843200
}
],
"num_frames": 1,
"depth_range": [
1.0
],
"extrinsics": [
[
[
1.0
]
]
],
"intrinsics": [
[
[
1.0
]
]
],
"timings": {}
},
"outputs": [
{
"type": "file",
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
"content_type": "image/jpeg",
"file_size": 1843200,
"stored": true
}
],
"error": null,
"metrics": {
"inference_seconds": 6.8
},
"urls": {
"self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
"cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
}
}
Polja izhoda
- point_cloud
- object {url, content_type, file_name, file_size} | nullIzvoz oblaka točk, vrnjen, ko je `export_point_cloud` true; njegov prizor GLB združuje zlit oblak s stožci kamer.
- depth_maps
- array of object {url, content_type, file_name, file_size, width, height}Izvoz globinskih zemljevidov, na voljo, ko je `export_depth_maps` true. Vnosi sledijo zaporedju izvornih sličic, pri čemer je vsaka sličica predstavljena kot sivinski rastrski PNG z 16-bitno globino.
- prediction_data
- array of object {url, content_type, file_name, file_size}Izvoz surovih napovedi: ko je `export_prediction_data` true, ima vsaka sličica svojo datoteko JSON, datoteke pa sledijo zaporedju sličic.
- num_frames
- integerSkupno število rekonstruiranih sličic, vključno s slikami in sličicami, vzorčenimi iz videa.
- depth_range
- array of numberMeje globine [min, max], uporabljene za kvantizacijo `depth_maps`. Globino obnovite kot min + pixel * (max - min) / 65535.
- extrinsics
- array of array of array of numberZunanje matrike kamera-iz-sveta velikosti 3x4 za vsako sličico; osi OpenCV kažejo desno vzdolž x, navzdol vzdolž y in naprej vzdolž z.
- intrinsics
- array of array of array of numberNotranje matrike modela luknjičaste kamere velikosti 3x3 za vsako sličico, izražene v koordinatah slikovnih pik modelove sličice 518x518.
- timings
- objectPretečeni čas po stenski uri za vsako fazo, v sekundah.
Več modelov: Vid
Za agente AI: ta stran je v obliki Markdown na voljo na https://doitong.com/sl/developers/models/vggt-1b.md. Vsi modeli in vodniki: https://doitong.com/developers/llms.txt