VGGT-1B
Comhtháthú
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/ga/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": {}
}
Glaoigh ar an tsamhail VGGT-1B (vggt-1b) tríd an Doitong API. Doiciméid do ghníomhairí: https://doitong.com/ga/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
{}
Má tá stádas an fhreagra "queued" nó "running", seiceáil GET https://api.doitong.com/v1/requests/REQUEST_ID?wait=20 arís go dtí go mbeidh sé "succeeded"; tá na comhaid in outputs[].url. Seolann POST https://api.doitong.com/v1/quote/vggt-1b leis an gcorp céanna an praghas beacht roimh an rith.
Suas le $1.755 in aghaidh an rith gearrtar táille de réir na húsáide iarbhír, aisíoctar an fuílleach Rith ar an leathanach seo
D’eochair API nua. Taispeántar anois é amháin agus tá sé sa chód agus i réimse eochair API thíos cheana féin. Coinnigh faoi rún é: ná cuir i gcód é a ritheann i mbrabhsálaí.
Beidh do chéad toradh anseo
Tóg iarratas thíos agus rith é le d’eochair API. Cóipeáiltear na haschuir chuig ár stóráil, coinnithe go deo nó ar feadh 7 lá saor in aisce.
Tóg iarratas
Gintear na rialtáin ó scéim na samhla. Nuashonraítear an cód agus an praghas de réir mar a athraíonn tú iad.
/run/vggt-1b?wait=20
luachan → $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
}
}
}
Rith an t-iarratas seo
Fanann d'eochair sa bhrabhsálaí seo: seoltar chuig Doitong API amháin í agus sábháiltear (localStorage) í ach amháin má chuireann tú tic le Meabhraigh. Faigh eochair API
Maidir le VGGT-1B
Measann sé céimseata ó ilradhairc. Tabhair suas le 48 íomhá in `image_urls`, agus cuir `video_url` leis más mian leat, sampláilte gach `frame_sampling_rate` fráma. Filleann sé léarscáileanna doimhneachta in aghaidh an fhráma, seachtracha agus inmheánacha an cheamara, comhaid amh tuartha, agus scamall pointí GLB le cóin cheamara. Rialaíonn `confidence_percentile` agus `max_points` dlús an scamaill pointí.
Paraiméadair
Seol an t-ainm canónach nó an t-ainm dúchasach, ní an dá cheann. Ainmneacha canónacha
image_urlsroghnach
images
video_urlroghnach
video
frame_sampling_rateroghnach
alpha_blend_ontoroghnach
export_prediction_dataroghnach
export_depth_mapsroghnach
export_point_cloudroghnach
array_encodingroghnach
exclude_keysroghnach
confidence_percentileroghnach
max_pointsroghnach
enable_safety_checkerroghnach
Glacann paraiméadair chomhaid le URL poiblí https://, URI data: suas le 10 MB, nó file_url uaslódála. Comhaid
Aschur
{
"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"
}
}
Réimsí aschuir
- point_cloud
- object {url, content_type, file_name, file_size} | nullEaspórtáil scamall pointí a chuirtear ar ais nuair atá `export_point_cloud` fíor; comhcheanglaíonn a radharc GLB an scamall comhleáite le cóin cheamara.
- depth_maps
- array of object {url, content_type, file_name, file_size, width, height}Easpórtáil léarscáile doimhneachta atá ar fáil nuair atá `export_depth_maps` fíor. Leanann na hiontrálacha seicheamh na bhfrámaí foinseacha, agus léirítear gach fráma mar raster PNG liathscála ag doimhneacht 16-giotán.
- prediction_data
- array of object {url, content_type, file_name, file_size}Easpórtáil tuartha amh: nuair atá `export_prediction_data` fíor, bíonn a chomhad JSON féin ag gach fráma, agus leanann na comhaid seicheamh na bhfrámaí.
- num_frames
- integerLíon iomlán na bhfrámaí athchruthaithe, lena n-áirítear íomhánna agus frámaí sampláilte ón bhfíseán.
- depth_range
- array of numberTeorainneacha doimhneachta [min, max] a úsáidtear do chainníochtú `depth_maps`. Aisghabh doimhneacht mar min + pixel * (max - min) / 65535.
- extrinsics
- array of array of array of numberMaitrísí seachtracha ceamara ón domhan, méid 3x4, do gach fráma; díríonn aiseanna OpenCV ar dheis feadh x, síos feadh y, agus ar aghaidh feadh z.
- intrinsics
- array of array of array of numberMaitrísí intreacha pollphionna, méid 3x3, do gach fráma, léirithe i gcomhordanáidí picteilíní fhráma 518x518 na samhla.
- timings
- objectAm iarbhír caite do gach céim, i soicind.
Tuilleadh samhlacha: Fís
Do ghníomhairí AI: tá an leathanach seo mar Markdown ag https://doitong.com/ga/developers/models/vggt-1b.md. Gach samhail agus treoir: https://doitong.com/developers/llms.txt