Vai al contenuto

Veo 3.1 Fast

Integra

ID del modello veo3.1/fast

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/veo3.1/fast?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Ultra realistic ASMR video of a fresh ripe pineapple being cut into a glass-shaped cylinder. Close-up macro shot, natural kitchen lighting, high detail pineapple texture, visible juice droplets, slow precise knife slicing.\nSound focus: crisp crunchy cutting sound, juicy wet fiber tearing sound, subtle knife sliding on cutting board, natural room ambience, no music, stereo binaural ASMR audio. \n\nVisual detail: yellow golden pineapple flesh, fresh green crown slightly visible on table, wooden cutting board, stainless steel sharp knife, realistic juice splashing slightly when sliced.\nCamera: slow cinematic movement, macro lens, depth of field, focus on knife entering pineapple flesh.\nStyle: hyper realistic, 4K, natural color grading, food photography realism, satisfying ASMR style.",
    "duration": "4s",
    "resolution": "720p",
    "generate_audio": true
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://vit.doitong.com/api/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/veo3.1/fast?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "Ultra realistic ASMR video of a fresh ripe pineapple being cut into a glass-shaped cylinder. Close-up macro shot, natural kitchen lighting, high detail pineapple texture, visible juice droplets, slow precise knife slicing.\nSound focus: crisp crunchy cutting sound, juicy wet fiber tearing sound, subtle knife sliding on cutting board, natural room ambience, no music, stereo binaural ASMR audio. \n\nVisual detail: yellow golden pineapple flesh, fresh green crown slightly visible on table, wooden cutting board, stainless steel sharp knife, realistic juice splashing slightly when sliced.\nCamera: slow cinematic movement, macro lens, depth of field, focus on knife entering pineapple flesh.\nStyle: hyper realistic, 4K, natural color grading, food photography realism, satisfying ASMR style.",
    "duration": "4s",
    "resolution": "720p",
    "generate_audio": true
  }),
});
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://vit.doitong.com/api/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "Ultra realistic ASMR video of a fresh ripe pineapple being cut into a glass-shaped cylinder. Close-up macro shot, natural kitchen lighting, high detail pineapple texture, visible juice droplets, slow precise knife slicing.\nSound focus: crisp crunchy cutting sound, juicy wet fiber tearing sound, subtle knife sliding on cutting board, natural room ambience, no music, stereo binaural ASMR audio. \n\nVisual detail: yellow golden pineapple flesh, fresh green crown slightly visible on table, wooden cutting board, stainless steel sharp knife, realistic juice splashing slightly when sliced.\nCamera: slow cinematic movement, macro lens, depth of field, focus on knife entering pineapple flesh.\nStyle: hyper realistic, 4K, natural color grading, food photography realism, satisfying ASMR style.",
    "duration": "4s",
    "resolution": "720p",
    "generate_audio": True,
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/veo3.1/fast", 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/it/developers/docs/mcp)
claude mcp add --transport http doitong-models https://vit.doitong.com/api/v1/mcp \
  --header "Authorization: Bearer $DOITONG_API_KEY"

# 2. Your agent calls the "run" tool with:
{
  "model_id": "veo3.1/fast",
  "input": {
    "prompt": "Ultra realistic ASMR video of a fresh ripe pineapple being cut into a glass-shaped cylinder. Close-up macro shot, natural kitchen lighting, high detail pineapple texture, visible juice droplets, slow precise knife slicing.\nSound focus: crisp crunchy cutting sound, juicy wet fiber tearing sound, subtle knife sliding on cutting board, natural room ambience, no music, stereo binaural ASMR audio. \n\nVisual detail: yellow golden pineapple flesh, fresh green crown slightly visible on table, wooden cutting board, stainless steel sharp knife, realistic juice splashing slightly when sliced.\nCamera: slow cinematic movement, macro lens, depth of field, focus on knife entering pineapple flesh.\nStyle: hyper realistic, 4K, natural color grading, food photography realism, satisfying ASMR style.",
    "duration": "4s",
    "resolution": "720p",
    "generate_audio": true
  }
}

Chiama il modello Veo 3.1 Fast (veo3.1/fast) tramite Doitong API. Documentazione per gli agenti: https://doitong.com/it/developers/models/veo3.1/fast.md

POST https://vit.doitong.com/api/v1/run/veo3.1/fast?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "prompt": "Ultra realistic ASMR video of a fresh ripe pineapple being cut into a glass-shaped cylinder. Close-up macro shot, natural kitchen lighting, high detail pineapple texture, visible juice droplets, slow precise knife slicing.\nSound focus: crisp crunchy cutting sound, juicy wet fiber tearing sound, subtle knife sliding on cutting board, natural room ambience, no music, stereo binaural ASMR audio. \n\nVisual detail: yellow golden pineapple flesh, fresh green crown slightly visible on table, wooden cutting board, stainless steel sharp knife, realistic juice splashing slightly when sliced.\nCamera: slow cinematic movement, macro lens, depth of field, focus on knife entering pineapple flesh.\nStyle: hyper realistic, 4K, natural color grading, food photography realism, satisfying ASMR style.",
  "duration": "4s",
  "resolution": "720p",
  "generate_audio": true
}

Se lo stato della risposta è "queued" o "running", interroga GET https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20 finché non diventa "succeeded"; i file si trovano in outputs[].url. POST https://vit.doitong.com/api/v1/quote/veo3.1/fast con lo stesso body restituisce il prezzo esatto prima dell'esecuzione.

Questa richiesta: 0,60 $ 600 crediti API Esegui in questa pagina

Ottieni la chiave API

Google Da testo a video Audio nativoOutput 4KVeloce4–8 sfino a 4k #fast#dialogue

Veo 3.1 più veloce ed economico per clip da 4 a 8 secondi con audio.

OpenAPI Markdown

Esempi

Output · ~42 s

PromptUltra realistic ASMR video of a fresh ripe pineapple being cut into a glass-shaped cylinder. Close-up macro shot, natural kitchen lighting, high detail pineapple texture, visible juice droplets, slow precise knife slicing. Sound focus: crisp crunchy cutting sound, juicy wet fiber tearing sound, subtle knife sliding on cutting board, natural room ambience, no music, stereo binaural ASMR audio. Visual detail: yellow golden pineapple flesh, fresh green crown slightly visible on table, wooden cutting board, stainless steel sharp knife, realistic juice splashing slightly when sliced. Camera: slow cinematic movement, macro lens, depth of field, focus on knife entering pineapple flesh. Style: hyper realistic, 4K, natural color grading, food photography realism, satisfying ASMR style.

4s720pgenerate_audio: true0,60 $ · 600 crediti API

Prompt di @Strength04_X su X

Prezzo

Prezzo esatto

a partire da 0,10 $ / secondo

100 crediti API / secondo

8 s ≈ 0,80 $

Questa richiesta: 4 secondi × 0,15 $ 0,60 $ 600 crediti API

Esegui · 0,60 $

Addebitato solo in caso di successo, rimborsato automaticamente in caso di errore.

duration 4 s

resolution

Regole di prezzo

Quando resolution = 4k e generate_audio = true: 0,35 $ / secondo
Quando resolution = 4k: 0,30 $ / secondo
Quando generate_audio = true: 0,15 $ / secondo

Addebitato per secondo di output (duration).

Tempo tipico: ~42 s
Endpoint del preventivo: POST /quote/{id}

Crea una richiesta

I controlli vengono generati dallo schema del modello. Il codice e il prezzo si aggiornano mentre li modifichi.

prompt •obbligatorio 789 / 20000

Descrizione testuale del video desiderato per la generazione.

duration 4 s

Durata del video output.

aspect_ratio predefinito 16:9

Rapporto larghezza-altezza del video generato.

resolution

Risoluzione usata per il video di output.

Avanzate negative_prompt · safety_tolerance · seed · auto_fix

negative_prompt

Prompt negativo usato per orientare la generazione del video.

safety_tolerance predefinito 4

Imposta la tolleranza della moderazione dei contenuti tra il livello meno restrittivo, 6, e quello più rigido, 1, che blocca la maggior parte dei contenuti.

seed

Valore seed che inizializza la generazione di numeri casuali.

POST /run/veo3.1/fast?wait=20 preventivo → 0,60 $

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/veo3.1/fast?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Ultra realistic ASMR video of a fresh ripe pineapple being cut into a glass-shaped cylinder. Close-up macro shot, natural kitchen lighting, high detail pineapple texture, visible juice droplets, slow precise knife slicing.\nSound focus: crisp crunchy cutting sound, juicy wet fiber tearing sound, subtle knife sliding on cutting board, natural room ambience, no music, stereo binaural ASMR audio. \n\nVisual detail: yellow golden pineapple flesh, fresh green crown slightly visible on table, wooden cutting board, stainless steel sharp knife, realistic juice splashing slightly when sliced.\nCamera: slow cinematic movement, macro lens, depth of field, focus on knife entering pineapple flesh.\nStyle: hyper realistic, 4K, natural color grading, food photography realism, satisfying ASMR style.",
    "duration": "4s",
    "resolution": "720p",
    "generate_audio": true
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://vit.doitong.com/api/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/veo3.1/fast?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "Ultra realistic ASMR video of a fresh ripe pineapple being cut into a glass-shaped cylinder. Close-up macro shot, natural kitchen lighting, high detail pineapple texture, visible juice droplets, slow precise knife slicing.\nSound focus: crisp crunchy cutting sound, juicy wet fiber tearing sound, subtle knife sliding on cutting board, natural room ambience, no music, stereo binaural ASMR audio. \n\nVisual detail: yellow golden pineapple flesh, fresh green crown slightly visible on table, wooden cutting board, stainless steel sharp knife, realistic juice splashing slightly when sliced.\nCamera: slow cinematic movement, macro lens, depth of field, focus on knife entering pineapple flesh.\nStyle: hyper realistic, 4K, natural color grading, food photography realism, satisfying ASMR style.",
    "duration": "4s",
    "resolution": "720p",
    "generate_audio": true
  }),
});
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://vit.doitong.com/api/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "Ultra realistic ASMR video of a fresh ripe pineapple being cut into a glass-shaped cylinder. Close-up macro shot, natural kitchen lighting, high detail pineapple texture, visible juice droplets, slow precise knife slicing.\nSound focus: crisp crunchy cutting sound, juicy wet fiber tearing sound, subtle knife sliding on cutting board, natural room ambience, no music, stereo binaural ASMR audio. \n\nVisual detail: yellow golden pineapple flesh, fresh green crown slightly visible on table, wooden cutting board, stainless steel sharp knife, realistic juice splashing slightly when sliced.\nCamera: slow cinematic movement, macro lens, depth of field, focus on knife entering pineapple flesh.\nStyle: hyper realistic, 4K, natural color grading, food photography realism, satisfying ASMR style.",
    "duration": "4s",
    "resolution": "720p",
    "generate_audio": True,
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/veo3.1/fast", 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": "veo3.1/fast",
      "input": {
        "prompt": "Ultra realistic ASMR video of a fresh ripe pineapple being cut into a glass-shaped cylinder. Close-up macro shot, natural kitchen lighting, high detail pineapple texture, visible juice droplets, slow precise knife slicing.\nSound focus: crisp crunchy cutting sound, juicy wet fiber tearing sound, subtle knife sliding on cutting board, natural room ambience, no music, stereo binaural ASMR audio. \n\nVisual detail: yellow golden pineapple flesh, fresh green crown slightly visible on table, wooden cutting board, stainless steel sharp knife, realistic juice splashing slightly when sliced.\nCamera: slow cinematic movement, macro lens, depth of field, focus on knife entering pineapple flesh.\nStyle: hyper realistic, 4K, natural color grading, food photography realism, satisfying ASMR style.",
        "duration": "4s",
        "resolution": "720p",
        "generate_audio": true
      },
      "wait_seconds": 20
    }
  }
}

Esegui questa richiesta

Chiave API

La tua chiave rimane in questo browser: viene inviata solo al Doitong API e salvata in localStorage solo se selezioni Ricorda. Ricorda in questo browser Ottieni una chiave API

Informazioni su Veo 3.1 Fast

Veo 3.1 Fast conserva il realismo, i dialoghi e la generazione audio di Veo, con tempi di rendering più brevi e un prezzo molto più basso, che lo rende una buona scelta predefinita per le iterazioni. 4, 6 o 8 secondi, 16:9 o 9:16, a 720p, 1080p o 4K; l'audio può essere disattivato.

Parametri

NomeTipo PredefinitoConsentiti Descrizione

promptobbligatorio

Tipostring

≤ 20.000 caratteri

Descrizione testuale del video desiderato per la generazione.

aspect_ratiofacoltativo

Tipoenum

Predefinito16:9

16:99:16

Rapporto larghezza-altezza del video generato.

durationfacoltativo

Tipoenum

Predefinito8s

4s6s8s

Durata del video output.

negative_promptfacoltativo

Tipostring | null

Prompt negativo usato per orientare la generazione del video.

resolutionfacoltativo

Tipoenum

Predefinito720p

720p1080p4k

Risoluzione usata per il video di output.

generate_audiofacoltativo

Tipoboolean

Predefinitotrue

Controlla se il video include audio generato.

seedfacoltativo

Tipointeger | null

Valore seed che inizializza la generazione di numeri casuali.

auto_fixfacoltativo

Tipoboolean

Predefinitotrue

Riscrittura automatica dei prompt per tentare di risolvere errori nei controlli delle norme sui contenuti o in altre validazioni.

safety_tolerancefacoltativo

Tipoenum

Predefinito4

123456

Imposta la tolleranza della moderazione dei contenuti tra il livello meno restrittivo, 6, e quello più rigido, 1, che blocca la maggior parte dei contenuti.

obbligatorio

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t

{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "veo3.1/fast",
  "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": 600,
    "usd": "0.60",
    "charged": 600,
    "refunded": 0
  },
  "input": {
    "prompt": "A golden retriever runs along a beach at sunset, waves splashing, slow motion, warm backlight",
    "duration": 6,
    "resolution": "720p"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}

I tuoi file, la tua sceltaOgni outputs[].url è una copia nella nostra archiviazione: conservata per sempre (a pagamento per GB-mese) oppure 7 giorni gratuitamente, in base all'impostazione dell'account o a ?storage=.

Stessa struttura per ogni modellotype, url, content_type, width, height e duration, per immagini, video e audio. output è l'oggetto risultato del modello.

Campi dell'output

video: object {url, content_type, file_name, file_size}Video prodotto dal modello.

Altri modelli: Da testo a video

Per gli agenti AI: questa pagina in Markdown è disponibile all'indirizzo https://doitong.com/it/developers/models/veo3.1/fast.md. Tutti i modelli e le guide: https://doitong.com/developers/llms.txt