Pronts per cumenzar

Svelta partenza

Mussar sco Markdown Actualisà 2026-10-22

Efectues tia emprima generaziun en paucs minuts. Tut ils 1 496 models acceptan il medem gener de dumonda e returnan il medem object da dumonda, per maletgs, video ed audio: emprenda quai ina giada qua.

1. Obtegna ina clav API

Crees ina clav a https://doitong.com/developers/dashboard#keys e tegnla en ina variabla d'ambient: ella vegn mussada mo ina giada. Mintga clav po avair ses agen budget, uschia che ti la pos dar ad in agent senza ristgar l'entir conto. GET /account returna tes saldo API.

export DOITONG_API_KEY="doitong_..."

curl "https://api.doitong.ru/v1/account" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const res = await fetch("https://api.doitong.ru/v1/account", {
  headers: { Authorization: `Bearer ${process.env.DOITONG_API_KEY}` },
});

console.log(await res.json());

import os
import requests

r = requests.get(
    "https://api.doitong.ru/v1/account",
    headers={"Authorization": f"Bearer {os.environ['DOITONG_API_KEY']}"},
)
print(r.json())

Las execuziuns vegnan pajadas dal saldo API da tes conto en credits API: 1 000 credits API = $1, e mintga model custa exactamain il pretsch da ses producent. Fa ina chargiada a https://doitong.ru/developers/dashboard#balance.

2. Dumonda in pretsch, lura exequies

POST /quote/{model_id} prenda il JSON d'input e returna il pretsch exact. I na dovra nagina clav e na custa nagut. La medema input custa exact quai: la quotaziun è la chargiada. (In model chargià tenor utilisaziun è l'excepziun: sia quotaziun è il maximum che l'execuziun po custar, e la part betg utilisada vegn restituida suenter l'execuziun.)

curl -X POST "https://api.doitong.ru/v1/quote/kling-video/v3/pro/image-to-video" \
  -H "Content-Type: application/json" \
  -d '{"image": "https://example.com/fox.jpg", "duration": 5, "generate_audio": true}'

const res = await fetch("https://api.doitong.ru/v1/quote/kling-video/v3/pro/image-to-video", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ image: "https://example.com/fox.jpg", duration: 5, generate_audio: true }),
});

const quote = await res.json();
console.log(quote.credits, quote.usd); // 840 "0.84"

import requests

r = requests.post(
    "https://api.doitong.ru/v1/quote/kling-video/v3/pro/image-to-video",
    json={"image": "https://example.com/fox.jpg", "duration": 5, "generate_audio": True},
)
print(r.json()["credits"], r.json()["usd"])  # 840 0.84

200 OK · quotaziun

{
  "object": "quote",
  "model": "kling-video/v3/pro/image-to-video",
  "credits": 840,
  "usd": "0.84",
  "unit": "second",
  "quantity": 5,
  "unit_credits": 168,
  "mode": "exact",
  "breakdown": "5 s × 168 API credits"
}

Lura trametta il medem coss a POST /run/{model_id}. Aggiunta ?wait=20 per tegnair la connexiun averta durant maximalmain 20 secundas: in model svelt returna il resultat terminà en ina unica communicaziun. Trametta in header Idempotency-Key per che ina repetiziun na lantschia (ni chargia) mai duas giadas.

curl -X POST "https://api.doitong.ru/v1/run/flux/schnell?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: lighthouse-001" \
  -d '{"prompt": "A lighthouse on a rocky coast at dusk, warm light in the window"}'

const res = await fetch("https://api.doitong.ru/v1/run/flux/schnell?wait=20", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.DOITONG_API_KEY}`,
    "Content-Type": "application/json",
    "Idempotency-Key": "lighthouse-001",
  },
  body: JSON.stringify({ prompt: "A lighthouse on a rocky coast at dusk, warm light in the window" }),
});

const request = await res.json();
console.log(request.status, request.outputs[0]?.url);

import os
import requests

r = requests.post(
    "https://api.doitong.ru/v1/run/flux/schnell",
    params={"wait": 20},
    headers={
        "Authorization": f"Bearer {os.environ['DOITONG_API_KEY']}",
        "Idempotency-Key": "lighthouse-001",
    },
    json={"prompt": "A lighthouse on a rocky coast at dusk, warm light in the window"},
)
request = r.json()
print(request["status"], request["outputs"][0]["url"] if request["outputs"] else None)

La resposta è in object da dumonda:

200 OK · dumonda

{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "flux/schnell",
  "status": "succeeded",
  "cost": { "credits": 3, "usd": "0.003", "charged": 3, "refunded": 0 },
  "outputs": [
    { "type": "image", "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg", "width": 1024, "height": 768, "stored": true }
  ],
  "error": null
}

3. Suanda il status

Sche il model lavura anc cura che l'attesa finescha, survegns 202 Accepted cun l'id da la dumonda e ses status actual. Mintga dumonda passa tras il medem ciclus da vita:

Ciclus da vita da la dumonda

queued Acceptà e debità, spetga sin in worker
running Il model generescha
Stadis finals:
- succeededLa summa indicada è vegnida addebitada; outputs[] cuntegnan URLs en noss arcun
- failedRestituì automaticamain; l'errur declera il motiv
- canceledFermà avant in resultat; restituì

Legia danovamain la dumonda cun ses id. ?wait=20 funcziuna era qua, uschia ch'in simpel ciclus basta:

curl "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const headers = { Authorization: `Bearer ${process.env.DOITONG_API_KEY}` };
let request = await (await fetch("https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t?wait=20", { headers })).json();

while (request.status === "queued" || request.status === "running") {
  const res = await fetch(`https://api.doitong.ru/v1/requests/${request.id}?wait=20`, { headers });
  request = await res.json();
}

console.log(request.status, request.outputs[0]?.url);

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['DOITONG_API_KEY']}"}
request = {"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t", "status": "queued"}

while request["status"] in ("queued", "running"):
    request = requests.get(
        f"https://api.doitong.ru/v1/requests/{request['id']}",
        params={"wait": 20},
        headers=headers,
    ).json()

print(request["status"], request["outputs"][0]["url"] if request["outputs"] else None)

Cura che status è succeeded, cuntegna outputs[].url ils links a las datotecas en nossa memorisaziun. Sche la dumonda è failed u canceled, vegnan ses credits API restituids automaticamain e error declera il motiv. Cancelescha tut quai che stat anc en queued u running:

terminal

curl -X POST "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Per lungs jobs da video pos ti sursiglir il polling e passar in webhook_url empè da quai (vesair Webhooks).

4. Datotecas

Passa mintga URL public sco input, u dumonda POST /files per ina URL d'upload, fa PUT da la datoteca là e utilisescha il file_url returnà (vesair Datotecas). Ina dumonda reussida enumerescha ses resultats en outputs[] cun il tip, il tip da cuntegna e, sch'èn enconuschentas, las dimensiuns e la durada.

terminal

curl -X POST "https://api.doitong.ru/v1/files" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"filename": "fox.jpg", "content_type": "image/jpeg", "size": 482113}'

Errurs

Mintga model fallescha en la medema moda: in envelop cun in type, in code exact, il param problematica e mintga problem en details, uschia che in agent po curreger la dumonda senza leger prosa. Ina dumonda invalida na vegn mai chargiada.

422 Unprocessable Entity

{
  "error": {
    "type": "invalid_request",
    "code": "invalid_input",
    "message": "duration must be one of 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.",
    "param": "duration",
    "details": [ { "param": "duration", "message": "duration must be one of 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15." } ],
    "request_id": null,
    "doc_url": "https://doitong.com/developers/docs/errors#invalid_input"
  }
}

Mintga tip e code èn enumerads en Errurs.

Pretschs

Ils pretschs èn en USD e credits API e vegnan mussads sin mintga pagina da model avant l'execuziun. Mintga dumonda cuntegna cost cun credits, usd, charged e refunded. Ina execuziun vegn chargiada cura ch'ella vegn acceptada; las dumondas failed e canceled vegnan restituids automaticamain. Tscherts models vegnan pretschads exactamain tenor l'input, tscherts tenor la lunghezza u grondezza da las datotecas che ti tramettas, ed auters chargian in pretsch stimà per execuziun: en mintga cas è la quotaziun quai che ti pajas. Pauc models (models da linguas e da visiun, vusch, utensils da temp da processament) vegnan chargiads tenor utilisaziun: la quotaziun è il maximum che l'execuziun po custar, e la part che l'execuziun n'ha betg utilisà vegn restituida automaticamain. Vesair Pretschs.

MCP ed agents d'IA

Colleges mintga client MCP a https://api.doitong.ru/v1/mcp cun la medema clav Bearer. Tes agent po tschertgar en il catalog, dumandar pretschs ed exequir models, e leger mintga pagina da documentaziun sco Markdown.

Claude Code

claude mcp add --transport http doitong-models https://api.doitong.ru/v1/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"

Proxims pass

Sfoglia tuts ils models. Mintga pagina ha in constructur da dumondas che scriva il code per tai.
Emprenda il ciclus da vita da las dumondas: Dumondas.
Utilisescha ils medems nums da parameters per mintga model: Parameters.
Lavuras cun in agent d'IA per programmar? Dà ad el https://doitong.com/developers/llms.txt u collia il server MCP.

1. Obtegna ina clav API#

2. Dumonda in pretsch, lura exequies#

3. Suanda il status#

4. Datotecas#

Errurs#

Pretschs#

MCP ed agents d'IA#

Proxims pass#

1. Obtegna ina clav API

2. Dumonda in pretsch, lura exequies

3. Suanda il status

4. Datotecas

Errurs

Pretschs

MCP ed agents d'IA

Proxims pass