Peke ki ngā ihirangi
Hou Kei te wātea a Kling 3.0 me Seedance 2.0

Kotahi API mō ngā tauira atahanga, ataata me te oro pai rawa

He rite tonu te whakatakotoranga tono mō ia tauira. Te utu tika i mua i te whakahaere. Ka tiakina ngā kōnae mō ake tonu atu, 7 rā mō te kore utu rānei, māu e whiriwhiri.

POSTapi.doitong.com/v1/run/{model_id}

1,496ngā tauira
84ngā taiwhanga
AtahangaAtaataOrorongo3DKuputuhiRaraunga (JSON)Kōnae
kotahi te whakatakotoranga tono mō ēnei katoa
Tīmatanga tere

Mai i te kī ki te ataata kua oti mā te karanga kotahi

Pānuihia te tīmatanga tere
kāpeka
# Keys start with doitong_
export DOITONG_API_KEY="doitong_..."

# Check it works: returns your API credit balance
curl https://api.doitong.com/v1/account \
  -H "Authorization: Bearer $DOITONG_API_KEY"
kāpeka
# 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/kling-video/v3/pro/image-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "The banana manager turns to the camera, smiles and waves while coworkers keep typing, gentle handheld camera",
    "image": "https://content.doitong.com/images/gp/image_20260610003801_541d9719_316882.png",
    "duration": 5
  }'

# 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"
response.json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "model": "kling-video/v3/pro/image-to-video",
  "status": "succeeded",
  "cost": {
    "credits": 840,
    "usd": "0.84",
    "charged": 840,
    "refunded": 0
  },
  "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
    }
  ]
}
1,496 tauira · 21 kāwai

Tirohia te mea ka waihangatia e ia tauira

Ngā kāwai katoa (21)

Tirotiro mā te taiwhanga

Ngā taiwhanga katoa (84)
He aha a Doitong API

Akohia kotahi te tono. Whakamahia ngā tauira katoa.

Ngā tawhā whakakotahi

He ōrite te tikanga o image, duration me aspect_ratio ki ia tauira. Ka mahi tonu ngā ingoa taketake o te tauira hei ingoa kē.

"image": "…", "duration": 5

Kotahi te URL tono mō ia tauira

Hurihia ngā tauira mā te huri i te ara. Ka noho ōrite te motuhēhēnga, te tinana me te whakautu.

POST /run/{model_id}

Quote = utu

Ka whakahokia e POST /quote/{model_id} te utu tika mō tō tāuru. Koirā te utu, kāore e nui ake.

→ { "credits": 560, "usd": "0.56" }

Pupurihia ngā kōnae mō te wā e hiahia ana koe

Ka tāruatia ia putanga ki tō mātou rokiroki. Tiakina mō ake tonu atu mō te $ 0.10 mō ia GB i te marama, 7 rā mō te kore utu rānei: kotahi te whakakā i tō pūkete, mō ia tono rānei.

?storage=permanent | temporary

Kotahi te whakatakotoranga hapa

Ka whakaingoatia e ia hapa te tawhā, te take me te hononga ki ngā tuhinga, mō ia tauira. Kāore he utu mō te tāuru muhu.

"param": "duration", "code": "out_of_range"

Ngā pūtea mō ia kī + MCP

Whakatakotoria he tepe whakapaunga mō ia kī, kātahi ka hoatu taua kī ki tētahi māngai mā te tūmau MCP.

api.doitong.com/v1/mcp
I hangaia mō ngā māngai AI

Tukua tō māngai ki te kōwhiri i te tauira, te whakatau i te utu me te whakahaere

Honoa a Claude, ChatGPT, a Cursor rānei ki te tūmau MCP Doitong mā te kī ōrite e whakamahia ana mō REST. Ka tukuna hoki ia whārangi tuhinga hei Markdown, nō reira ka pānui ngā māngai i ngā mea e pānui ana koe.

  • He whakatau utu i mua i ia whakahaere, kia noho ngā māngai ki roto i te pūtea
  • Ka whakaingoatia e ngā hapa te tawhā me whakatika e te māngai
  • He putanga Markdown o ia whārangi mō ngā matapihi horopaki

Whakapirihia ki Claude, ChatGPT, ki Cursor rānei, kātahi ka whakaahua i tāu e hiahia ana ki te waihanga.

Whakaaturia te tono
You can generate images, video, audio and 3D with the Doitong API.
Read https://doitong.com/developers/llms.txt first, then the .md page of each model you plan to use.
Base URL: https://api.doitong.com/v1. Authenticate with the header "Authorization: Bearer $DOITONG_API_KEY".
List models with GET /models and read one model's schema with GET /models/{model_id}.
Always call POST /quote/{model_id} with the input first and tell me the price (1000 API credits = 1 USD).
Then call POST /run/{model_id}?wait=20 with the same JSON body and an Idempotency-Key header.
If the status is still queued or running, poll GET /requests/{id}?wait=20.
Use outputs[].url from the response; files are kept forever unless the account keeps them 7 days
(pass ?storage=temporary for throwaway runs). Use only parameters from the model schema.
claude mcp add --transport http doitong-models https://api.doitong.com/v1/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"

Whakahaerehia kotahi ki tō kōpaki kaupapa. He kī Bearer ōrite ki te REST API.