In'unica API per ils megliers models da maletgs, video ed audio
Il medem format da dumonda per mintga model. Prezi exact avant l'execuziun. Datotecas conservadas per adina u 7 dis gratuitamain, tenor vossa tscherna.
POSTapi.doitong.com/v1/run/{model_id}
Da la clav al video terminà en ina clamada
# 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"
# 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"
{
"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
}
]
}
Guardar tge che mintga model producescha
Sfegliar tenor laboratori
Tut ils laboratoris (84)- Alibaba Endpoints: 142
- Black Forest Labs Endpoints: 135
- Lightricks Endpoints: 102
- MiniMax Endpoints: 64
- Kling Endpoints: 62
- ByteDance Endpoints: 57
- Bria AI Endpoints: 54
- Stability AI Endpoints: 48
- PixVerse Endpoints: 42
- Google Endpoints: 41
- Ideogram Endpoints: 36
- Tencent Endpoints: 33
- Microsoft Endpoints: 27
- NVIDIA Endpoints: 25
- Meta Endpoints: 24
- Recraft Endpoints: 24
- Vidu Endpoints: 22
- xAI Endpoints: 19
Emprender ina dumonda. Utilisar mintga model.
Parameters unifitgads
image, duration e aspect_ratio muntan il medem sin mintga model. Ils nums specifics dal model funcziunan vinavant sco aliases.
"image": "…", "duration": 5
Ina URL da dumonda per mintga model
Midar il model cun midar il path. Auth, body e resposta restan identics.
POST /run/{model_id}
Quote = debit
POST /quote/{model_id} returna il pretsch exact per tes input. Quai è quai che ti pajas, mai dapli.
→ { "credits": 560, "usd": "0.56" }
Datotecas conservadas uschè ditg sco ti dovras
Mintga output vegn copià en nossa memorisaziun. Conserva'l per adina per $0,10 per GB e mais, u 7 dis gratuitamain: cun in switch en tes conto u per dumonda.
?storage=permanent | temporary
In format d'errur
Mintga errur numna il parameter, il motiv ed ina colliaziun a la documentaziun, per mintga model. Inputs invalids na vegnan mai debitads.
"param": "duration", "code": "out_of_range"
Budgets per clav + MCP
Limitar la expensa per clav e surdar quella clav ad in agent tras il server MCP.
api.doitong.com/v1/mcp
Lascha tes agent tscherner il model, citar il pretsch e l'executar
Connectar Claude, ChatGPT u Cursor al server MCP da Doitong cun la medema clav che ti dovras per REST. Mintga pagina da la documentaziun è er disponibla sco Markdown, uschia che ils agents legian exact quai che ti legias.
- Citats avant mintga execuziun, uschia che ils agents restan en il budget
- Las errurs numran il parameter che l'agent sto curreger
- Ina versiun Markdown da mintga pagina per las fanestras da context
Collar quel en Claude, ChatGPT u Cursor e descriver lura tge che ti vuls construir.
Mussar il prompt
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"
// .cursor/mcp.json
{
"mcpServers": {
"doitong-models": {
"url": "https://api.doitong.com/v1/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
// claude_desktop_config.json
{
"mcpServers": {
"doitong-models": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.doitong.com/v1/mcp",
"--header",
"Authorization: Bearer YOUR_API_KEY"
]
}
}
}
Executa ina giada en il dossier dal project. La medema clav Bearer sco per REST API.
Reaviar Cursor suenter avair memorisà. Il server cumpara sut MCP en ils parameters.
Settings → Developer → Edit config e lura reaviar Claude Desktop. Node.js è necessari.