# Dokumentacia AI-agentonge

Kadala dokumentacia kerdine si te ginavel len AI-asistentura sar thaj manuša. De tire agentos jekh entry pointos andral e tele thaj
voj šaj te ramol čačuno integraciako kodo bi te gindil e parametronge nava vaj e molipena.

## Entry pointura

| URL | So si |
|---|---|
| [https://doitong.com/developers/llms.txt](https://doitong.com/developers/llms.txt) | Indexo ko [llms.txt](https://llmstxt.org) formato: sako gidipen thaj modelo jekhe-rindako deskripciaha. |
| [https://doitong.com/developers/llms-full.txt](https://doitong.com/developers/llms-full.txt) | Sako gidipen pherdo, e featured modelura pherde thaj e esencialura savore 1,496 modelonge (id, kerutno, molipe, linko ko pherdo lil) jekhe Markdown fajloste. |
| `/<lang>/developers/llms.txt` | Savo-jekh indexo le gidipenca aver site-oski čhibaha, vareso `https://doitong.com/de/developers/llms.txt` (English si standardno). |
| `<any page>.md` | O Markdown dvojnik jekhe pajinako, vareso [https://doitong.com/developers/models/flux/schnell.md](https://doitong.com/developers/models/flux/schnell.md) vaj [https://doitong.com/developers/docs/quickstart.md](https://doitong.com/developers/docs/quickstart.md). |
| `/developers/models/<id>/llms.txt` | Savo-jekh sar e modelosko `.md` dvojnik. |
| [https://doitong.com/developers/openapi.json](https://doitong.com/developers/openapi.json) | OpenAPI 3.1 vaš kodo-generatorura: sako endpoint thaj tipime mangipenoske telura le featured modelonge; `?model=<id>`, `?category=<id>` vaj `?models=all` anen aver. |
| `https://api.doitong.com/v1/models` | O katalogo sar JSON (na mangela klidin). |

Saki modeloski Markdown página si le molipnaha ko USD thaj API krediti, sa parametrura sa dozvolime vrednostenca, jekh numa-zorutno thaj jekh
pherdo exemplo, o respondentengo lilavipen, thaj gata kodo vaš curl, JavaScript, Python thaj MCP.

## Copy vaš AI

Sako modeloski página si la jekh **Copy for AI** button: kopirisar e pajina sar Markdown, vaj phirav la ko ChatGPT vaj Claude jekhe
promptoha savo sikavel le asistantos ko Markdown-versia.

## Jekh prompto savo kerel buti

Čhinav kado ko Claude, ChatGPT vaj Cursor, palal phen so kames te kerel:

```text Prompt
I want to generate images/video/audio with the Doitong API.
Read https://doitong.com/developers/llms.txt first, then the .md page of each model you plan to use.
Facts: base URL https://api.doitong.com/v1; auth header "Authorization: Bearer <key>" with the key from the
DOITONG_API_KEY environment variable; run with POST /run/{model_id}?wait=20 and, if the status is
still queued or running, poll GET /requests/{id}?wait=20; outputs[].url are file URLs on Doitong storage
(kept forever by default; add ?storage=temporary for throwaway runs, deleted after 7 days).
Get the price first with POST /quote/{model_id} (same body): exact, or for a model charged by usage the
most the run can cost (the unused part is refunded). Prices are in USD; 1000 API credits = 1 USD.
Use the parameter names from the model page; never invent parameters.
```

## Mukh le agentos te kerel callura modelonge korkori

Te mukhes jekhe agentes te kerel media direktno, phand le [MCP serveroha](https://doitong.com/developers/docs/mcp) jekhe klidinaha savo si le
budžetosa ko API krediti. O agento akana si les instrumentura te rodel modelura, te pučhel molipe, te kerel thaj te anel palpale rezultatura, thaj našti potrošinela buter so o budžeto mukel.