Nyaraka za mawakala wa AI
Nyaraka hizi zimeundwa kusomwa na wasaidizi wa AI pamoja na watu. Mpe wakala wako mojawapo ya sehemu za kuanzia hapa chini na utaweza kuandika msimbo sahihi wa ujumuishaji bila kubashiri majina ya vigezo au bei.
Sehemu za kuanzia
| URL | Ni nini |
|---|---|
| https://doitong.com/developers/llms.txt | Faharasa katika umbizo la llms.txt: kila mwongozo na modeli ikiwa na maelezo ya mstari mmoja. |
| https://doitong.com/developers/llms-full.txt | Kila mwongozo kwa ukamilifu, modeli zilizoangaziwa kwa ukamilifu na mambo muhimu ya modeli zote 1,496 (id, mtengenezaji, bei, kiungo cha ukurasa kamili) katika faili moja la Markdown. |
/<lang>/developers/llms.txt |
Faharasa ileile yenye miongozo katika lugha nyingine ya tovuti, kwa mfano https://doitong.com/de/developers/llms.txt (Kiingereza ndicho chaguomsingi). |
<any page>.md |
Nakala pacha ya Markdown ya ukurasa, kwa mfano https://doitong.com/developers/models/flux/schnell.md au https://doitong.com/developers/docs/quickstart.md. |
/developers/models/<id>/llms.txt |
Sawa na nakala pacha ya modeli ya .md. |
| https://doitong.com/developers/openapi.json | OpenAPI 3.1 kwa jenereta za msimbo: kila endpoint na miili ya maombi yenye aina ya modeli zilizoangaziwa; ?model=<id>, ?category=<id> au ?models=all huongeza nyingine. |
https://api.doitong.com/v1/models |
Katalogi kama JSON (hakuna ufunguo unaohitajika). |
Ukurasa wa Markdown wa kila modeli una bei yake katika USD na krediti za API, kila kigezo kikiwa na thamani zote zinazoruhusiwa, mfano wa lazima pekee na mfano kamili, muundo wa jibu, na msimbo tayari wa curl, JavaScript, Python na MCP.
Nakili kwa AI
Kila ukurasa wa modeli una kitufe cha Nakili kwa AI: nakili ukurasa kama Markdown, au uufungue katika ChatGPT au Claude ukiwa na kidokezo kinachomwelekeza msaidizi kwenye toleo la Markdown.
Kidokezo kinachofanya kazi
Bandika hiki kwenye Claude, ChatGPT au Cursor, kisha eleza unachotaka kujenga:
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.Mruhusu wakala aziite modeli wenyewe
Ili kumruhusu wakala azalishe midia moja kwa moja, unganisha seva ya MCP kwa ufunguo wenye bajeti katika krediti za API. Wakala atakuwa na zana za kutafuta modeli, kunukuu bei, kuziendesha na kuchukua matokeo, na hawezi kutumia zaidi ya bajeti.