Skip to content
AI agents

Dokumentation für KI-Agenten

View as Markdown Updated

These docs are built to be read by AI assistants as well as people. Hand your agent one of the entry points below and it can write correct integration code without guessing parameter names or prices.

Entry points

URL What it is
https://doitong.com/developers/llms.txt Index in the llms.txt format: every guide and model with a one-line description.
https://doitong.com/developers/llms-full.txt Every guide in full, the featured models in full and the essentials of all 1,496 models (id, maker, price, link to the full page) in one Markdown file.
/<lang>/developers/llms.txt The same index with the guides in another site language, for example https://doitong.com/de/developers/llms.txt (English is the default).
<any page>.md The Markdown twin of a page, for example https://doitong.com/developers/models/flux/schnell.md or https://doitong.com/developers/docs/quickstart.md.
/developers/models/<id>/llms.txt Same as the model's .md twin.
https://doitong.com/developers/openapi.json OpenAPI 3.1 for code generators: every endpoint and typed request bodies of the featured models; ?model=<id>, ?category=<id> or ?models=all add others.
https://api.doitong.com/v1/models The catalog as JSON (no key needed).

Each model's Markdown page has its price in USD and API credits, every parameter with all allowed values, a required-only and a full example, the response shape, and ready code for curl, JavaScript, Python and MCP.

Copy for AI

Every model page has a Copy for AI button: copy the page as Markdown, or open it in ChatGPT or Claude with a prompt that points the assistant to the Markdown version.

A prompt that works

Paste this into Claude, ChatGPT or Cursor, then describe what you want to build:

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.

Let the agent call models itself

To let an agent generate media directly, connect the MCP server with a key that has a budget in API credits. The agent then has tools to search models, quote, run and fetch results, and cannot spend more than the budget.