# Vidgo

> Vidgo (vidgo.ai) is a generative media API: one API key for image, video, audio, music, 3D and LLM models. Generation is asynchronous: submit a task with a `vendor/model/mode` model ID, then poll its status or receive a webhook.

The developer documentation lives at https://docs.vidgo.ai. Start with its llms.txt index or connect the docs MCP server. Every docs page is also available as Markdown by adding `.md` to its URL.

API basics:

- Base URL: `https://api.vidgo.ai`
- Auth header: `Authorization: Bearer $VIDGO_API_KEY` (create a key at https://vidgo.ai/apis/dashboard/api-key; keep it in the `VIDGO_API_KEY` environment variable)
- Submit: `POST /api/generate/submit` with JSON `{"model": "kwaivgi/kling-v4.0/text-to-video", "input": {...}, "callback_url": "optional"}`
- Status: `GET /api/generate/status/{task_id}` until `data.status` is `finished` or `failed`; results are in `data.files[].file_url` and expire after 24 hours

## Docs for agents

- [Docs index](https://docs.vidgo.ai/llms.txt): every docs page with a one-line summary
- [Full docs](https://docs.vidgo.ai/llms-full.txt): the complete docs in one text file
- [Docs MCP server](https://docs.vidgo.ai/mcp): Streamable HTTP, no auth; tools `search_vidgo_api` and `query_docs_filesystem_vidgo_api`
- [AI agent setup](https://vidgo.ai/apis/agent-setup): setup for Claude Code, Codex, Cursor and OpenCode, plus a copy-paste prompt

## API guides

- [Quick start](https://docs.vidgo.ai/api-manual/quickstart.md): create a key, submit a task, poll the result
- [Get task status](https://docs.vidgo.ai/api-manual/task-management/status.md): status values and the `files` array
- [Webhook callbacks](https://docs.vidgo.ai/api-manual/task-management/webhooks.md): `callback_url` payloads
- [Error codes](https://docs.vidgo.ai/api-manual/error-codes.md): response formats and HTTP status codes
- [Upload a file from a URL](https://docs.vidgo.ai/api-manual/file-series/upload-url.md): host inputs for image and video models
- [Query user balance](https://docs.vidgo.ai/api-manual/account-management/user-balance.md): remaining credits

## Models

- [Image models](https://docs.vidgo.ai/api-manual/image-series/overview.md): text-to-image and image editing
- [Video models](https://docs.vidgo.ai/api-manual/video-series/overview.md): text, image and reference to video
- [Audio models](https://docs.vidgo.ai/api-manual/music-series/audio-overview.md): text-to-speech
- [Music models](https://docs.vidgo.ai/api-manual/music-series/overview.md): Suno actions and music models
- [3D models](https://docs.vidgo.ai/api-manual/3d-series/overview.md): text and image to 3D
- [LLM models](https://docs.vidgo.ai/api-manual/chat-series/overview.md): OpenAI-, Claude- and Gemini-compatible chat endpoints
- [Model catalog](https://vidgo.ai/apis/models): every model with its page on vidgo.ai

## Optional

- [API pricing](https://vidgo.ai/apis/api-pricing): current rates per model
- [FAQs](https://docs.vidgo.ai/faqs.md): billing, models and common questions
- [Changelog](https://vidgo.ai/apis/changelog): new models and updates