# Picsart API Platform > One API for 251 AI models from 31 providers: image, video, audio and LLMs, plus Picsart's own photo editing such as background removal. TypeScript and Python SDKs, a REST API, a CLI and an MCP server, on one API key. Every model has an id, such as `seedance-2.5`. To get from "which model" to a working call: pick an id from the catalog, then fetch `https://picsart.com/api-platform/models//llms.txt`. That document is generated from the same data as the model page: every parameter with its type, default and constraints, a JSON Schema, whether the call is sync or async, the live rates, and ready-to-run SDK, REST and CLI examples. It is usually all that is needed. To call a model: create an API key in the console at https://picsart.com/api-platform/dashboard/api-keys, keep it in a server-side environment variable and send it as a bearer token. With the SDK, `npm install @picsart/ai-sdk` (TypeScript) or `pip install picsart-ai-sdk` (Python), then `ai.generate('', { ... })`; it polls long jobs for you. Over plain HTTP, `POST https://api.picsart.com/workflows/v1/models/execute` with `{ "params": { "model": "", "params": { ... } } }`. Video and audio jobs outrun the sync limit: `POST .../submit`, then poll `GET .../{taskId}/result`. Pricing is per generation in USD, published per model, and every response reports what it charged. Take rates from the model's document or page, never from memory. ## Models 251 models, newest first, each with its id, provider and summary: [Model catalog](https://picsart.com/api-platform/models/llms.txt). - **Image** (75): Generate and edit images. - **Video** (102): Generate video from text, images, or video. - **Audio** (32): Speech, music, and sound effects. - **Text** (42): LLM text generation and understanding. Featured: - [Seedance 2.5](https://picsart.com/api-platform/models/seedance-2.5/llms.txt): `seedance-2.5` by ByteDance. Latest cinematic video with audio, multi-reference input, and mp4/mov output in 10- or 8-bit. Up to 30s. [new, premium, hot] - [Grok Imagine 2.0](https://picsart.com/api-platform/models/grok-imagine-image-2.0/llms.txt): `grok-imagine-image-2.0` by Grok. Latest Grok Imagine generation — sharper detail with a low/medium quality tier. - [Kling 4.0](https://picsart.com/api-platform/models/kling-v4/llms.txt): `kling-v4` by Kling. Video up to 30s at 720p or 1080p, with start, middle and end keyframes. [new] - [GPT Image 2.5 Flare](https://picsart.com/api-platform/models/gpt-image-2.5-flare/llms.txt): `gpt-image-2.5-flare` by OpenAI. Fast GPT Image tier — everyday generation at roughly half the latency of GPT Image 2. - [MiniMax H3 Max Turbo](https://picsart.com/api-platform/models/minimax-h3-max-turbo/llms.txt): `minimax-h3-max-turbo` by MiniMax. Faster-than-realtime MiniMax H3 Max Turbo video from text or a start/end frame, with prompt expansion. Up to 15s at 1080p. - [Flux 3 Image](https://picsart.com/api-platform/models/flux-3-image/llms.txt): `flux-3-image` by Flux. Generate and edit images with up to 10 references — multi-reference composition, precise local edits and text rendering, natively up to 4K. ## Documentation - [Introduction](https://picsart.com/api-platform/docs) - [Authentication](https://picsart.com/api-platform/docs/authentication) - [Quickstart](https://picsart.com/api-platform/docs/quickstart) - [Image generation](https://picsart.com/api-platform/docs/guides/image) - [Video generation](https://picsart.com/api-platform/docs/guides/video) - [Audio generation](https://picsart.com/api-platform/docs/guides/audio) - [Text & analysis](https://picsart.com/api-platform/docs/guides/text) - [LLM APIs](https://picsart.com/api-platform/docs/guides/llm-apis) - [SDK](https://picsart.com/api-platform/docs/sdk) - [REST API](https://picsart.com/api-platform/docs/api-reference) - [CLI](https://picsart.com/api-platform/docs/cli) - [MCP](https://picsart.com/api-platform/docs/mcp) - [Files & Drive](https://picsart.com/api-platform/docs/files-and-drive) ## Agent-readable surfaces - [Model catalog](https://picsart.com/api-platform/models/llms.txt): every model with its id, provider and summary, grouped by category - [Per-model document, worked example](https://picsart.com/api-platform/models/seedance-2.5/llms.txt): parameters, schema, rates and examples for `seedance-2.5`; substitute any model id - [MCP server](https://picsart.com/gen-ai-mcp/): the same models from Claude, ChatGPT and other MCP clients; signs in through the browser, no API key - [CLI reference](https://picsart.github.io/picsart-mcp-cli-docs/guide/introduction): `gen-ai` for terminals, scripts and CI - [Sitemap](https://picsart.com/api-platform/sitemap.xml): every page ## Optional - [Contact sales](https://picsart.com/api-platform/contact-sales): volume pricing, invoicing and annual agreements - [Picsart](https://picsart.com): the creative platform these models also power; its own index is https://picsart.com/llms.txt