> ## Documentation Index
> Fetch the complete documentation index at: https://docs.infery.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Core concepts

> Workspaces, plans, credits, Playground and API — a mental model for the platform.

## Workspace

A **workspace** is the container for everything: members, subscription plan, API keys, credits, chats, projects and files. Every API call and every Playground message is scoped to exactly one workspace.

You can belong to multiple workspaces (switch via the top-left selector in the app).

## Members and roles

Each member has a role that controls what they can do:

| Role          | Playground  | API keys | Billing | Admin settings |
| ------------- | ----------- | -------- | ------- | -------------- |
| **Owner**     | ✓           | full     | full    | full           |
| **Admin**     | ✓           | full     | view    | full           |
| **Developer** | ✓           | own      | —       | —              |
| **Billing**   | ✓           | —        | full    | —              |
| **Viewer**    | ✓ read-only | —        | —       | —              |

See [Members and roles](/workspaces/members-and-roles) for details.

## Credits

Everything on Infery is priced in **credits**. 1 credit ≈ \$0.01. Every
chat token, every generated image, every second of voice is metered to the same
balance — no per-provider invoices to juggle.

Two sources of credits:

* **Monthly plan credits** — granted at the start of each billing cycle (may roll over on higher-tier plans)
* **Topups** — one-off purchases that never expire

Details: [Credits](/billing/credits), [Plans](/billing/subscription-plans).

## Playground

The **Playground** is the in-browser product surface: chats, projects, file uploads, generations, sharing with teammates, bookmarks. If you're evaluating or exploring — this is where you live.

Learn more: [Playground overview](/playground/overview).

## API

The **API** is how you build with Infery in production. It's OpenAI-compatible at the wire level — `POST /v1/chat/completions`, `POST /v1/embeddings`, `POST /v1/images/generations`, etc — authenticated with a Bearer token (`inf_...`).

Both Playground and API share the **same credit balance** and **same models**. A Playground message and an API call cost the same.

Start: [API introduction](/api-reference/introduction).

## Models

\~150 models from OpenAI, Anthropic, Google, xAI, DeepSeek, Alibaba, Suno and more are available by slug (e.g. `gpt-4o`, `claude-opus-4-6`, `gemini-2-5-pro`). Every model speaks the OpenAI format through our gateway — no provider-specific SDK required.

Browse the live list at [models/catalog](/models/catalog) or fetch programmatically via `GET /v1/models`.

## Files

Two kinds of files, kept separate:

* **Playground files** — dropped into a chat message (inherits chat sharing scope, cascades via PlaygroundMessage references)
* **API files** — uploaded via `POST /v1/files` with OpenAI-compatible semantics (id → `file_abc...`, referenced in chat completions as content blocks)

Details: [Files API](/api-reference/files), [Files in chat](/playground/files-and-attachments).

## Safety nets

| Feature         | What it does                                             | Docs                                       |
| --------------- | -------------------------------------------------------- | ------------------------------------------ |
| Fallback chains | Re-route to a backup model when primary errors/throttles | [Fallbacks](/workspaces/fallback-chains)   |
| Budget alerts   | Email/Slack when spend hits a threshold                  | [Budget alerts](/workspaces/budget-alerts) |
| Per-key quotas  | RPM, daily tokens, allowed models, cost cap per API key  | [Quotas](/workspaces/quotas-and-presets)   |
| Idempotency     | `Idempotency-Key` on file uploads prevents duplicates    | [Files API](/api-reference/files)          |
| CAPTCHA         | Turnstile on contact forms and sign-up                   | [Security](/reference/security)            |