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

> ## Agent Instructions
> The Deepshi API is an OpenAI-compatible gateway. Base URL: https://api.deepshi.ai/v1. API keys start with sk-bf- and go in the Authorization: Bearer header. Prefer the official OpenAI SDKs pointed at the Deepshi base URL. Model ids are clean with no provider prefix (e.g. deepshi-3.0, claude-opus-4.8, gpt-5.5). Chat and image requests are synchronous; video and music requests are asynchronous job APIs (create, then poll). Every synchronous response carries usage.cost.total_cost in USD. Do not reference the internal /api/* admin plane or virtual keys.

# Models overview

> How models work in the Deepshi API and how to reference them.

The Deepshi API gives you one key and one balance for many models, across text, image, video, and music: Deepshi's own models plus leading third-party models. You choose a model with the `model` field on each request.

## Referencing a model

Pass the model's `id` in the `model` field. The id is all you need.

```json theme={null}
{ "model": "deepshi-3.0", "messages": [ ... ] }
```

## Listing available models

Call `GET /v1/models` to list the models available to you:

```bash theme={null}
curl https://api.deepshi.ai/v1/models \
  -H "Authorization: Bearer $DEEPSHI_API_KEY"
```

Each entry's `id` is the value you pass as `model`:

```json theme={null}
{
  "object": "list",
  "data": [
    { "id": "deepshi-3.0", "object": "model", "owned_by": "deepshi" },
    { "id": "claude-opus-4.8", "object": "model", "owned_by": "deepshi" }
  ]
}
```

## Browse models

<CardGroup cols={2}>
  <Card title="Chat models" icon="comments" href="/models/text-models">
    Chat and reasoning models, with context windows and capabilities.
  </Card>

  <Card title="Image models" icon="image" href="/models/image-models">
    Image generation and editing models, with sizing options and prompt limits.
  </Card>

  <Card title="Video models" icon="clapperboard" href="/models/video-models">
    Video generation models, with resolutions, durations, and audio support.
  </Card>

  <Card title="Audio models" icon="music" href="/models/audio-models">
    Audio generation models, with prompt limits and output options.
  </Card>
</CardGroup>