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

# Introduction

> The Dolphy API gives you OpenAI-compatible access to creative AI models — chat, image generation, image editing, video, and motion control.

## What you get

The Dolphy API exposes the same models that power dolphy.chat, behind a clean
OpenAI-compatible interface. Drop in the official `openai` SDK, change the
`baseURL`, and you're up and running.

* **Creative chat** — `dolphy-chat-1`, our base conversational model
* **25+ image generation models** — from FLUX 2, Nano Banana 2, GPT Image,
  Seedream, Lustify, Chroma, and more
* **Specialty image editing** with Seedream 4.5
* **Wan 2.5 / Wan 2.7 video generation** at up to 1080p
* **Kling v3 motion control** to retarget character motion onto a reference video

## Quick start

```ts theme={null}
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://dolphy.chat/api/v1",
  apiKey: "dpy_live_...", // get yours at https://dolphy.chat/settings/api-keys
});

const response = await client.chat.completions.create({
  model: "dolphy-chat-1",
  messages: [{ role: "user", content: "Write a sci-fi opening line." }],
});

console.log(response.choices[0].message.content);
```

```python theme={null}
from openai import OpenAI

client = OpenAI(
    base_url="https://dolphy.chat/api/v1",
    api_key="dpy_live_...",
)

response = client.chat.completions.create(
    model="dolphy-chat-1",
    messages=[{"role": "user", "content": "Write a sci-fi opening line."}],
)

print(response.choices[0].message.content)
```

## Model groups

| Group            | Endpoint                                           | Notes                                  |
| ---------------- | -------------------------------------------------- | -------------------------------------- |
| Chat             | `POST /v1/chat/completions`                        | OpenAI-compatible, streaming supported |
| Image generation | `POST /v1/images/generations`                      | OpenAI-compatible                      |
| Image editing    | `POST /v1/images/edits`                            | Specialty Seedream 4.5                 |
| Video            | `POST /v1/video/queue` + `POST /v1/video/retrieve` | Async — queue then poll                |
| Motion control   | `POST /v1/video/motion-control`                    | Async, poll via `/v1/video/retrieve`   |
| Models list      | `GET /v1/models`                                   | Lists everything available             |

## Billing

API requests draw from the same credit balance you use on dolphy.chat. There
is no separate billing system — buy credits at
[dolphy.chat/credits](https://dolphy.chat/credits) and they fund both your
web usage and your API calls.

Members get **almost 55% more credits per dollar** on every credit purchase.
See [Pricing](/pricing) for the exact credit cost per endpoint.

## Limits

* 60 chat requests / minute per API key
* 30 image requests / minute per API key
* 5 video requests / minute per API key
* Up to 10 active API keys per account

Hit one of these and you'll get a `429` with a `Retry-After` hint.

## What we don't have (yet)

* Webhooks (you poll for video completion)
* Per-key cost caps (set Stripe spending limits instead)
* Usage analytics dashboard for API customers (coming soon)

If you need any of these, [tell us](mailto:support@dolphy.chat) — we
prioritize based on what real customers ask for.