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

# SnapGen API

> Use one API key for GPT text, image generation, and asynchronous video generation.

SnapGen is a prepaid AI gateway with OpenAI-compatible, Anthropic-compatible, and Gemini-compatible text protocols plus image and video generation APIs.

Change your base URL to `https://api.snapgen.org/v1`, keep your API key on the server, and select a model ID from the live catalog.

## Quick start

<Steps>
  <Step title="Create an API key">
    [Create an account](https://snapgen.org/sign-up), add balance, then create
    a key under **Console > API Keys**.
  </Step>

  <Step title="Choose a model">
    Call [`GET /v1/models`](/api-reference/list-models) or browse the model
    pages in the sidebar. Model availability is scoped to your key.
  </Step>

  <Step title="Send a request">
    Send the key as `Authorization: Bearer sk-...` and use the endpoint for the
    selected modality.
  </Step>
</Steps>

```bash theme={null}
curl https://api.snapgen.org/v1/chat/completions \
  -H "Authorization: Bearer $SNAPGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4-mini",
    "messages": [{"role": "user", "content": "Reply with one sentence."}]
  }'
```

## API surfaces

<CardGroup cols={2}>
  <Card title="Text Series" icon="font" href="/api-manual/text/gpt-5-4">
    Use Chat Completions, Responses, Anthropic Messages, or Gemini native
    requests with the current GPT-5.4+ catalog.
  </Card>

  <Card title="Image Series" icon="image" href="/api-manual/image/gpt-image-2">
    Generate images through the OpenAI-compatible image endpoint.
  </Card>

  <Card title="Video Series" icon="video" href="/api-manual/video/gemini-omni-t2v">
    Submit Gemini Omni, Seedance 2, or Veo 3.1 tasks, then poll and download.
  </Card>

  <Card title="Development tools" icon="code" href="/integrations">
    Configure Claude Code, Cursor, Cline, Gemini CLI, or Codex CLI.
  </Card>
</CardGroup>

## Compatible text protocols

| Protocol                | Endpoint                                      | Typical use                          |
| ----------------------- | --------------------------------------------- | ------------------------------------ |
| OpenAI Chat Completions | `POST /v1/chat/completions`                   | OpenAI SDKs, Cursor, Cline           |
| OpenAI Responses        | `POST /v1/responses`                          | Codex CLI and Responses clients      |
| Anthropic Messages      | `POST /v1/messages`                           | Claude Code gateway mode             |
| Gemini native           | `POST /v1beta/models/{model}:generateContent` | Gemini CLI and Google Gen AI clients |

All four text protocols were verified against the live gateway. The gateway converts compatible requests to the selected model's serving protocol.

## Billing and availability

SnapGen uses prepaid USD balance with no subscription. Text routes are token-billed. GPT Image 2 and video routes use fixed or duration-based request prices.

<Note>
  The [live models page](https://snapgen.org/models) is the source of truth for
  current availability and pricing. Call [`GET /v1/models`](/api-reference/list-models)
  before hardcoding a model ID.
</Note>