> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Models and Pricing

EmpirioLabs AI exposes a canonical model catalog through the API. The same catalog powers the [Models page](https://empiriolabs.ai/models) and [Pricing page](https://empiriolabs.ai/pricing) on the website.

## List models

```bash
curl "https://api.empiriolabs.ai/v1/models?available=true" \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY"
```

The response includes each model's `id`, display name, author, modalities, capabilities, supported parameters (with types, defaults, min/max), context window, and pricing.

## Retrieve one model

```bash
curl "https://api.empiriolabs.ai/v1/models/seed-2-0-pro" \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY"
```

The detail response includes the full `supported_parameters` array, `capabilities` object, `default_params`, and pricing breakdown.

## Model categories

These are the canonical categories used in the live catalog (the `category` field on `GET /v1/models/<id>`). Vision and reasoning are model capabilities, not separate categories; a Text Generation model can also be a vision model and a reasoning model.

| Category              | Examples                                                                                     | Typical pricing unit                                  |
| --------------------- | -------------------------------------------------------------------------------------------- | ----------------------------------------------------- |
| **Text Generation**   | Qwen3-Max, DeepSeek V4 Pro, Seed 2.0 Pro, Mistral Medium 3.1, Nova Pro, MiMo V2.5 Pro, Manus | Per input + output token                              |
| **Image Generation**  | Qwen Image 2.0, Seedream 5.0 Lite, Hunyuan Image 3, Nova Canvas, Wan 2.7 Image               | Per image                                             |
| **Video Generation**  | Kling O3, Wan 2.7, Seedance 2.0 Pro, Hunyuan Video 1.5, Pixverse V5.6, SVI 2.0 Pro           | Per second of generated video                         |
| **Audio Generation**  | GLM-TTS, SoulX-Podcast, Gemini 2.5 / 3.1 TTS, Stable Audio 2.5                               | Per character or per second of audio                  |
| **Transcription**     | Deepgram Nova 3, OpenAI Whisper                                                              | Per second / minute of input audio                    |
| **Research & Search** | Exa Search, Tavily, Linkup, Perplexity Sonar, GPTZero                                        | Per request, per call, or per token (model-dependent) |

## Pricing units

Models are not all token-priced. The catalog may use any of these billing units:

* **token**: charged per input token and per output token (most text/chat models)
* **request**: flat rate per API call
* **image**: charged per generated image
* **video-second**: charged per second of generated video
* **audio-second**: charged per second of generated or transcribed audio
* **tool-call**: charged per tool invocation
* **custom**: model-specific billing (see the model's pricing array)

Always call `GET /v1/models` or `GET /v1/models/{modelId}` for current pricing metadata before estimating cost.

## Discount labels

Discount labels such as `Save up to 10%` reflect the maximum discount shown for that model against comparable standard API rates from the model's author, when standard rates are available. These discounts are applied automatically; no coupon or special plan required.