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

# Models & Pricing

> Explore available models, pricing tiers, and deployment strategies, from shared infrastructure to air-gapped on-prem.

This page shows the prices for all available models on the Prem API platform. All prices are pay-as-you-go, based on usage.

## Available Models

| Model                                                                                      | API ID                    | Type                | Modalities         | Pricing                             |
| :----------------------------------------------------------------------------------------- | :------------------------ | :------------------ | :----------------- | :---------------------------------- |
| **Qwen 3.6** · 27B ([weights](https://huggingface.co/Qwen/Qwen3.6-27B))                    | `qwen36-27b`              | Chat                | Text, Image, Video | \$1.50 in · \$15.00 out / 1M tokens |
| **DeepGram General Nova 3**                                                                | `deepgram/general-nova-3` | Audio Transcription | Audio              | \$0.05 / audio minute               |
| **DeepSeek V4 Pro** · 862B ([weights](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro)) | `deepseek-v4-pro`         | Chat                | Text               | \$8.95 in · \$17.20 out / 1M tokens |

* **Qwen 3.6**: A sparse Mixture-of-Experts architecture. It gives frontier-level intelligence with low latency.
* **DeepGram General Nova 3**: A general-purpose ASR model with the highest performance. Use it for meetings, captions, and multilingual audio.
* **DeepSeek V4 Pro**: A high-performance multimodal model. It is good at advanced reasoning, full-stack coding, multilingual processing, mathematics, and precise instruction following. It has robust tool-use capabilities.

<span className="not-prose"><a href="https://dashboard.prem.io" target="_blank" className="transition-opacity hover:opacity-70"><Badge color="blue">Try in Playground</Badge></a></span>

<Info>
  You get access to all models through an OpenAI-compatible API. See the [Quickstart](/quickstart) guide to start.
</Info>

## Deployment Strategies

| Feature              | Explorer          | Developer           | Enterprise           |
| -------------------- | ----------------- | ------------------- | -------------------- |
| **Rate Limit**       | 10 req / sec      | Scalable            | Dedicated            |
| **API Deployment**   | Multi-Tenant APIs | Dedicated APIs      | Dedicated APIs       |
| **Model Deployment** | Curated Models    | Custom Model Choice | Custom Model Choice  |
| **Infrastructure**   | Shared Instances  | Dedicated Instances | air-gapped / on-prem |

<Tip>
  See the [Rate Limits](/rate-limits) page for the rate limits of each tier. The page includes token limits (TPM), audio processing limits, and concurrent request limits.
</Tip>

<Tip>
  Prem serves all APIs in agreement with its security model. For more information, see the [Security Model](/security-model) page.
</Tip>

## Get Started

<CardGroup cols={3}>
  <Card title="Create Account" icon="user-plus" href="https://dashboard.prem.io" arrow="true">
    Register. Then start to use the Confidential APIs.
  </Card>

  <Card title="Quickstart" icon="bolt" href="/quickstart" arrow="true">
    Make your first API call in minutes.
  </Card>

  <Card title="Contact Sales" icon="envelope" href="mailto:sales@premai.io" arrow="true">
    Contact Prem for enterprise features, custom models, or dedicated infrastructure.
  </Card>
</CardGroup>