> ## 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.

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

## Available Models

|                  | **Qwen 3.6**                                                                                                                                                                             | **DeepGram General Nova 3**                                                                                                                                                              | **DeepSeek V4 Pro**                                                                                                                                                                                |
| ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Description**  | Sparse Mixture-of-Experts architecture delivering frontier-level intelligence with low latency                                                                                           | Highest-performing general-purpose ASR for meetings, captioning, and multilingual audio                                                                                                  | High-performance multimodal model specializing in advanced reasoning, full-stack coding, multilingual processing, mathematics, and precise instruction following with 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> | <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> | <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>           |
| **API ID**       | `qwen36-27b`                                                                                                                                                                             | `deepgram/general-nova-3`                                                                                                                                                                | `deepseek-v4-pro`                                                                                                                                                                                  |
| **Type**         | Chat                                                                                                                                                                                     | Audio Transcription                                                                                                                                                                      | Chat                                                                                                                                                                                               |
| **Parameters**   | 27B                                                                                                                                                                                      | -                                                                                                                                                                                        | 862B                                                                                                                                                                                               |
| **Modalities**   | Text, Image, Video                                                                                                                                                                       | Audio                                                                                                                                                                                    | Text                                                                                                                                                                                               |
| **Input price**  | \$1.50 / 1M tokens                                                                                                                                                                       | —                                                                                                                                                                                        | \$8.95 / 1M tokens                                                                                                                                                                                 |
| **Output price** | \$15.00 / 1M tokens                                                                                                                                                                      | —                                                                                                                                                                                        | \$17.20 / 1M tokens                                                                                                                                                                                |
| **Audio price**  | —                                                                                                                                                                                        | \$0.05 / min                                                                                                                                                                             | —                                                                                                                                                                                                  |
| **Weights**      | [Weights](https://huggingface.co/Qwen/Qwen3.6-27B)                                                                                                                                       | -                                                                                                                                                                                        | [Weights](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro)                                                                                                                                      |

<Info>
  All models are accessed through an OpenAI-compatible API. See the [Quickstart](/basics/build/quickstart) guide to get started.
</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>
  For detailed rate limits by tier, including token limits (TPM), audio processing limits, and concurrent request limits, see the [Rate Limits](/developer-resources/get-started/rate-limits) page.
</Tip>

<Tip>
  All APIs are served in accordance with our security model. For more information, see the [Security Model](/basics/learn-more/security-model) Page.
</Tip>

## Get Started

<CardGroup cols={3}>
  <Card title="Create Account" icon="user-plus" href="https://dashboard.prem.io">
    Sign up and start using the Confidential APIs.
  </Card>

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

  <Card title="Contact Sales" icon="envelope" href="mailto:sales@premai.io">
    Need enterprise features, custom models, or dedicated infrastructure? Get in touch.
  </Card>
</CardGroup>