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

# Together AI

> Configure Together AI open-source models in EnConvo

## Overview

Together AI is an inference platform specializing in open-source models. It provides fast, cost-effective access to the best open-weight models including Llama, Mixtral, Qwen, and many more, with competitive pricing and high throughput.

## Supported Models

| Model              | Description          | Best For               |
| ------------------ | -------------------- | ---------------------- |
| **Llama 3.1 405B** | Largest open model   | Complex reasoning      |
| **Llama 3.1 70B**  | Strong open model    | General tasks, coding  |
| **Llama 3.1 8B**   | Fast open model      | Quick responses        |
| **Mixtral 8x22B**  | Mistral MoE model    | Balanced quality/speed |
| **Qwen 2.5 72B**   | Alibaba's open model | Multilingual, coding   |
| **DeepSeek V3**    | DeepSeek open model  | Reasoning, analysis    |

<Tip>
  Together AI frequently adds new open-source models as they are released. Check the model dropdown in EnConvo for the latest available models.
</Tip>

## Setup

<Steps>
  <Step title="Get API Key">
    1. Go to [Together AI](https://api.together.xyz)
    2. Sign in or create an account
    3. Navigate to **Settings** → **API Keys**
    4. Create a new API key
  </Step>

  <Step title="Configure in EnConvo">
    1. Open **Settings** → **AI Provider**
    2. Select **Together AI**
    3. Go to **Credentials** module
    4. Enter your API key
  </Step>

  <Step title="Select Model">
    Choose your preferred model from the dropdown
  </Step>
</Steps>

## Configuration

| Setting         | Description           | Default       |
| --------------- | --------------------- | ------------- |
| **Credentials** | API key configuration | Required      |
| **Model Name**  | Model to use          | Llama 3.1 70B |
| **Temperature** | Creativity (0-2)      | Medium (1)    |

## Validate and Use

<Steps>
  <Step title="Validate credentials">
    Click **Validate** in the Together AI credential settings. If validation fails, confirm the API key is active and your account has credits.
  </Step>

  <Step title="Start with a smaller model">
    Use smaller open models for quick testing before moving to larger models such as 70B or 405B variants.
  </Step>

  <Step title="Confirm model availability">
    Together AI frequently updates hosted models. If a model fails, select it from the EnConvo dropdown again or choose a nearby model family.
  </Step>
</Steps>

## Pricing

Together AI offers competitive pricing for open-source models. Check [Together AI Pricing](https://www.together.ai/pricing) for current rates.

| Model          | Input     | Output    |
| -------------- | --------- | --------- |
| Llama 3.1 405B | \$3.50/1M | \$3.50/1M |
| Llama 3.1 70B  | \$0.88/1M | \$0.88/1M |
| Llama 3.1 8B   | \$0.18/1M | \$0.18/1M |
| Mixtral 8x22B  | \$1.20/1M | \$1.20/1M |

<Note>
  New accounts receive free credits to get started. Together AI pricing is often significantly lower than commercial model providers.
</Note>

## Best Practices

<AccordionGroup>
  <Accordion title="Model Selection">
    * **Llama 3.1 405B**: When you need maximum open-source quality
    * **Llama 3.1 70B**: Best balance of quality and cost for most tasks
    * **Llama 3.1 8B**: High-volume or latency-sensitive workloads
    * **Mixtral 8x22B**: Good general-purpose alternative
    * **Qwen 2.5 72B**: Excellent for multilingual and coding tasks
  </Accordion>

  <Accordion title="Cost Optimization">
    * Start with smaller models and scale up only if needed
    * Use 8B models for simple tasks to save costs
    * Monitor usage in the Together AI dashboard
  </Accordion>
</AccordionGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="Invalid API key">
    * Verify the key is copied correctly from [api.together.xyz](https://api.together.xyz)
    * Check if your account has sufficient credits
    * Ensure the key has not been revoked
  </Accordion>

  <Accordion title="Model not available">
    * Some models may be temporarily offline for maintenance
    * Try a different model from the same family
    * Check Together AI status page for service updates
  </Accordion>

  <Accordion title="Slow responses">
    * Larger models (405B) take longer to respond
    * Switch to a smaller model for faster inference
    * Check if Together AI is experiencing high load
  </Accordion>
</AccordionGroup>