> ## Documentation Index
> Fetch the complete documentation index at: https://portkey-docs-chore-backend-1-29-0.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Together AI

> Integrate Together AI models with Prisma AIRS AI Gateway

The AI Gateway provides a robust and secure gateway to integrate various Large Language Models (LLMs) into applications, including [Together AI's hosted models](https://docs.together.ai/reference/inference).

With the AI Gateway, take advantage of features like fast AI gateway access, observability, and more, while securely managing API keys through [Model Catalog](/aigw/product/model-catalog).

## Quick Start

Get Together AI working in 3 steps:

<CodeGroup>
  ```sh cURL icon="square-terminal" theme={null}
  # 1. Add @together-ai provider in model catalog
  # 2. Use it:

  curl https://aigw.portkey.ai/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $PORTKEY_API_KEY" \
    -d '{
      "model": "@together-ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
      "messages": [
        { "role": "user", "content": "Say this is a test" }
      ]
    }'
  ```

  ```python OpenAI Py icon="python" theme={null}
  from openai import OpenAI

  # 1. Install: pip install openai
  # 2. Add @together-ai provider in model catalog
  # 3. Use it:

  client = OpenAI(
      api_key="PORTKEY_API_KEY",  # AI Gateway API key
      base_url="https://aigw.portkey.ai/v1"
  )

  response = client.chat.completions.create(
      model="@together-ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
      messages=[{"role": "user", "content": "Say this is a test"}]
  )

  print(response.choices[0].message.content)
  ```

  ```js OpenAI JS icon="square-js" theme={null}
  import OpenAI from "openai"

  // 1. Install: npm install openai
  // 2. Add @together-ai provider in model catalog
  // 3. Use it:

  const client = new OpenAI({
      apiKey: "PORTKEY_API_KEY",  // AI Gateway API key
      baseURL: "https://aigw.portkey.ai/v1"
  })

  const response = await client.chat.completions.create({
      model: "@together-ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
      messages: [{ role: "user", content: "Say this is a test" }]
  })

  console.log(response.choices[0].message.content)
  ```
</CodeGroup>

<Note>
  **Tip:** You can also send `x-portkey-provider: @together-ai` as a header and use just `model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"` in the request.
</Note>

## Add Provider in Model Catalog

1. Go to [**Model Catalog → Add Provider**](https://stratacloudmanager.paloaltonetworks.com/)
2. Select **Together AI**
3. Choose existing credentials or create new by entering your [Together AI API key](https://api.together.ai/settings/api-keys)
4. Name your provider (e.g., `together-ai-prod`)

<Card title="Complete Setup Guide →" href="/aigw/product/model-catalog">
  See all setup options, code examples, and detailed instructions
</Card>

## Reasoning / Thinking Support

Together AI supports reasoning models that expose their internal chain of thought. Use the `reasoning_effort` parameter to control reasoning behaviour, and set `strict_open_ai_compliance=False` to receive the thinking content in `content_blocks`.

<CodeGroup>
  ```sh cURL theme={null}
  curl https://aigw.portkey.ai/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $PORTKEY_API_KEY" \
    -H "x-portkey-strict-open-ai-compliance: false" \
    -d '{
      "model": "@together-ai/deepseek-ai/DeepSeek-R1",
      "messages": [
        { "role": "user", "content": "Solve step by step: What is 23 * 47?" }
      ],
      "reasoning_effort": "medium"
    }'
  ```
</CodeGroup>

The reasoning response includes `content_blocks` with both the model's thinking process and the final answer. Streaming is also supported and returns reasoning chunks in the `content_blocks` field of the stream delta.

<Card title="Thinking Mode Documentation" icon="brain" href="/aigw/product/ai-gateway/multimodal-capabilities/thinking-mode">
  Learn more about thinking/reasoning support across providers
</Card>

## Video Generation

Together AI supports video generation through the AI Gateway's proxy. Generate videos from text prompts and track usage in Strata Cloud Manager.

<CodeGroup>
  ```sh cURL theme={null}
  curl --location 'https://aigw.portkey.ai/v1/v2/videos' \
    --header 'Content-Type: application/json' \
    --header 'Authorization: Bearer PORTKEY_API_KEY' \
    --data '{
      "prompt": "A serene sunset over the ocean with gentle waves",
      "model": "@together-ai/minimax/hailuo-02",
      "width": 1366,
      "height": 768
    }'
  ```
</CodeGroup>

Video generation pricing is logged in Strata Cloud Manager for cost tracking.

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Add Metadata" icon="tags" href="/aigw/product/observability/metadata">
    Add metadata to your Together AI requests
  </Card>

  <Card title="Gateway Configs" icon="gear" href="/aigw/product/ai-gateway/configs">
    Add gateway configs to your Together AI requests
  </Card>

  <Card title="Tracing" icon="chart-line" href="/aigw/product/observability/traces">
    Trace your Together AI requests
  </Card>

  <Card title="Fallbacks" icon="arrow-rotate-left" href="/aigw/product/ai-gateway/fallbacks">
    Setup fallback from OpenAI to Together AI
  </Card>
</CardGroup>


## Related topics

- [Enterprise Gateway](/changelog/enterprise.md)
- [Thinking Mode](/aigw/product/ai-gateway/multimodal-capabilities/thinking-mode.md)
- [Prisma AIRS AI Gateway Models](/aigw/product/model-catalog/gateway-models.md)
- [Overview](/aigw/integrations/llms.md)
- [Messages](/aigw/product/ai-gateway/messages-api.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.