---
updatedAt: 2025-12-23T19:10:57.000Z
agentTools:
  projectIndex: https://ai-studio-docs.quiq.com/llms.txt
---

# Supported LLMs

AI Studio supports a variety of LLMs, enabling you to choose the right model for a given task. Whenever possible we provision redundant resources spanning different cloud regions and providers to maximize reliability. For an overview of how AI studio interacts with LLMs please review the section on Prompt AI Behaviors.

In order to insure proper resource allocation, some LLMs require you to contact Quiq Support to be enabled.

<Table align={["left","left","left","left","left"]}>
  <thead>
    <tr>
      <th style={{ textAlign: "left" }}>
        LLM
      </th>

      <th style={{ textAlign: "left" }}>
        Description
      </th>

      <th style={{ textAlign: "left" }}>
        External API Reference
      </th>

      <th style={{ textAlign: "left" }}>
        Example Functions
      </th>

      <th style={{ textAlign: "left" }}>
        Contact Support?
      </th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td style={{ textAlign: "left" }}>
        `gpt-4o-0806`
      </td>

      <td style={{ textAlign: "left" }}>
        ChatCompletion style built by OpenAI, available through both OpenAI and Azure cloud offerings. Slower but generally more accurate than 35-turbo models.

        * `completion` maps to `/choices[0]["message"]["content"]` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://platform.openai.com/docs/api-reference/chat)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#open-ai-chatcompletions-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `gpt-4o-mini-0718`
      </td>

      <td style={{ textAlign: "left" }}>
        ChatCompletion style built by OpenAI, available through both OpenAI and Azure cloud offerings. Slower but generally more accurate than 35-turbo models.

        * `completion` maps to `/choices[0]["message"]["content"]` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://platform.openai.com/docs/api-reference/chat)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#open-ai-chatcompletions-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        No
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `gpt-4o-1120`
      </td>

      <td style={{ textAlign: "left" }}>
        ChatCompletion style built by OpenAI, available through both OpenAI and Azure cloud offerings. Slower but generally more accurate than 35-turbo models.

        * `completion` maps to `/choices[0]["message"]["content"]` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://platform.openai.com/docs/api-reference/chat)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#open-ai-chatcompletions-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `gpt-5-nano-2025-08-07`
      </td>

      <td style={{ textAlign: "left" }}>
        ChatCompletion style built by OpenAI, available through both OpenAI and Azure cloud offerings. Slower but generally more accurate than 35-turbo models.

        * `completion` maps to `/choices[0]["message"]["content"]` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://platform.openai.com/docs/api-reference/chat)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#open-ai-chatcompletions-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        No
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `gpt-5-mini-2025-08-07`
      </td>

      <td style={{ textAlign: "left" }}>
        ChatCompletion style built by OpenAI, available through both OpenAI and Azure cloud offerings. Slower but generally more accurate than 35-turbo models.

        * `completion` maps to `/choices[0]["message"]["content"]` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://platform.openai.com/docs/api-reference/chat)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#open-ai-chatcompletions-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `o3-mini-0131`
      </td>

      <td style={{ textAlign: "left" }}>
        ChatCompletion style and reasoning model built by OpenAI, available through both OpenAI and Azure cloud offerings.

        * `completion` maps to `/choices[0]["message"]["content"]` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://platform.openai.com/docs/api-reference/chat)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#open-ai-chatcompletions-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `o4-mini-0416`
      </td>

      <td style={{ textAlign: "left" }}>
        ChatCompletion style and reasoning model built by OpenAI, available through both OpenAI and Azure cloud offerings.

        * `completion` maps to `/choices[0]["message"]["content"]` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://platform.openai.com/docs/api-reference/chat)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#open-ai-chatcompletions-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `llama3-1-8b-instruct-v1`
      </td>

      <td style={{ textAlign: "left" }}>
        The 8B parameter variant of the Llama 3 Chat family of LLMs built by Meta. Hosted on AWS Bedrock.

        * `completion` maps to `/generation` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#llama-3-bedrock-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `llama3-2-1b-instruct`
      </td>

      <td style={{ textAlign: "left" }}>
        The 1B parameter variant of the Llama3 Chat family of LLMs built by Meta. Hosted on AWS Bedrock.

        * `completion` maps to `/generation` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `llama3-2-3b-instruct`
      </td>

      <td style={{ textAlign: "left" }}>
        The 3B parameter variant of the Llama3 Chat family of the LLMs built by Meta. Hosted on AWS Bedrock.

        * `completion` maps to `/generation` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `llama3-2-11b-instruct`
      </td>

      <td style={{ textAlign: "left" }}>
        The 11B parameter variant of the Llama3 Chat family of the LLMs built by Meta. Hosted on AWS Bedrock.

        * `completion` maps to `/generation` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `llama3-2-90b-instruct`
      </td>

      <td style={{ textAlign: "left" }}>
        The 90B parameter variant of the Llama3 Chat family of the LLMs built by Meta. hosted on AWS Bedrock and GCP.

        * `completion` maps to `/generation` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `llama3-3-70b-instruct`
      </td>

      <td style={{ textAlign: "left" }}>
        The 70B parameter variant of the Llama3 Chat family of the LLMs built by Meta. hosted on AWS Bedrock and GCP.

        * `completion` maps to `/generation` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `llama4-maverick-17b-instruct`
      </td>

      <td style={{ textAlign: "left" }}>
        The 17B parameter variant of the Llama4 Maverick Chat family of the LLMs built by Meta. hosted on AWS Bedrock and GCP.

        * `completion` maps to `/generation` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `llama4-scout-17b-instruct`
      </td>

      <td style={{ textAlign: "left" }}>
        The 17B parameter variant of the Llama4 Scout Chat family of the LLMs built by Meta. hosted on AWS Bedrock and GCP.

        * `completion` maps to `/generation` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `claude-3-haiku`
      </td>

      <td style={{ textAlign: "left" }}>
        Claude V3 Haiku model by Anthropic - hosted on AWS Bedrock.

        * `completion` maps to `/content/text` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.anthropic.com/claude/reference/messages_post)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#claude-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        No
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `claude-3-5-haiku`
      </td>

      <td style={{ textAlign: "left" }}>
        Claude V3.5 Haiku model by Anthropic - hosted on AWS Bedrock.

        * `completion` maps to `/content/text` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.anthropic.com/claude/reference/messages_post)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#claude-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `claude-3-5-sonnet`
      </td>

      <td style={{ textAlign: "left" }}>
        Claude V3.5 V2 Sonnet model by Anthropic - hosted on AWS Bedrock.

        * `completion` maps to `/content/text` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.anthropic.com/claude/reference/messages_post)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#claude-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `claude-sonnet-4-5-20250929`
      </td>

      <td style={{ textAlign: "left" }}>
        Claude V4.5 V1 Sonnet model by Anthropic - hosted on AWS Bedrock.

        * `completion` maps to `/content/text` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.anthropic.com/claude/reference/messages_post)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#claude-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `claude-haiku-4-5-20251001`
      </td>

      <td style={{ textAlign: "left" }}>
        Claude V4.5 V1 Haiku model by Anthropic - hosted on AWS Bedrock.

        * `completion` maps to `/content/text` in the response
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.anthropic.com/claude/reference/messages_post)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#claude-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `gemini-2.0-flash`
      </td>

      <td style={{ textAlign: "left" }}>
        Googles Gemini 2.0 Flash model which tends to be faster than the 1.5 Flash version.

        * `completion` maps to `/candidates/0/content/parts/0/text`
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai.google.dev/api/generate-content)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#gemini-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        No
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `gemini-2.5-flash-lite`
      </td>

      <td style={{ textAlign: "left" }}>
        Googles Gemini 2.5 Flash Lite model which tends to be faster than the 1.5 Flash version.

        * `completion` maps to `/candidates/0/content/parts/0/text`
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai.google.dev/api/generate-content)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#gemini-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        No
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `gemini-2.5-flash`
      </td>

      <td style={{ textAlign: "left" }}>
        Googles Gemini 2.0 Flash model which tends to be faster than the 1.5 Flash version.

        * `completion` maps to `/candidates/0/content/parts/0/text`
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai.google.dev/api/generate-content)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#gemini-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        No
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `gemini-2.5-pro`
      </td>

      <td style={{ textAlign: "left" }}>
        Googles Gemini 2.5 Pro model which tends to be faster than the 2.5 Flash version.

        * `completion` maps to `/candidates/0/content/parts/0/text`
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai.google.dev/api/generate-content)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#gemini-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `gemini-3-flash-preview`
      </td>

      <td style={{ textAlign: "left" }}>
        Googles Gemini 3.0 Flash Preview model which tends to be faster than the 2.5 Flash version.

        * `completion` maps to `/candidates/0/content/parts/0/text`
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai.google.dev/api/generate-content)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#gemini-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `nova-lite`
      </td>

      <td style={{ textAlign: "left" }}>
        Amazon Nova Lite model - hosted on AWS Bedrock.

        * `completion` maps to `/output/message/content/0/text`
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/nova/latest/userguide/using-invoke-api.html)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#gemini-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `nova-micro`
      </td>

      <td style={{ textAlign: "left" }}>
        Amazon Nova Micro model - hosted on AWS Bedrock.

        * `completion` maps to `/output/message/content/0/text`
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/nova/latest/userguide/using-invoke-api.html)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#gemini-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>

    <tr>
      <td style={{ textAlign: "left" }}>
        `nova-pro`
      </td>

      <td style={{ textAlign: "left" }}>
        Amazon Nova Pro model - hosted on AWS Bedrock.

        * `completion` maps to `/output/message/content/0/text`
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://docs.aws.amazon.com/nova/latest/userguide/using-invoke-api.html)
      </td>

      <td style={{ textAlign: "left" }}>
        [Link](https://ai-studio-docs.quiq.com/docs/prompt-ai-behavior-examples#gemini-examples)
      </td>

      <td style={{ textAlign: "left" }}>
        Yes
      </td>
    </tr>
  </tbody>
</Table>

Notes

* When building prompt payloads in the Function Editor you can assume that the `request` object should generally mimic the request payload of the underlying LLM according to its docs, but the framework may override certain parameters. See the example functions
* Some LLM request payloads specify the model in the payload. AI studio will implicitly set/override these parts of your prompt objects
* When an LLM is invoked on behalf of a resource transformation we may override settings such as temperature to produce the most deterministic result

We continually uptake new LLMs and have preliminary support for additional models not listed in this documentation. Contact Quiq support or your account rep if you have specific LLM requirements

## Custom LLMs

Custom LLMs enable you to communicate with your own LLM resources rather than Quiq's managed resources. For example, if you've created your own fine-tuned ChatCompletion model hosted by OpenAI, you can configure AI studio to use your fine-tuned resource. Configuring a Custom LLM requires the following information:

* The URL where the LLM is hosted
* Appropriate credentials enabling AI Studio to securely access the LLM
* The family/style of LLM resource (for purposes of matching the API contract)

In order to register a Custom LLM, contact Quiq Support.

## Embeddings Models

The following table lists the supported models for embedding your AI Resources for purposes of semantic search.

| Model                    | Description                                                              | Contact Support? |
| :----------------------- | :----------------------------------------------------------------------- | :--------------- |
| `text-ada-002-embedding` | Built by OpenAI, available through both OpenAI and Azure cloud offerings | No               |
| `titan-embed-text-v1`    | Built by Amazon and and available through AWS                            | Yes              |
| `text-embedding-3-small` | Built by OpenAI, available through both OpenAI and Azure cloud offerings | Yes              |
| `text-embedding-3-large` | Built by OpenAI, available through both OpenAI and Azure cloud offerings | Yes              |
| `gemini-embedding-001`   | Built by Google, available through Google cloud offerings                | No               |