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

# Supported AI Models

Agent Platform supports a wide range of AI models—platform-hosted, open-source, externally integrated, and third-party. Choose based on your use case: agentic workflows, real-time voice, or background processing.

***

## Models for Agentic Apps and Agents

### External Models

Agentic Apps support Agent and Supervisor orchestration with models from these providers:

| Provider | Model Variants |
| :- | :- |
| OpenAI | <ul><li>chat-latest</li><li>gpt-5.5</li><li>gpt-5.5-2026-04-23</li><li>gpt-5.4</li><li>gpt-5.4-nano</li><li>gpt-5.4-mini</li><li>gpt-realtime-2</li><li>gpt-realtime-1.5</li><li>gpt-5.3-chat-latest</li><li>gpt-5.2-2025-12-11</li><li>gpt-5.2</li><li>gpt-5.2-chat-latest</li><li>gpt-5.1-2025-11-13</li><li>gpt-5.1</li><li>gpt-5.1-chat-latest</li><li>gpt-realtime-mini-2025-10-06</li><li>gpt-audio-mini-2025-10-06</li><li>gpt-5-2025-08-07</li><li>gpt-5-mini-2025-08-07</li><li>gpt-5-nano-2025-08-07</li><li>gpt-audio-2025-08-28</li><li>gpt-realtime-2025-08-28</li><li>gpt-5</li><li>gpt-5-mini</li><li>gpt-5-nano</li><li>gpt-5-chat-latest</li><li>gpt-4o-audio-preview-2025-06-03</li><li>gpt-4.5-preview-2025-02-27</li><li>o3-2025-04-16</li><li>o4-mini-2025-04-16</li><li>gpt-4.1-2025-04-14</li><li>gpt-4.1-mini-2025-04-14</li><li>gpt-4.1-nano-2025-04-14</li><li>gpt-4o-search-preview-2025-03-11</li><li>o3-mini-2025-01-31</li><li>gpt-4o-mini-audio-preview-2024-12-17</li><li>gpt-4o-audio-preview-2024-12-17</li><li>o1-2024-12-17</li><li>gpt-4o-2024-11-20</li><li>gpt-4o-2024-08-06</li><li>gpt-4o-mini-2024-07-18</li><li>gpt-4o-2024-05-13</li><li>gpt-4-turbo-2024-04-09</li><li>gpt-4-1106-preview</li><li>gpt-4-0125-preview</li><li>gpt-4-turbo-preview</li><li>gpt-4-0613</li><li>gpt-4o</li><li>gpt-4o-mini</li><li>gpt-4</li><li>gpt-4o-search-preview</li><li>gpt-4.1</li><li>gpt-4.1-mini</li><li>gpt-4.1-nano</li><li>gpt-4-turbo</li><li>gpt-3.5-turbo-1106</li><li>gpt-3.5-turbo-0125</li><li>gpt-3.5-turbo</li><li>gpt-4o-mini-transcribe</li><li>gpt-4o-mini-audio-preview</li><li>gpt-4o-audio-preview</li><li>gpt-audio-mini</li><li>gpt-audio</li><li>gpt-image-1-mini</li><li>gpt-image-1</li><li>gpt-image-1.5</li><li>gpt-realtime-mini</li><li>gpt-realtime</li><li>o4-mini</li><li>o3</li><li>o1</li></ul> |
| Azure OpenAI | <ul><li>GPT-5.3-Chat</li><li>GPT-5.4</li><li>GPT-5.4-Nano</li><li>GPT-5.4-Mini</li><li>GPT-Realtime-1.5</li><li>GPT-3.5-Turbo</li><li>GPT-4</li><li>GPT-4o</li><li>GPT-4o-Mini</li><li>GPT-4.1</li><li>GPT-4.1-Nano</li><li>GPT-4.1-Mini</li><li>O1</li><li>O1-Mini</li><li>O3-Mini</li><li>GPT-5</li><li>GPT-5-Mini</li><li>GPT-5-Nano</li><li>GPT-5-Chat</li><li>GPT-5.1</li><li>GPT-5.1-Chat</li><li>GPT-5.2</li><li>GPT-5.2-Chat</li></ul> |
| Anthropic | <ul><li>claude-opus-4-8</li><li>claude-opus-4-7</li><li>claude-sonnet-4-6</li><li>claude-3-5-sonnet</li><li>claude-3-haiku</li><li>claude-3-sonnet</li><li>claude-3-opus</li><li>claude-3-7-sonnet-20250219</li><li>claude-3-5-sonnet-20241022</li><li>claude-sonnet-4-20250514</li><li>claude-sonnet-4-5-20250929</li><li>claude-3-5-haiku-20241022</li><li>claude-haiku-4-5-20251001</li><li>claude-opus-4-20250514</li><li>claude-opus-4-1-20250805</li><li>claude-opus-4-5-20251101</li><li>claude-opus-4-6</li></ul> |
| Google | <ul><li>gemini-3.5-flash</li><li>gemini-3.1-pro-preview</li><li>gemini-3.1-flash-lite</li><li>gemini-3.1-flash-live-preview</li><li>gemini-3.1-pro-preview</li><li>gemini-3.1-flash-lite-preview</li><li>gemini-3.1-pro-preview-customtools</li><li>gemini-2.5-flash-native-audio-preview-12-2025</li><li>gemini-2.5-flash-native-audio-preview-09-2025</li><li>gemini-2.5-flash-preview-09-2025</li><li>gemini-2.5-flash-lite-preview-09-2025</li><li>gemini-3-pro-preview</li><li>gemini-3-pro-image-preview</li><li>gemini-3-flash-preview</li><li>gemini-2.5-flash-preview-05-20</li><li>gemini-2.5-flash</li><li>gemini-2.5-pro</li><li>gemini-2.5-flash-lite</li><li>gemini-2.5-flash-image</li><li>gemini-2.0-flash</li><li>gemini-2.0-flash-lite</li><li>gemini-1.5-flash-latest</li><li>gemini-1.5-pro</li><li>gemini-1.0-pro</li></ul> |

### Open-Source Models

Agentic Apps support select open-source models from these providers:

| Provider | Model Variants |
| :- | :- |
| Meta-llama | <ul><li>meta-llama/Meta-Llama-3.1-8B-Instruct</li><li>meta-llama/Llama-3.2-1B-Instruct</li><li>meta-llama/Llama-3.2-3B-Instruct</li></ul> |
| Mistralai | <ul><li>mistralai/Mistral-7B-Instruct-v0.3</li><li>mistralai/Mistral-Nemo-Instruct-2407</li></ul> |
| Xiaomimimo | <ul><li>XiaomiMiMo/MiMo-VL-7B-RL</li></ul> |

### Real-Time Voice Models

Real-Time Voice is available only with the following models:

| Provider | Model Variants |
| :- | :- |
| OpenAI | <ul><li>gpt-realtime-2</li><li>gpt-realtime-1.5</li><li>gpt-realtime-mini-2025-10-06</li><li>gpt-realtime-2025-08-28</li><li>gpt-realtime-mini</li><li>gpt-realtime</li></ul> |
| Google Gemini | <ul><li>gemini-live-2.5-flash-preview</li><li>gemini-2.0-flash-live-001</li></ul> These models are not supported with Adaptive Network Orchestration. |
| Azure OpenAI | <ul><li>GPT-Realtime</li><li>GPT-Realtime-Mini</li></ul> |

### Custom Model Integration

To use a custom third-party model in Agentic Apps, it must meet two requirements:

#### Tool Calling Support (Mandatory)

The model must natively support Tool Calling. Models without this capability cannot be used in Agentic Apps.

If supported, enable Tool Calling explicitly during model configuration.

![Enable Tool Calling](https://mintcdn.com/koreai/heZ8XBmKiQhpZGaT/agent-platform/v1/models/images/custom-model/enable-tool.png?fit=max\&auto=format\&n=heZ8XBmKiQhpZGaT\&q=85\&s=119ee1313a6c642960382b0c72ee805f)

[Learn how to enable model features](https://koreai.mintlify.site/agent-platform/v1/models/external-models.md#add-a-model-via-api-integration)

#### Compatible API Structure

The request and response structure must follow either:

* **Anthropic** – Messages API
* **OpenAI** – Chat Completions API

![Request/Response Structures](https://mintcdn.com/koreai/heZ8XBmKiQhpZGaT/agent-platform/v1/models/images/custom-model/format.png?fit=max\&auto=format\&n=heZ8XBmKiQhpZGaT\&q=85\&s=a1190c664e071aa1a8de2fc6a2277d57)

For setup steps, see [Add an External Model Using API Integration](https://koreai.mintlify.site/agent-platform/v1/models/external-models.md).

***

## Platform-Hosted Open-Source Models

The platform hosts 30+ curated open-source models, available as a service and optimizable before deployment.

| Provider | Model Variants |
| :- | :- |
| Argilla | <ul><li>argilla/notus-7b-v1</li><li>argilla/notux-8x7b-v1</li></ul> |
| DeepSeek | <ul><li>deepseek-ai/DeepSeek-R1-Distill-Llama-8B</li><li>deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B</li><li>deepseek-ai/DeepSeek-R1-Distill-Qwen-14B</li><li>deepseek-ai/DeepSeek-R1-Distill-Qwen-7B</li></ul> |
| EleutherAI | <ul><li>EleutherAI/gpt-j-6b</li><li>EleutherAI/gpt-neo-1.3B</li><li>EleutherAI/gpt-neo-125m</li><li>EleutherAI/gpt-neo-2.7B</li><li>EleutherAI/gpt-neox-20b</li></ul> |
| Facebook | <ul><li>facebook/opt-1.3b</li><li>facebook/opt-2.7b</li><li>facebook/opt-350m</li><li>facebook/opt-6.7b</li></ul> |
| Google | <ul><li>google/flan-t5-base</li><li>google/flan-t5-large</li><li>google/flan-t5-small</li><li>google/flan-t5-xl</li><li>google/flan-t5-xxl</li><li>google/gemma-2-27b-it</li><li>google/gemma-2-9b-it</li><li>google/gemma-2b</li><li>google/gemma-2b-it</li><li>google/gemma-3-12b-it</li><li>google/gemma-7b</li><li>google/gemma-7b-it</li></ul> |
| Helsinki-NLP | <ul><li>Helsinki-NLP/opus-mt-es-en</li></ul> |
| HuggingFaceH4 | <ul><li>HuggingFaceH4/zephyr-7b-alpha</li><li>HuggingFaceH4/zephyr-7b-beta</li></ul> |
| Meta-llama | <ul><li>meta-llama/Llama-2-13b-hf</li><li>meta-llama/Llama-2-7b-hf</li><li>meta-llama/Llama-3.2-1B</li><li>meta-llama/Llama-3.2-1B-Instruct</li><li>meta-llama/Llama-3.2-3B</li><li>meta-llama/Llama-3.2-3B-Instruct</li><li>meta-llama/Llama-3.2-11B-Vision-Instruct</li><li>meta-llama/Llama-Guard-4-12B</li><li>meta-llama/Meta-Llama-3-8B</li><li>meta-llama/Meta-Llama-3-8B-Instruct</li><li>meta-llama/Meta-Llama-3.1-8B</li><li>meta-llama/Meta-Llama-3.1-8B-Instruct</li></ul> |
| Microsoft | <ul><li>microsoft/phi-1</li><li>microsoft/phi-1\_5</li><li>microsoft/phi-2</li><li>microsoft/Phi-3-medium-128k-instruct</li><li>microsoft/Phi-3-medium-4k-instruct</li><li>microsoft/Phi-3-mini-128k-instruct</li><li>microsoft/Phi-3-mini-4k-instruct</li></ul> |
| Mistralai | <ul><li>mistralai/Mistral-7B-Instruct-v0.1</li><li>mistralai/Mistral-7B-Instruct-v0.2</li><li>mistralai/Mistral-7B-Instruct-v0.3</li><li>mistralai/Mistral-7B-v0.1</li><li>mistralai/Mistral-Nemo-Instruct-2407</li><li>mistralai/Mixtral-8x7B-Instruct-v0.1</li><li>mistralai/Mixtral-8x7B-v0.1</li></ul> |
| OpenAI | <ul><li>GPT2</li></ul> |
| OpenAI Community | <ul><li>openai-community/gpt2-large</li><li>openai-community/gpt2-medium</li><li>openai-community/gpt2-xl</li></ul> |
| Stable Diffusion | <ul><li>stabilityai/stable-diffusion-xl-base-1.0</li><li>stabilityai/stable-diffusion-2-1</li><li>stable-diffusion-v1-5/stable-diffusion-v1-5 (Available only in the text-to-image node; no Prompt Studio support)</li></ul> |
| T5 | <ul><li>t5-base</li><li>t5-large</li><li>t5-small</li></ul> |
| Tiiuae | <ul><li>tiiuae/falcon-40b</li><li>tiiuae/falcon-40b-instruct</li><li>tiiuae/falcon-7b</li><li>tiiuae/falcon-7b-instruct</li><li>tiiuae/falcon-rw-1b</li></ul> |
| Xiaomimimo | <ul><li>XiaomiMiMo/MiMo-VL-7B-RL</li></ul> |

### Structured Output

Platform-hosted models can produce structured JSON responses, making outputs consistent and easy to parse.

**Supported optimization techniques**: No optimization or vLLM only.

> [!NOTE]
>
> CT2-optimized, fine-tuned, Hugging Face imported, and locally imported models do not support structured output.

| Model | vLLM | No Optimization |
| - | :-: | :-: |
| amazon/MistralLite | ❌ | ✅ |
| argilla/notus-7b-v1 | ❌ | ✅ |
| EleutherAI/gpt-j-6b | ❌ | ✅ |
| facebook/opt-1.3b | ✅ | ✅ |
| facebook/opt-2.7b | ✅ | ✅ |
| facebook/opt-350m | ✅ | ✅ |
| facebook/opt-6.7b | ✅ | ✅ |
| google/gemma-2b | ❌ | ✅ |
| google/gemma-2b-it | ❌ | ✅ |
| google/gemma-7b | ❌ | ✅ |
| google/gemma-7b-it | ❌ | ✅ |
| HuggingFaceH4/zephyr-7b-alpha | ❌ | ✅ |
| HuggingFaceH4/zephyr-7b-beta | ❌ | ✅ |
| meta-llama/Llama-2-7b-chat-hf | ❌ | ❌ |
| meta-llama/Llama-2-7b-hf | ❌ | ✅ |
| meta-llama/Llama-3.2-1B | ✅ | ❌ |
| meta-llama/Llama-3.2-1B-Instruct | ✅ | ❌ |
| meta-llama/Llama-3.2-3B | ✅ | ❌ |
| meta-llama/Llama-3.2-3B-Instruct | ✅ | ❌ |
| meta-llama/Meta-Llama-3-8B | ✅ | ✅ |
| meta-llama/Meta-Llama-3-8B-Instruct | ❌ | ✅ |
| meta-llama/Meta-Llama-3.1-8B | ✅ | ✅ |
| meta-llama/Meta-Llama-3.1-8B-Instruct | ❌ | ✅ |
| microsoft/Phi-3-medium-128k-instruct | ❌ | ✅ |
| microsoft/Phi-3-medium-4k-instruct | ❌ | ✅ |
| microsoft/Phi-3-mini-128k-instruct | ✅ | ✅ |
| microsoft/Phi-3-mini-4k-instruct | ❌ | ✅ |
| microsoft/phi-1 | ❌ | ✅ |
| microsoft/phi-1\_5 | ❌ | ✅ |
| microsoft/phi-2 | ✅ | ✅ |
| mistralai/Mistral-7B-Instruct-v0.1 | ❌ | ✅ |
| mistralai/Mistral-7B-Instruct-v0.2 | ❌ | ✅ |
| mistralai/Mistral-7B-Instruct-v0.3 | ✅ | ✅ |
| mistralai/Mistral-7B-v0.1 | ❌ | ✅ |
| openai-community/gpt2-large | ❌ | ✅ |
| openai-community/gpt2-medium | ❌ | ✅ |
| openai-community/gpt2-xl | ❌ | ✅ |
| tiiuae/falcon-7b | ❌ | ✅ |
| tiiuae/falcon-7b-instruct | ❌ | ✅ |
| tiiuae/falcon-rw-1b | ✅ | ✅ |

***

## External Models for Easy Integration

With Easy Integration, connect to external model providers without any infrastructure setup—just authenticate and start using models in flows, tools, or agents.

| Provider | Model Variants |
| :- | :- |
| Anthropic | <ul><li>claude-opus-4-8</li><li>claude-opus-4-7</li><li>claude-sonnet-4-6</li><li>claude-3-5-sonnet-20240620</li><li>claude-3-haiku-20240307</li><li>claude-3-opus-20240229</li><li>claude-3-sonnet-20240229</li><li>claude-2.1</li><li>claude-2.0</li><li>claude-3-7-sonnet-20250219</li><li>claude-3-5-sonnet-20241022</li><li>claude-3-5-haiku-20241022</li><li>claude-sonnet-4-20250514</li><li>claude-opus-4-20250514</li><li>claude-opus-4-1-20250805</li><li>claude-opus-4-5-20251101</li><li>claude-haiku-4-5-20251001</li><li>claude-sonnet-4-5-20250929</li><li>claude-opus-4-6</li><li>Claude Sonnet Vision (Available only for the image-to-text node; no Prompt Studio support)</li></ul> |
| Azure OpenAI | <ul><li>GPT-5.3-Chat</li><li>GPT-5.4</li><li>GPT-5.4-Nano</li><li>GPT-5.4-Mini</li><li>GPT-Realtime-1.5</li><li>GPT-4</li><li>GPT-3.5-Turbo</li><li>GPT-4o-Mini</li><li>GPT-4o</li><li>GPT-4.1</li><li>GPT-4.1-mini</li><li>GPT-4.1-nano</li><li>GPT-4.5-preview</li><li>O1-Mini</li><li>O1</li><li>O3-Mini</li><li>GPT-5</li><li>GPT-5-Mini</li><li>GPT-5-Nano</li><li>GPT-5-Chat</li><li>GPT-5.1</li><li>GPT-5.1-Chat</li><li>GPT-5.2</li><li>GPT-5.2-Chat</li></ul> |
| Cohere | <ul><li>command-light-nightly</li><li>command-light</li><li>command</li><li>command-nightly</li></ul> |
| Google | <ul><li>gemini-3.7-flash</li><li>gemini-3.7-flash-lite</li><li>gemini-3.6-flash</li><li>gemini-3.5-flash-lite</li><li>gemini-3.5-flash</li><li>gemini-3.1-pro-preview</li><li>gemini-3.1-flash-lite</li><li>gemini-3.1-flash-live-preview</li><li>gemini-3.1-flash-lite-preview</li><li>gemini-3.1-pro-preview-customtools</li><li>gemini-2.5-flash-native-audio-preview-12-2025</li><li>gemini-2.5-flash-native-audio-preview-09-2025</li><li>gemini-2.5-flash-preview-09-2025</li><li>gemini-2.5-flash-lite-preview-09-2025</li><li>gemini-3-pro-preview</li><li>gemini-3-pro-image-preview</li><li>gemini-3-flash-preview</li><li>gemini-2.5-flash-preview-05-20</li><li>gemini-2.5-Pro</li><li>gemini-2.5-flash</li><li>gemini-2.5-flash-lite</li><li>gemini-2.5-flash-image</li><li>gemini-2.0-flash</li><li>gemini-2.0-flashlite</li><li>gemini-1.5-flash-latest</li><li>gemini-1.5-pro</li><li>gemini-1.0-pro</li></ul> |
| OpenAI | <ul><li>chat-latest</li><li>gpt-5.5</li><li>gpt-5.5-2026-04-23</li><li>gpt-5.4</li><li>gpt-5.4-nano</li><li>gpt-5.4-mini</li><li>gpt-realtime-2</li><li>gpt-realtime-1.5</li><li>gpt-5.3-chat-latest</li><li>gpt-5.2-2025-12-11</li><li>gpt-5.2</li><li>gpt-5.2-chat-latest</li><li>gpt-5.1-2025-11-13</li><li>gpt-5.1</li><li>gpt-5.1-chat-latest</li><li>gpt-5-2025-08-07</li><li>gpt-5-nano-2025-08-07</li><li>gpt-5-mini-2025-08-07</li><li>gpt-5</li><li>gpt-5-nano</li><li>gpt-5-mini</li><li>gpt-5-chat-latest</li><li>gpt-4.5-preview-2025-02-27</li><li>gpt-4.1-2025-04-14</li><li>gpt-4.1-mini-2025-04-14</li><li>gpt-4.1-nano-2025-04-14</li><li>gpt-realtime-mini-2025-10-06</li><li>gpt-audio-mini-2025-10-06</li><li>gpt-audio-2025-08-28</li><li>gpt-realtime-2025-08-28</li><li>gpt-4o-audio-preview-2025-06-03</li><li>o3-2025-04-16</li><li>o4-mini-2025-04-16</li><li>gpt-4o-search-preview-2025-03-11</li><li>o3-mini-2025-01-31</li><li>gpt-4o-mini-audio-preview-2024-12-17</li><li>gpt-4o-audio-preview-2024-12-17</li><li>o1-2024-12-17</li><li>gpt-4o-2024-11-20</li><li>gpt-4o-2024-08-06</li><li>gpt-4o-mini-2024-07-18</li><li>gpt-4o-2024-05-13</li><li>gpt-4-turbo-2024-04-09</li><li>gpt-4-1106-preview</li><li>gpt-4-0125-preview</li><li>gpt-4-turbo-preview</li><li>gpt-4-0613</li><li>gpt-4o</li><li>gpt-4o-mini</li><li>gpt-4</li><li>gpt-4o-search-preview</li><li>gpt-4.1</li><li>gpt-4.1-mini</li><li>gpt-4.1-nano</li><li>gpt-4-turbo</li><li>gpt-3.5-turbo-0125</li><li>gpt-3.5-turbo-1106</li><li>gpt-3.5-turbo</li><li>gpt-4o-mini-transcribe</li><li>gpt-4o-mini-audio-preview</li><li>gpt-4o-audio-preview</li><li>gpt-audio-mini</li><li>gpt-audio</li><li>gpt-image-1-mini</li><li>gpt-image-1</li><li>gpt-image-1.5</li><li>gpt-realtime-mini</li><li>gpt-realtime</li><li>o4-mini</li><li>o3</li><li>o1-mini</li><li>o1-preview</li><li>o1</li><li>whisper-1</li><li>whisper (Available only for the audio-to-text node; no Prompt Studio support)</li><li>dall-e-3</li><li>dall-e-2</li><li>text-embedding-3-large</li><li>text-embedding-3-small</li><li>text-embedding-ada-002</li></ul> |

***


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