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

# Supported AI Models

AI for Process supports a wide range of AI models across major providers. You can use platform-hosted open-source models or connect to external providers through Easy Integration.

## Open-Source Models

AI for Process supports over thirty open-source models and provides them as a service. Platform-hosted models can be optimized prior to deployment, making them ideal for private environments or specialized applications.

The following table lists the supported models and their variants:

| **Model Provider**   | **Model Variant**                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
| -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Amazon**           | • amazon/MistralLite                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
| **Argilla**          | • argilla/notus-7b-v1<br /> • argilla/notux-8x7b-v1                                                                                                                                                                                                                                                                                                                                                                                                                    |
| **DeepSeek**         | • deepseek-ai/DeepSeek-R1-Distill-Llama-8B<br /> • deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B<br /> • deepseek-ai/DeepSeek-R1-Distill-Qwen-14B<br /> • deepseek-ai/DeepSeek-R1-Distill-Qwen-7B                                                                                                                                                                                                                                                                          |
| **Eleutherai**       | • EleutherAI/gpt-j-6b<br /> • EleutherAI/gpt-neo-1.3B<br /> • EleutherAI/gpt-neo-125m<br /> • EleutherAI/gpt-neo-2.7B<br /> • EleutherAI/gpt-neox-20b                                                                                                                                                                                                                                                                                                                  |
| **Facebook**         | • facebook/opt-1.3b<br /> • facebook/opt-2.7b<br /> • facebook/opt-350m<br /> • facebook/opt-6.7b                                                                                                                                                                                                                                                                                                                                                                      |
| **Google**           | • google/flan-t5-base<br /> • google/flan-t5-large<br /> • google/flan-t5-small<br /> • google/flan-t5-xl<br /> • google/flan-t5-xxl<br /> • google/gemma-2-27b-it<br /> • google/gemma-2-9b-it<br /> • google/gemma-2b<br /> • google/gemma-2b-it<br /> • google/gemma-3-12b-it<br /> • google/gemma-7b<br /> • google/gemma-7b-it                                                                                                                                    |
| **Helsinki-nlp**     | • Helsinki-NLP/opus-mt-es-en                                                                                                                                                                                                                                                                                                                                                                                                                                           |
| **Huggingfaceh4**    | • HuggingFaceH4/zephyr-7b-alpha<br /> • HuggingFaceH4/zephyr-7b-beta                                                                                                                                                                                                                                                                                                                                                                                                   |
| **Meta-llama**       | • meta-llama/Llama-2-13b-hf<br /> • meta-llama/Llama-2-7b-hf<br /> • meta-llama/Llama-3.2-1B<br /> • meta-llama/Llama-3.2-1B-Instruct<br /> • meta-llama/Llama-3.2-3B<br /> • meta-llama/Llama-3.2-3B-Instruct<br /> • meta-llama/Llama-3.2-11B-Vision-Instruct<br /> • meta-llama/Llama-Guard-4-12B<br /> • meta-llama/Meta-Llama-3-8B<br /> • meta-llama/Meta-Llama-3-8B-Instruct<br /> • meta-llama/Meta-Llama-3.1-8B<br /> • meta-llama/Meta-Llama-3.1-8B-Instruct |
| **Microsoft**        | • microsoft/phi-1<br /> • microsoft/phi-1\_5<br /> • microsoft/phi-2<br /> • microsoft/Phi-3-medium-128k-instruct<br /> • microsoft/Phi-3-medium-4k-instruct<br /> • microsoft/Phi-3-mini-128k-instruct<br /> • microsoft/Phi-3-mini-4k-instruct                                                                                                                                                                                                                       |
| **Mistralai**        | • mistralai/Mistral-7B-Instruct-v0.1<br /> • mistralai/Mistral-7B-Instruct-v0.2<br /> • mistralai/Mistral-7B-Instruct-v0.3<br /> • mistralai/Mistral-7B-v0.1<br /> • mistralai/Mistral-Nemo-Instruct-2407<br /> • mistralai/Mixtral-8x7B-Instruct-v0.1<br /> • mistralai/Mixtral-8x7B-v0.1                                                                                                                                                                             |
| **OpenAI**           | • GPT2                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
| **OpenAI Community** | • openai-community/gpt2-large<br /> • openai-community/gpt2-medium<br /> • openai-community/gpt2-xl                                                                                                                                                                                                                                                                                                                                                                    |
| **Stable Diffusion** | • stabilityai/stable-diffusion-xl-base-1.0<br /> • stabilityai/stable-diffusion-2-1<br /> • stable-diffusion-v1-5/stable-diffusion-v1-5<br /> • (Available only in the text-to-image node, No Prompt Studio support.)                                                                                                                                                                                                                                                  |
| **T5**               | • t5-base<br /> • t5-large<br /> • t5-small                                                                                                                                                                                                                                                                                                                                                                                                                            |
| **Tiiuae**           | • tiiuae/falcon-40b<br /> • tiiuae/falcon-40b-instruct<br /> • tiiuae/falcon-7b<br /> • tiiuae/falcon-7b-instruct<br /> • tiiuae/falcon-rw-1b                                                                                                                                                                                                                                                                                                                          |
| **Xiaomi**           | • Mimo-7B--VL-RL                                                                                                                                                                                                                                                                                                                                                                                                                                                       |

### Structured Output

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

* Structured output support depends on the optimization technique used: No optimization or vLLM.
* Models optimized with CT2, fine-tuned models, Hugging Face imports, and locally imported models are not supported.

The following table lists the models that support structured JSON output:

| Model Name                            | 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, you can connect to external model providers such as OpenAI, Anthropic, Google, Cohere, and Amazon Bedrock. No infrastructure setup is required—authenticate and start deploying models.

The following table lists all external models supported in AI for Process:

| **Model Provider** | **Model Variant**                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
| ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Anthropic          | • claude-3-5-sonnet-20240620<br /> • claude-3-haiku-20240307<br /> • claude-3-opus-20240229<br /> • claude-3-sonnet-20240229<br /> • claude-2.1<br /> • claude-2.0<br /> • claude-3-7-sonnet-20250219<br /> • claude-3-5-sonnet-20241022<br /> • claude-3-5-haiku-20241022<br /> • claude-sonnet-4-20250514<br /> • claude-opus-4-20250514<br /> • claude-opus-4-1-20250805<br /> • Claude Sonnet Vision (Available only for the Image-to-text node, No Prompt Studio support.)                                                                                                                                                                                                                                                                                                                               |
| Azure Open AI      | • GPT-4<br /> • GPT-3.5-Turbo<br /> • GPT-4o-Mini<br /> • GPT-4o<br /> • GPT-4.1<br /> • GPT-4.1-mini<br /> • GPT-4.1-nano<br /> • GPT-4.5-preview<br /> • O1-Mini<br /> • O1<br /> • O3-Mini                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
| Cohere             | • command-light-nightly<br /> • command-light<br /> • command<br /> • command-nightly                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
| Google             | • gemini-1.5-flash-latest<br /> • gemini-1.5-pro<br /> • gemini-1.0-pro<br /> • gemini-2.5-Pro<br /> • gemini-2.0-flash<br /> • gemini-2.0-flash-lite<br /> • gemini-2.5-flash-preview-05-20<br /> • gemini-2.5-flash                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
| Open AI            | • gpt-4o<br /> • gpt-4o-mini<br /> • gpt-3.5-turbo<br /> • gpt-3.5-turbo-1106<br /> • gpt-4-0613<br /> • o1-preview<br /> • o1-mini<br /> • o3-mini<br /> • gpt-4-0125-preview<br /> • gpt-4-turbo-preview<br /> • gpt-4-1106-preview<br /> • gpt-5-2025-08-07<br /> • gpt-5-nano-2025-08-07<br /> • gpt-5-mini-2025-08-07<br /> • gpt-5-chat-latest<br /> • gpt-4<br /> • whisper (Available only for the Audio-to-text node, No Prompt Studio support.)<br /> • whisper-1<br /> • gpt-4o-realtime-preview<br /> • gpt-4o-mini-realtime-preview<br /> • gpt-4.1-2025-04-14<br /> • gpt-4.1-mini-2025-04-14<br /> • gpt-4.1-nano-2025-04-14<br /> • gpt-4.5-preview-2025-02-27<br /> • dall-e-3<br /> • dall-e-2<br /> • text-embedding-3-small<br /> • text-embedding-3-large<br /> • text-embedding-ada-002 |