Large Language Models (LLMs)

Karini AI supports integrations with the following Large Language Model providers and custom models. Using these models, users can create model endpoints in the Karini AI model hub.

1. Amazon Bedrock

   In Amazon Bedrock, the "Model Serving" configuration provides two options for how your models are deployed and managed: On Demand and Provisioned Throughput.

   1. On Demand

      With the On Demand option, Amazon Bedrock automatically adjusts the computational resources to match the volume of requests your model receives. This means the system scales up or down in real-time based on demand, offering flexibility without the need for manual resource management. This option is suitable for workloads with varying traffic, ensuring you only pay for the resources used during active requests.

      The table below lists all available models.

   2. Provisioned Throughput

      The Provisioned Throughput option allows you to specify a fixed amount of computational capacity for your model, ensuring consistent performance and response times. This is ideal for use cases where you require a stable level of throughput, regardless of fluctuating demand. Resources are pre-allocated, which guarantees predictable performance but comes with a fixed cost, regardless of actual usage.

      When Provisioned Throughput is selected, the following model providers are available:

      • Amazon

      • AI21 Labs

      • Anthropic

      • Cohere

      For more details on model providers, please refer to the relevant documentation.

   Model ARN: Enter the ARN (Amazon Resource Name) of the selected model in this field. The ARN serves as a unique identifier for the model within the AWS ecosystem, ensuring proper configuration and secure linkage to your account.

2. OpenAI

3. Azure OpenAI

4. Databricks

5. Anyscale

6. Amazon SageMaker

Add New Model Endpoint

To add a new model endpoint to the model hub, do the following:

1. On the Model Endpoints menu, select Large language model endpoints(LLM) tab and click Add New.

2. Select a model provider and associated model id in the list.

3. User has option to override default configurations such as temperature, max tokens and pricing.

4. By default, the organization level credentials are used to access the model. User can User can optionally overwrite credentials with a new set of model credentials.

5. User can test the model endpoint request and response by using the Test endpoint button.

Review Model Endpoints

User can review the created model endpoints under Large language model endpoints(LLM) tab. It includes following information:

1. Model provider and model id

2. Max tokens, Min tokens and Temperature: The default values are displayed based on model specifications from the model provider. User has the ability to override them.

3. Model Price: The default price displays public pricing of the model inference per 1000 input and output tokens. This price is used in Karini AI Dashboards to calculate cost. User has the ability to override this price if needed - such as in case of special pricing agreement with the model provider.
4. Link to view the the recipes and prompts in which the model endpoint is used.

5. Link to view the model information including the cost and usage dashboard for the model endpoint.

Available LLM Configurations

The following table describes LLMs that are available for integration with Karini AI model hub. It also includes links to model provider reference documentation offering detailed information on model specifications, usage instructions, and API endpoints for effective integration and utilization.

Provider	Models	Config Parameters	Reference
Amazon Bedrock	Anthropic Claude 3.7 Sonnet vl Anthropic Claude 3.5 Sonnet v2 Anthropic Claude 3.5 Haiku 20241022 vl DeepSeek RI vl Amazon Nova Pro vl .Amazon Nova Lite vl Amazon Nova Micro vl Anthropic Claude 3.5 Sonnet 20240620 vl Anthropic Claude 3 Opus 20240229 vl Anthropic Claude 3 Sonnet 20240229 vl Anthropic Claude 3 Haiku 20240307 vl Anthropic Claude v2.1 Anthropic Claude v2 Anthropic Claude Instant vl Llama 3.3 70B Instruct Llama 3.2 1B Instruct Llama 3.2 3B Instruct Llama 3.2 11B Vision Instruct Llama 3.2 90B Vision Instruct Meta Llama 3.1 8B Instruct Meta Llama 3.1 70B Instruct Meta Llama 3 8B Instruct Meta Llama 3 70B Instruct Mistral 7B Instruct Mistral Mixtral 8x7B Instruct Mistral Large (24.02) Mistral Small (24.02) Cohere Command R Plus Cohere Command R Amazon Titan Text Premier Amazon Titan Text Express Amazon Titan Text Lite A121 Jamba 1.5 Mini A121 Jamba 1.5 Large A121 Jamba Instruct	Temperature Max Tokens	https://docs.aws.amazon.com/bedrock/latest/userguide/titan-text-models.html
Azure OpenAI	GPT 4O 2024-11-20 GPT 4O Mini O3 Mini O1 GPT 4O 2024-08-06 GPT 4O GPT 3.5 Turbo (Legacy) GPT-4 (Legacy)	Temperature Max Tokens Azure OpenAI API Base Azure OpenAI Deployment Name	https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/create-resource?pivots=web-portal
OpenAI	GPT 4O 2024-11-20 GPT 4O Mini O3 Mini O1 GPT 4O 2024-08-06 GPT 4O Whisper-I TTS-I TTS-1-hd GPT-4-Turbo GPT-3.5-Turbo (Legacy)	Temperature Max Tokens	https://platform.openai.com/docs/models
Google Gemini	Gemini 2.O Flash Gemini 2.O Flash-Lite Preview Gemini 1.5 Pro Gemini 1.5 Flash	Temperature Max Token	https://ai.google.dev/gemini-api/docs/models
Vertex Gemini	Gemini 2.O Flash Gemini 2.O Flash-Lite Preview Gemini 2.O Flash Thinking Gemini 1.5 Pro Gemini 1.5 Flash	Temperature Max Token	https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models
Fireworks	Llama 4 Maverick Instruct (Basic) Llama 4 Scout Instruct (Basic) DeepSeek RI Deepseek V3-0324 Llama V3P1 405B Instruct Llama V3P3 70B Instruct	Temperature Max Token	https://fireworks.ai/models
Anyscale	Google Gemma 7B Meta Llama 3 8B Meta Lama 3 70B Mistral 7B Instruct Mixtral 8x7B Instruct Mixtral 8x22B Instruct	Temperature Max Tokens	https://docs.anyscale.com/endpoints/model-serving/get-started
Databricks	Foundation Models Databricks DBRX Instruct Meta Lama 3 70B Instruct Mistral 8x7B Instruct Llama 2 70B Chat (Legacy) Databricks External Models Databricks Custom Models	Temperature Max Tokens Endpoint URL: Databricks model Endpoint URL	https://docs.databricks.com/en/generative-ai/external-models/index.html
Amazon SageMaker		Temperature Max Tokens Model Endpoint Name: SageMaker model endpoint name	https://docs.aws.amazon.com/sagemaker/latest/dg/deploy-model.html
Cohere	Rerank-english-v3.0 Rerank-multilingual-v3.0 Rerank-english-v2.0 Rerank-multilingual-v2.0		https://docs.cohere.com/v2/docs/reranking-with-cohere