Here’s a list of the available models:

Learn about the available models in Prem.

Available Models

Prem

Fine-tune, Evaluate, Observe and Deploy Your Custom AI Models.

Welcome To Prem

Let's get you started with Prem in minutes. In this guide, we'll show you how to use the **Chat Completions** funcationality.

Quickstart Guide

Learn how to create and use datasets to fine-tune your models.

Datasets Overview

Learn how to create, manage, and use datasets in Prem.

Get Started With Datasets

Learn how to enrich a dataset with synthetic data.

Enrich a Dataset

Learn how to autosplit a dataset into training, and validation sets.

Autosplit a Dataset

Learn how to create a snapshot of your dataset.

Create a Snapshot 📸

Use fine-tuning to create a custom model for your use case.

Fine-Tuning Overview

Learn how to fine-tune a model with Prem.

Get Started With Finetuning

Learn how to create experiments with your fine-tuned model.

Experiments

Learn how to run evaluations on your fine-tuned models.

Evaluations Overview

Get Started With Evaluations

Using The Playground

Check Your Stats

Find answers to common questions about Prem.

Frequently Asked Questions

Learn how to interact with Prem's API endpoints.

Getting Started With The Prem API

Use this endpoint to generate a chat completion.

Chat Completions

Use this endpoint to get a list of models available to you. 

The models available will depend on your subscription tier.

Get Models

Use this endpoint to get a list of models available to you including models you've fine-tuned.

Get Internal Models

Welcome to Prem

Let's create a Generative AI application in minutes.

Set up Prem SDK

Monitoring and Tracing

Autonomous Fine-Tuning

Structured Output

Function Calling

The [chat completion](/api-reference/chat-completions/post-v1chatcompletions) endpoint provides a way to generate chat completions based on provided input messages. This endpoint supports streaming via Server-Sent Events (SSE), allowing for partial message deltas to be sent back to the client.

Streaming Chat

Prompt Templates

This example explains how to access different LLMs and Embedding Models in Llamaindex through PremAI SDK.

LlamaIndex

This example goes over how to use LangChain to interact with different chat models using langchain `ChatPremAI`

LangChain

This example explains how to use DsPY by Stanford NLP to interact with different chat models.

DSPy

Qdrant is a vector similarity search engine. It provides a production-ready service with a convenient API to store, search, and manage points - vectors with an additional payload. Qdrant is tailored to extended filtering support. It makes it useful for all sorts of neural network or semantic-based matching, faceted search, and other applications.

Qdrant

PREM Cookbook Repository

Chat with PDF

URL Content Summarizer

Generate SQL from Text

Chat with SQL Tables

Paper search and QnA on ArXiv papers

Introduction

Learn how to use and customize premsql datasets for Text-to-SQL tasks, including working with available datasets, creating your own, and extending functionalities.

Datasets

Models that generate SQL queries from user input and a specified database source.

Generators

Connects to databases and executes generated SQL queries to fetch results.

Executors

Evaluates different Text to SQL models and pipelines with standard benchmarks and metrics.

Evaluators

Helps to make error handling prompts and datasets for error free inference and fine-tuning datasets for enforcing self correction property.

Error Handling

Helps to fine-tune Open Source models using different readily available datasets or custom datasets for Text to SQL tasks.

Tuner

End-to-end workflows customizable Text to SQL Agentic workflows for querying, analysing and plotting charts in databases all in natural language.

Agents

Agent Server where you can deploy PremSQL agents in the most customized forms.

Name	Description
claude-3.5-haiku	Fast, efficient Anthropic model for everyday tasks. Good at concise responses and basic reasoning.
claude-3.5-sonnet	Balanced Anthropic model with strong reasoning and creative capabilities.
claude-3.7-sonnet	Advanced Anthropic model with superior reasoning and instruction-following abilities.
deepseek-r1	Code-specialized model with strong programming and technical reasoning capabilities.
gemma3-1b	Compact Google model for efficient, lightweight applications.
gemma3-4b	Balanced Google model offering good performance for general tasks at moderate size.
gpt-4o	OpenAI’s multimodal model with strong reasoning and creative capabilities.
gpt-4o-mini	Smaller, faster version of GPT-4o for everyday tasks and applications.
llama3.1-8b	Mid-sized Meta model balancing performance and resource efficiency.
llama3.2-1b	Compact Meta model for lightweight applications with minimal resource needs.
llama3.2-3b	Balanced Meta model for general-purpose tasks with reasonable resource requirements.
llama3.2-3b Exp2	Experimental version of llama3.2-3b with optimized performance.
llama3.3-70b-instruct	Large instruction-tuned Meta model with advanced reasoning capabilities.
nova-lite	Lighter version of Anthropic’s Nova model for everyday tasks.
nova-micro	Most compact Nova model optimized for speed and efficiency.
nova-pro	Premium Anthropic Nova model with advanced capabilities for complex tasks.
qwen2.5-0.5b	Ultra-compact Alibaba model for extremely lightweight applications.
qwen2.5-1.5b	Compact Alibaba model balancing efficiency and basic capabilities.
qwen2.5-3b	Mid-sized Alibaba model with good performance for everyday tasks.
qwen2.5-3b Exp1	Experimental version of qwen2.5-3b with performance enhancements.
qwen2.5-7b	Larger Alibaba model with enhanced reasoning and generation capabilities.
qwen2.5-7b Exp4	Experimental version of qwen2.5-7b with advanced optimizations.
smollm-1.7b	Efficient small model optimized for resource-constrained environments.
smollm-135m	Tiny model for basic tasks with minimal computational requirements.
smollm-360m	Very small model balancing capability and extreme efficiency.

Get started

Datasets 🗃️

Fine-Tuning 🛠️

Evaluations 📈

Playground 🛝

Stats 📊

Resources 🧰

Available Models

Here’s a list of the available models:

Get started

Datasets 🗃️

Fine-Tuning 🛠️

Evaluations 📈

Playground 🛝

Stats 📊

Resources 🧰

​Here’s a list of the available models:

Here’s a list of the available models: