ChatLabs currently supports over 100 AI text models and 3 image-to-text models from top and well-known providers such as OpenAI, Google Gemini, Llama by Meta, Claude, and Perplexity.
All models on our platform are categorized into several tiers based on their performance and cost:
Free tier
Premium tier
Professional tier
Ultimate tier
Text AI models
Below is a list of the main and most popular models, grouped by provider. You can view the complete list of models in the Model Discovery section of ChatLabs.
LLMs available for free, Premium, Pro, and Ultimate plans.
See list
OpenAI
GPT-4 Turbo: An optimized version of GPT-4 for faster and more efficient responses.
GPT-4: A state-of-the-art language model known for its high-quality text generation.
GPT-3.5 Turbo: A slightly enhanced version of GPT-3.5, focusing on speed and efficiency.
GPT-4o: A variant of GPT-4 with specific optimizations for certain applications.
GPT-4o mini: A smaller version of GPT-4o designed for resource-constrained environments.
O1 Mini: A compact model aimed at quick tasks and low-latency applications.
O1 Preview: A preview version of O1 with experimental features for testing.
Google Gemini
Gemini 1.0 Pro: An advanced language model designed for high-performance tasks.
Gemini 1.0 Pro Vision: A variant of Gemini 1.0 Pro with enhanced visual processing capabilities.
Gemini 1.5 Pro: An upgraded version of Gemini with improved understanding and response generation.
Gemini 1.5 Flash: A lightweight model focused on quick responses and efficiency.
Claude
Claude 3 Haiku: A creative model optimized for generating poetic and artistic text.
Claude 3 Sonnet: A model specialized in crafting structured poetic forms, particularly sonnets.
Claude 3 Opus: A comprehensive model for extensive and detailed content creation.
Claude 3.5 Sonnet: An enhanced version of Claude 3 Sonnet with refined poetic capabilities.
Mistral
Mistral Tiny: A compact model suited for lightweight applications and quick tasks.
Mistral Small: A small-scale model offering a balance between performance and resource usage.
Mistral Medium: A mid-sized model designed for general-purpose language tasks.
Mistral Large: A larger model providing enhanced capabilities for complex language processing.
Mistral 7B Instruct: A model specifically trained for instruction-following tasks.
Meta AI
Meta LLama 3 8B: A versatile model from Meta optimized for a range of language tasks.
Meta LLama 3 70B: A powerful model designed for high-capacity language processing and understanding.
Llama 3.1 405b Instruct: An instruction-following model from the Llama series designed for detailed task execution.
Perplexity
Sonar Small Chat: A model tailored for casual conversation and chat applications.
Sonar Small Online: A version of Sonar optimized for online interactions.
Sonar Large Chat: A more robust model for engaging in detailed conversations.
Sonar Large Online: An enhanced version of Sonar for comprehensive online discussions.
Other
Mixtral 8x7b Instruct: A model designed for instruction-based tasks with a focus on clarity and adherence.
Mixtral 8x22B: A larger model optimized for extensive language generation tasks.
WizardLM 2 8x22B: A powerful language model designed for creative and complex text generation.
Command R Plus: An advanced model focused on command execution and task automation.
DBRX Instruct: A model specialized in following detailed instructions for various applications.
Mythomax 13B: A large language model designed for mythological and narrative text generation.
Image Generation Models
Supported text-to-image LLMs.
DALL-E 3: Created by , available for Premium, Pro, and Ultimate users.
Stable Diffusion 3: Created by , available for Pro and Ultimate users.
Flux.1: Developed by , available for Ultimate users.
Free AI models
ChatLabs' models available for users for free.
Full List
GPT-3.5 Turbo: A slightly enhanced version of GPT-3.5, focusing on speed and efficiency.
GPT-4o mini: A smaller version of GPT-4o designed for resource-constrained environments.
Claude 3 Haiku: A creative model optimized for generating poetic and artistic text.
Gemini 1.5 Flash: A lightweight model focused on quick responses and efficiency.
Mistral Tiny: A compact model suited for lightweight applications and quick tasks.
Mixtral 8x7b Instruct: A model designed for instruction-based tasks with a focus on clarity and adherence.
Mixtral 8x22B: A larger model optimized for extensive language generation tasks.
Meta LLama 3 8B: A versatile model from Meta optimized for a range of language tasks.
Meta LLama 3 70B: A powerful model designed for high-capacity language processing and understanding.
Mistral 7B Instruct: A model specifically trained for instruction-following tasks.
Sonar Small Chat: A model tailored for casual conversation and chat applications.
Sonar Small Online: A version of Sonar optimized for online interactions.
WizardLM 2 8x22B: A powerful language model designed for creative and complex text generation.
Command R Plus: An advanced model focused on command execution and task automation.
DBRX Instruct: A model specialized in following detailed instructions for various applications.
Mythomax 13B: A large language model designed for mythological and narrative text generation.
Supported API Keys
If you provide your own API keys, ChatLabs will use them instead. This option lifts the plan-based limitations but requires you to manage your own API usage and billing with the respective providers.
Supported APIs
OpenAI
Azure OpenAI
Anthropic
Google Gemini
Mistral
Groq
Perplexity
OpenRouter
Usually we add every new popular Al model within 1-2 days as it becomes publicly available.