Model Catalog

GPT-4 Turbo

OpenAI

Most capable GPT-4 model with 128K context window, optimized for chat and complex reasoning tasks. Best for production applications requiring high accuracy.

GPT-4o

OpenAI

Omni model with multimodal capabilities including text, vision, and audio understanding. Faster and more efficient than GPT-4 Turbo.

GPT-3.5 Turbo

OpenAI

Fast and cost-effective model for simple tasks. Great for chatbots, content generation, and basic reasoning.

Claude 3 Opus

Anthropic

Most powerful Claude model with exceptional performance on complex tasks, analysis, and creative writing. 200K context window.

Claude 3 Sonnet

Anthropic

Balanced model offering strong performance at a lower cost. Ideal for most enterprise workloads and customer-facing applications.

Claude 3 Haiku

Anthropic

Fastest and most compact Claude model. Perfect for high-volume, low-latency applications and real-time interactions.

Gemini 1.5 Pro

Google

Advanced multimodal model with 1M token context window. Exceptional for long-document analysis, video understanding, and complex reasoning.

Gemini 1.5 Flash

Google

Lightweight multimodal model optimized for speed and efficiency. Great for high-frequency tasks with multimodal inputs.

Llama 3 70B Instruct

Meta

Open-source model with strong performance on instruction following and reasoning. Cost-effective alternative to proprietary models.

Llama 3 8B Instruct

Meta

Compact open-source model perfect for edge deployment and high-throughput applications. Excellent price-performance ratio.

Mistral Large

Mistral

European flagship model with strong multilingual capabilities and reasoning. Excellent for enterprise applications requiring data sovereignty.

Mistral Medium

Mistral

Balanced model offering strong performance across various tasks. Good for general-purpose applications with multilingual support.

Mistral Small

Mistral

Cost-effective model for simple tasks and high-volume applications. Fast and efficient for basic reasoning and content generation.

DALL-E 3

OpenAI

Advanced image generation model with exceptional quality and prompt adherence. Supports 1024x1024, 1024x1792, and 1792x1024 resolutions.

Stable Diffusion XL

Stability AI

Open-source image generation model with high-quality outputs. Cost-effective alternative for image generation at scale.

Whisper Large V3

OpenAI

State-of-the-art speech recognition model supporting 99 languages. Exceptional accuracy for transcription and translation tasks.

GPT-4 Vision

OpenAI

GPT-4 with vision capabilities for image understanding and analysis. Perfect for visual question answering and image description.

Command R+

Cohere

Enterprise-grade model optimized for RAG and tool use. Excellent for building AI assistants with external knowledge integration.

Mixtral 8x7B Instruct

Mistral

Mixture-of-experts model with 47B parameters. Outperforms many larger models while being more efficient and cost-effective.

PaLM 2

Google

Legacy Google model with strong multilingual and reasoning capabilities. Being phased out in favor of Gemini models.