MODELS

Qwen 3 model with 14B parameters offering excellent performance-to-size efficiency

MoE Qwen 3 model with 30B total parameters, activating 3B for efficient inference

Large MoE Qwen 3 thinking model with 235B parameters and advanced reasoning capabilities

Qwen API model with 1M token context support for extensive document processing

AWS Nova lightweight model with 300K context for fast, cost-efficient text processing

AWS Nova advanced model with 300K context for complex reasoning and multimodal tasks

Advanced Haiku model matching Claude 3 Opus performance with maintained speed and cost-efficiency

Latest generation Sonnet with best-in-class performance for complex agents and coding tasks

Exceptional reasoning model for specialized complex tasks requiring advanced analytical capabilities

Hybrid reasoning model with extended thinking mode for complex problem-solving and quick responses

Updated Haiku model from October 2024 with enhanced accuracy and performance

DeepSeek MoE model with 671B parameters (37B active) and 128K context for general tasks

DeepSeek reasoning model from May 2024 with chain-of-thought capabilities for complex problems

Advanced DeepSeek reasoning model with RL training, comparable to OpenAI o1 in performance

Efficient MoE model with 671B parameters trained with FP8, achieving strong benchmark results

Advanced thinking model with adaptive reasoning, excellent price-performance, and multimodal capabilities

Optimized Gemini model for cost-efficiency, high throughput, and low latency applications

Most intelligent Gemini model with enhanced reasoning for complex coding, math, and scientific tasks

Open-source instruction-tuned Gemma model with 27B parameters for diverse language tasks

Specific Gemini 2.0 Flash version with stable performance and consistent behavior

Preview version of Gemini 2.5 Pro with advanced reasoning capabilities released in March 2025

Next-generation Llama 4 model with advanced capabilities and improved training efficiency

Llama 4 Scout variant with 17B parameters and mixture-of-experts architecture for efficiency

Llama 3.3 model with 70B parameters offering improved performance over 3.1 version

FP8-quantized 17B Llama 4 Maverick model optimized for deployment efficiency and speed

Latest Phi model with 14B parameters offering improved performance in reasoning and coding

Updated Mistral Large from November 2024 with improved performance and capabilities

Specialized Mistral model variant designed for specific enterprise use cases

Compact 24B parameter Mistral model optimized for cost-effective instruction following

Advanced Kimi model with improved reasoning depth and instruction following capabilities

NVIDIA-tuned 253B Llama 3.1 model optimized for enterprise applications and instruction following

NVIDIA optimized 49B Llama 3.3 model providing excellent performance-to-size ratio

NVIDIA tuned 70B Llama 3.1 model with enhanced instruction following and helpfulness

Smaller, faster, and more affordable version of GPT-4o, ideal for high-volume applications requiring good intelligence

Enhanced iteration of GPT-4 with improved reasoning, coding, and multimodal capabilities

Most advanced OpenAI reasoning model with multimodal capabilities and agentic tool use for complex analysis

Lightweight reasoning model balancing speed and intelligence for everyday complex tasks

Next-generation GPT model with enhanced reasoning, larger context window, and improved general capabilities

Efficient version of GPT-5 designed for high-throughput applications with cost optimization

Ultra-compact GPT-5 variant for edge deployment and resource-constrained environments

Open-source large language model with 120B parameters offering competitive performance

Compact GPT-4.1 variant optimized for efficiency while maintaining strong performance

January 2025 release of o3-mini with enhanced STEM capabilities and developer features

April 2025 o4-mini release with improved reasoning efficiency and balanced performance

Compact Grok model optimized for efficient deployment with maintained intelligence

Latest Grok model with advanced reasoning capabilities and extended thinking mode

Grok 2 version from December 2024 with incremental improvements and optimizations

Beta version of Grok 3 with extended reasoning for complex problem-solving tasks

Enhanced GLM model with improved agentic capabilities, reasoning, and coding performance

Lightweight GLM 4.5 variant optimized for faster inference and lower computational costs