Explore Available Models
Browse our curated collection of production-ready AI models. Click on any card to view detailed specs, use cases, and pricing.
LLaMA 3.2 90B Vision
Meta
Open Source
Meta's cutting-edge multimodal model combining vision and language understanding with exceptional reasoning capabilities.
multimodalvisionchatreasoning
Size: 90BVRAM: 180GBSpeed: 12 tokens/s
LLaMA 3.1 405B
Meta
Open Source
Meta's largest and most capable open-source model with exceptional reasoning capabilities and extended context length.
chatreasoninglong-contextresearch
Size: 405BVRAM: 810GBSpeed: 8 tokens/s
LLaMA 3.1 70B
Meta
Open Source
High-performance model with superior reasoning and 128K context window, perfect for enterprise deployments.
chatinstructionlong-contextenterprise
Size: 70BVRAM: 140GBSpeed: 25 tokens/s
LLaMA 3.1 8B
Meta
Open Source
Meta's latest language model with improved reasoning capabilities and multilingual support. Excellent for general-purpose applications.
chatinstructioncodingreasoning
Size: 8BVRAM: 16GBSpeed: 45 tokens/s
DeepSeek-V2.5 Coder
DeepSeek
Open Source
DeepSeek's most advanced coding model with mixture of experts architecture, trained on massive code datasets.
codeprogrammingsoftware-engineeringdebugging
Size: 236BVRAM: 472GBSpeed: 15 tokens/s
Qwen2.5 72B Instruct
Alibaba
Open Source
Alibaba's flagship model with exceptional multilingual capabilities and advanced reasoning across 29+ languages.
chatreasoningmultilinguallong-context
Size: 72BVRAM: 144GBSpeed: 22 tokens/s
Mixtral 8x22B Instruct
Mistral AI
Open Source
Mistral's largest Mixture of Experts model with exceptional performance across diverse tasks and function calling.
chatcodereasoningfunction-calling
Size: 8x22BVRAM: 176GBSpeed: 18 tokens/s
Phi-3.5 Mini Instruct
Microsoft
Open Source
Microsoft's latest compact model with impressive reasoning capabilities, perfect for edge deployment and mobile applications.
chatedgemobilereasoning
Size: 3.8BVRAM: 8GBSpeed: 75 tokens/s
DeepSeek Coder V2
DeepSeek
Open Source
Advanced coding model with exceptional performance on programming tasks.
codingcode-completiondebugging
Size: 16B, 236BVRAM: 32GBSpeed: 35 tokens/s
LLaMA 3.1
llama
Open Source
Meta's open-source LLaMA 3.1 with improved reasoning and instruction following.
chatinstructionlong-context
Size: 8B, 70BVRAM: 8 GBSpeed: 8 tokens/s @ 8GB
Mistral 7B
mistral
Open Source
Mistral 7B: strong accuracy for instruction tasks and low-latency inference.
chatcode
Size: 7BVRAM: 8 GBSpeed: 9 tokens/s @ 8GB