gpt-oss
OpenAI's open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.

mixtral
A mixture-of-experts model offering superior performance across various tasks, by Mistral team.

deepseek-r1
Deploy and run your own DeepSeek R1 model for advanced language processing and generation capabilities.

deepseek-v3
Latest version of DeepSeek's general-purpose language model.

mistral
High-performance language model with strong reasoning capabilities.

llama2
Meta's state-of-the-art large language model optimized for dialogue use cases.

dolphin-mixtral
A fine-tuned version of Mixtral offering enhanced instruction following capabilities.

llama3.2-vision
Multimodal version of LLaMA 3.2 with vision capabilities.

qwen2.5-coder
Code-specialized version of Qwen 2.5 optimized for programming tasks.

qwq
General purpose language model with strong performance.

nemotron
NVIDIA's high-performance language model for general tasks.

smollm2
Second generation of the efficient small language model.

starcoder2
Advanced code generation model trained on a diverse set of programming languages.

deepseek-coder-v2
Advanced code generation model with strong performance on programming tasks.

qwen2.5
Latest version of the Qwen model series with enhanced performance.

phi3.5
Latest version of Microsoft's Phi model series with improved capabilities.

codestral
Code-specialized language model optimized for programming tasks.

granite-code
Specialized code generation model with multiple size options.

mistral-nemo
NVIDIA-optimized version of Mistral for enhanced performance.

internlm2
Advanced language model with strong multilingual capabilities.

smollm
Efficient small language model for resource-constrained environments.

phi3
Microsoft's efficient language model known for strong reasoning capabilities.

codellama
Meta's code-specialized language model optimized for programming tasks.

codegemma
Code-specialized version of Google's Gemma model for programming tasks.

gemma2
Second generation of Google's Gemma model with improved capabilities.

codegeex4
Advanced code generation model with multilingual programming capabilities.

codeqwen
Code-specialized version of Qwen optimized for programming tasks.
yi
Versatile language model with strong multilingual capabilities.

aya
Versatile language model with strong general capabilities.

qwen
A versatile language model with multiple size options for different use cases.

gemma
Google's efficient and powerful language model for various tasks.

wizardlm2
Advanced language model focused on instruction following and reasoning.

zephyr
Fine-tuned language model optimized for chat and instruction following.

llava
Multimodal model capable of understanding and reasoning about images and text.

openchat
Open-source chat model optimized for dialogue interactions.

tinyllama
Compact and efficient language model suitable for resource-constrained environments.

nous-hermes2
Second generation of the Nous Hermes language model.

starcoder
Original StarCoder model for code generation and understanding.

vicuna
Fine-tuned language model known for high-quality chat interactions.

wizard-vicuna-uncensored
Uncensored version of Wizard-Vicuna for open-ended interactions.

mistral-openorca
Fine-tuned version of Mistral optimized with the OpenOrca dataset.

llama2-chinese
Chinese-optimized version of LLaMA 2 for enhanced Chinese language capabilities.