Configuration
Set your TogetherAI API key in your.env file:
config/llm-magic.php:
Available Models
TogetherAI offers several open-source models:Meta Llama 3.2 Vision Models
- meta-llama/Llama-3.2-3B-Vision-Instruct-Turbo - Compact vision model (3B parameters)
- meta-llama/llama-3.2-11b-vision-instruct-turbo - Medium vision model (11B parameters)
- meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo - Large vision model (90B parameters)
Meta Llama 3.1 Models
- meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo - Fast instruction-following model
Qwen Models
- Qwen/Qwen2.5-7B-Instruct-Turbo - Alibaba’s Qwen model optimized for instruction following
Mistral Models
- mistralai/Mixtral-8x7B-Instruct-v0.1 - Mixtral mixture-of-experts model
Usage
Using String Identifier
Using Constructor
Using Constants
Vision Models
TogetherAI’s Llama 3.2 models support vision inputs:Model Constants
All available model constants from theTogetherAI class:
TogetherAI::META_LLAMA_3_2_3B_VISION_INSTRUCT_TURBOTogetherAI::META_LLAMA_3_2_11B_VISION_INSTRUCT_TURBOTogetherAI::META_LLAMA_3_2_90B_VISION_INSTRUCT_TURBOTogetherAI::META_LLAMA_3_1_8B_INSTRUCT_TURBOTogetherAI::OWEN_QWEN2_5_7B_INSTRUCT_TURBO
Advanced Options
Configure model behavior usingElElEmOptions:
Organization
- Provider: TogetherAI
- Website: together.ai
- API Documentation: docs.together.ai
See Also
- Chat API
- Model Selection
- OpenRouter Provider - Alternative unified API access