Together AI
Cloud platform for running and fine-tuning open-source AI models with optimized inference
FreemiumPay-per-token: Llama 3 70B from $0.88/M tokens, fine-tuning from $3/hr, free $5 credits for new users API web api
Visit Together AIAbout Together AI
Together AI provides a cloud platform for running, fine-tuning, and building with open-source AI models. It offers optimized inference for popular models like Llama, Mistral, and Mixtral, with an OpenAI-compatible API. The platform supports custom fine-tuning, embedding generation, and offers competitive pricing for inference workloads.
Key Features
- Optimized inference engine
- Custom fine-tuning
- OpenAI-compatible API
- Embedding generation
- Function calling
- JSON mode
- Streaming support
Pros
- Fast inference speeds
- Competitive pricing
- Good model selection
- Easy fine-tuning
Cons
- Limited to open-source models
- Fewer features than major clouds
- Documentation could be better
Tags
inferencefine-tuningopen-source-modelsapigpu-cloud
Alternatives to Together AI
01Fireworks AI
Fast and affordable inference platform for open-source and custom AI models with sub-second latencyGroq
Ultra-fast LLM inference powered by custom LPU hardware delivering 10x faster token generationMore Developer Infrastructure ToolsView All
01Hugging Face
The leading open-source platform for sharing, discovering, and deploying ML models, datasets, and SpacesLangChain
Open-source framework for building LLM-powered applications with chains, agents, and retrieval-augmented generationPinecone
Managed vector database for building high-performance AI applications with similarity search at scaleReplicate
Run and deploy open-source ML models in the cloud with a simple API, no infrastructure neededWeights & Biases (W&B)
ML experiment tracking, model versioning, and dataset management platform for AI teamsWeaviate
Open-source vector database with built-in vectorization modules and hybrid search capabilities