Together AI
AI acceleration cloud: open-model hosting, fine-tuning, and high-throughput inference.
Executive Summary
AI acceleration cloud: open-model hosting, fine-tuning, and high-throughput inference.
Use Cases
- Hosting and serving open-source AI models at scale
- Fine-tuning large language models (LLMs) and other AI models
- Developing and deploying generative AI applications
- Running high-throughput, low-latency AI inference for production workloads
- Processing large batches of AI model requests asynchronously
Features
Visibility
- Account Management: Manage API keys, projects, and organizational settings.
- Batch Job Monitoring: Monitor the progress of asynchronous batch API requests and download results upon completion.
Intelligence
- Optimized Inference Performance: Achieve up to 2x faster inference speeds powered by cutting-edge research and workload-specific optimizations.
- Cost-Efficient Operations: Reduce operational costs by up to 60% through optimized infrastructure and workload management.
- Accelerated Pre-training: Benefit from faster pre-training capabilities for AI models.
Technical Specifications
- Architecture
- Full-stack AI platform providing serverless models, dedicated endpoints, and GPU clusters for inference, fine-tuning, and model shaping.
- Deployment
- SaaS
- Authentication
- API Key, OIDC
- API Available
- Yes
Infrastructure
- NVIDIA GPU Clusters
AI/ML Stack
- Open-source AI models
- Large Language Models (LLMs)
- Generative AI
Security & Compliance
Certifications: SOC 2 Type 2, ISO 27001:2022, GDPR, HIPAA
Encryption: End-to-end encryption for all data, both in transit and at rest.
Pricing
- Model
- Usage-based pricing for inference and fine-tuning, with options for monthly reserved dedicated capacity.
- Starting Price
- Contact sales
- Target Customer
- Mid-Market,Enterprise,Leading Model Providers
- Contract Type
- Monthly, Annual
- Free Trial
- Yes
About Together AI
Together AI is the AI Native Cloud, a full-stack platform purpose-built for AI engineers and researchers. It provides a suite of tooling for production AI, accelerating inference, model shaping, and pre-training, powered by cutting-edge systems research.