Vendors · Profile
Together AI
Dedicated GPUServerless tokens plus single-tenant dedicated endpoints and GPU clusters
Visit Together AI ↗Deployment
| Deployment models | Serverless, Dedicated endpoint, GPU clusters |
| Regions | Not verified |
Compliance
| SOC 2 Type II together.ai ↗ verified 2026-07-07 |
| HIPAA BAA together.ai ↗ verified 2026-07-07 |
| Pricing model | Per 1M tokens serverless; per GPU-hour for dedicated endpoints and clusters |
| Public pricing | Yes |
| Data residency guarantee | No |
| Parent jurisdiction | US |
Analyst note
Dedicated endpoints are explicitly single-tenant GPU instances with public per-hour pricing. Terms of service make no geographic storage commitment, so residency guarantee is recorded as none.
Compare Together AI vs…
- Comparison Together AI vs Amazon Bedrock Provisioned Throughput
- Comparison Together AI vs Azure OpenAI Provisioned Throughput (PTU)
- Comparison Together AI vs Baseten
- Comparison Together AI vs Civo
- Comparison Together AI vs CoreWeave
- Comparison Together AI vs Databricks Model Serving
- Comparison Together AI vs Fireworks AI
- Comparison Together AI vs Hugging Face Inference Endpoints
- Comparison Together AI vs Modal
- Comparison Together AI vs Nebius
- Comparison Together AI vs NVIDIA NIM
- Comparison Together AI vs OVHcloud
- Comparison Together AI vs RunPod
- Comparison Together AI vs Scaleway
- Comparison Together AI vs Vertex AI Provisioned Throughput