Interested in running DeepSeek-R1 in production?
Request access to Together Dedicated Endpoints—private and fast DeepSeek-R1 inference at scale.
- Fastest inference: Our DeepSeek-R1 API runs 10x faster than DeepSeek's API
- Flexible scaling: Deploy via Together Serverless or dedicated endpoints
- High throughput: Up to 334 tokens/sec on dedicated infrastructure
- Secure & reliable: Private, compliant, and built for production
We'll get back to you shortly!
DeepSeek-R1 on Together AI
Unmatched performance. Cost-effective scaling. Secure infrastructure.
Fastest inference engine
We run DeepSeek-R1 10x faster than DeepSeek's API, ensuring low-latency performance for production workloads.
Scalable infrastructure
Whether you're just starting out or scaling to production workloads, choose from Together Serverless APIs for flexible, pay-per-token usage or dedicated endpoints for predictable, high-volume operations.
Security-first approach
We host all models in our own data centers, with no data sharing back to DeepSeek. Developers retain full control over their data with opt-out privacy settings.
Seamlessly scale your R1 deployment
Together Serverless API
We run DeepSeek-R1 10x faster than DeepSeek's API, ensuring low-latency performance for production workloads.
- Instant scalability and generous rate limits
- Flexible, pay-per-token pricing with no long-term commitments
- Full opt-out privacy controls
Together Dedicated Endpoints
Whether you're just starting out or scaling to production workloads, choose from Together Serverless APIs for flexible, pay-per-token usage or dedicated endpoints for predictable, high-volume operations.
- Low latency (speeds up to 334 tokens/sec) from Together Inference stack
- High-performance NVIDIA HGX B200 GPUs, optimized for reasoning models
- Contract-based pricing for predictable, cost-effective scaling
