Supercharge generative AI
for any scale and environment
Friendli Container
Serve your custom generative AI models within your own private environment.
Compare plans and features
Features | Trial | Enterprise | |
---|---|---|---|
API | OpenAI compatible APIs | ||
Long context handling | |||
Function calling & JSON mode | |||
gRPC APIs | |||
Serving | Serve Hugging Face models | ||
Serve quantized models | |||
Serve MoE models | |||
Inference optimization | |||
Observability | Metrics | ||
Environment | Use in local or cloud environment | ||
Use in AWS Sagemaker | |||
Use in air-gapped environment | |||
Use in production environment | |||
Support | Customer support | Business hours | Dedicated support |
API
Trial
Enterprise
OpenAI compatible APIs
Long context handling
Function calling & JSON mode
gRPC APIs
Serving
Trial
Enterprise
Serve Hugging Face models
Serve quantized models
Serve MoE models
Inference optimization
Observability
Trial
Enterprise
Metrics
Environment
Trial
Enterprise
Use in local or cloud environment
Use in AWS Sagemaker
Use in air-gapped environment
Use in production environment
Support
Trial
Enterprise
Customer support
Business hours
Dedicated support