SENDFU-operated inference infrastructure.
SENDFU operates the public API gateway, inference runtime, model deployments, release control, and capacity allocation as one integrated service.
One integrated SENDFU service.
SENDFU operates the complete service from authenticated API access through deployed inference.
SENDFU-operated runtime
SENDFU operates the inference runtime, deployed weights, model versions, release control, and capacity allocation for published model services.
Unified SENDFU API
SENDFU operates authentication, the public model catalog, request validation, usage controls, and OpenAI-compatible API delivery.
Model developer retained
Operating the service does not transfer authorship or ownership of third-party base models to SENDFU. The original developer remains identified by the model ID.
SENDFU-operated delivery path.
SENDFU operates the complete path from authenticated requests to deployed model inference.
↓
SENDFU public API, authentication, and usage controls
↓
SENDFU-operated inference infrastructure and deployed model runtime
Serving controls
Authentication, access controls, model selection, concurrency management, rate controls, streaming delivery, metering, and support are managed as available for each program.
Health and status
Public application health is on the Status page. Model-pool and capacity monitoring are reported only when those checks are actually connected.
Actual service method
Service documentation distinguishes SENDFU-developed services from services based on third-party base models. SENDFU does not claim ownership of third-party base-model weights.