Skip to main content
Effective Date — May 7, 2026
As part of the IAM hierarchy simplification, a new format of the TIR APIs is now available. All endpoints that previously included /teams/:team_id segment will now follow a service-centric structure, with project_id now passed as a query parameter instead of a path segment. You can read more about this change
TIR · AI / ML PLATFORM API

Ship AI workloads from your code

TIR's REST API powers the full AI lifecycle — fine-tune and deploy models, run inference, orchestrate pipelines and manage GPU clusters without leaving your terminal.

Base URL /myaccount/api/v1/gpuAuth Bearer tokenFormat JSON
Download the full OpenAPI spec
bash — run inference
POST https://api.e2enetworks.com/myaccount/api/v1/gpu/
Authorization: Bearer <TIR_API_TOKEN>

{
  "model": "llama-3-8b-instruct",
  "prompt": "Summarise the E2E TIR platform.",
  "max_tokens": 256
}
200 OK  # streamed completion

// developer experience

Purpose-built for AI teams

GPU-native primitives with the ergonomics of a modern REST API.

Token authentication

Authenticate with your TIR API token and project context in the Authorization header.

End-to-end AI lifecycle

Fine-tune, deploy and serve models, then orchestrate pipelines — all through one API.

GPU-native

Spin up optimized GPU containers with PyTorch, TensorFlow and Triton pre-configured.