---
title: "Serverless GPU Inference API for LLMs | E2E Networks"
description: "Deploy LLMs as autoscaling API endpoints on Indian GPUs. One-click catalog (DeepSeek R1, Llama 4), vLLM/SGLang/Triton, scale-to-zero from ₹49/hr."
url: "https://www.e2enetworks.com/inference-endpoints"
canonical: "https://www.e2enetworks.com/inference-endpoints"
provider: "E2E Networks Limited"
type: "Service"
keywords: ["llm inference api india", "deploy model endpoint", "serverless gpu inference", "vllm hosting india", "deploy huggingface model api", "gpu inference endpoints", "model serving platform india"]
priceCurrency: "INR"
taxNote: "Prices exclude GST"
region: "India (Delhi NCR, Chennai)"
generated: "2026-09-11"
---

# Serverless GPU Inference API for LLMs | E2E Networks

> Deploy LLMs as autoscaling API endpoints on Indian GPUs. One-click catalog (DeepSeek R1, Llama 4), vLLM/SGLang/Triton, scale-to-zero from ₹49/hr.

Canonical page: https://www.e2enetworks.com/inference-endpoints

Ship models as APIs. Scale to zero when quiet. Pick a model from the catalog or your Hugging Face account, choose a GPU, and get an authenticated OpenAI-style endpoint served from Indian data centers — with autoscaling you actually control.

## At a glance

Note: Indicative — see the live rate card for current pricing.

- **6** — Runtimes: vLLM · SGLang · Triton · PyTorch · Dynamo · Custom
- **0** — Idle replicas with scale-to-zero
- **₹49/hr*** — GPU endpoints start
- **99.9%** — Uptime SLA

## Models available in the catalog

- **One-click catalog models:** DeepSeek R1, DeepSeek V3, Llama 4 Maverick, Llama 4 Scout, GPT-OSS 120B, Hermes 3 405B, Dolphin Mixtral 8x22B, Sarvam-2B

## Platform capabilities

- **One-click catalog deploys** — Serve state-of-the-art open models from the TIR catalog, or hit the shared GenAI API (GPT-OSS 120B, Llama 3.1 8B, Qwen3 32B, Sarvam and more) without deploying anything yourself.
- **Hugging Face & Model Repository** — Point an endpoint at any HF model or a TIR Model Repository on E2E Object Storage — files download to the container automatically at start. Validate model and config before deploy.
- **Custom containers** — Bring your own Docker image from a public or private registry, optionally attached to a TIR Model for automatic weight downloads. Full control over the serving stack.
- **Metric-driven autoscaling** — Scale on concurrent requests, requests/sec, or runtime metrics like vllm:num_requests_running, sglang:gen_throughput and Triton queue depth. Tune idle timeout and cooldown to balance latency vs cost.
- **Async & WebSocket APIs** — Queue long-running jobs with async invocation — get a request_id, results land as JSON in your EOS dataset, workers bill only while the queue is non-empty. Streaming? Connect over wss://.
- **Private, observable serving** — Security Groups and VPC attach keep endpoints off the public internet. Centralized inference and per-replica logs, hardware + service metrics, access logs and email alerts come standard.

## How it works

1. **Pick a source** — Catalog model, Hugging Face repo, TIR Model Repository, or your own container image.
2. **Choose runtime & GPU** — vLLM, SGLang, Triton or PyTorch; select GPU plan and replicas. Tune engine args — dtype, quantization, context length — if you need to.
3. **Set scaling** — Active Workers, Max Workers, metric type and target value. Different min/max = autoscaling on. Zero minimum = scale-to-zero.
4. **Call it** — Create an API token, copy the sample cURL/Python from the console, and test in the built-in playground before wiring up your app.

## OpenAI-compatible out of the box

Every endpoint gets a root URL; append standard routes like /v1/chat/completions.

```bash
# illustrative — copy the exact URL from your endpoint's API Request tab
curl https://infer.e2enetworks.net/project/p-XXXX/endpoint/is-XXXX/v1/chat/completions \
  -H "Authorization: Bearer $TIR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-r1",
    "messages": [{"role": "user", "content": "Summarise this contract clause:"}],
    "max_tokens": 400
  }'
```

Tokens live under API Tokens in your TIR project. The playground supports chat models with temperature, top-p, top-k and repetition-penalty controls.

## Autoscaling metrics

What an endpoint can scale on, and when to pick each metric.

| Metric | Scales on | Best for | Example target |
| --- | --- | --- | --- |
| Concurrent Request Count | In-flight requests per worker | Latency-sensitive LLM chat, where each request holds the GPU for the full generation | 10 concurrent requests |
| Request Rate per Second | Requests/sec arriving per worker | High-throughput, short-lived calls — embeddings, classification | 50 req/s |
| Custom (vLLM) | vllm:num_requests_running, vllm:gpu_cache_usage_perc… | Preventing KV-cache OOM, queue-depth-aware scaling | 32 running requests |
| Custom (SGLang) | sglang:num_queue_reqs, sglang:gen_throughput… | Token-throughput-driven serving | Queue > 8 |
| Triton | nv_inference_pending_request_count, nv_gpu_utilization… | Multi-model servers | GPU util 80% |
| TorchServe | GPUUtilization, ts_queue_latency_microseconds… | Classic PyTorch serving | Queue latency |

## Fine-tune first, then serve it here

Models trained or fine-tuned on TIR deploy to endpoints in a few clicks — same project, same storage.

- [Training & Fine-tuning](https://www.e2enetworks.com/training-fine-tuning)
- [AI Dev Nodes](https://www.e2enetworks.com/ai-dev-nodes)
- [Explore TIR - AI Platform](https://www.e2enetworks.com/tir)
- [GPU pricing](https://www.e2enetworks.com/pricing#gpu-pricing)

## Frequently asked questions

### Is this really serverless — do I pay for idle GPUs?

Set Active Workers to zero and the endpoint scales to zero when idle; you pay only while workers run (including any configured idle timeout). Async workers bill only while the request queue is non-empty.

### What model types can I serve?

LLMs, embeddings, speech (ASR/TTS) and diffusion models across vLLM, SGLang, Triton and PyTorch runtimes — or anything that runs in your own container.

### How do I keep inference traffic off the public internet?

Attach the endpoint to your E2E VPC to get a private IP reachable only from your VPC nodes, then lock ports down with Security Groups. Note: VPC Connect requires a VPC created with E2E-provided CIDR blocks.

### Can I debug production traffic?

Yes — centralized inference logs, per-replica logs, deployment/lifecycle events, hardware and service metrics, per-hour access logs, and threshold-based email alerts are built into every endpoint.

### Do committed plans work for endpoints?

Yes — reserve capacity at committed rates for steady traffic (committed endpoints can't be stopped during the commitment period). See the rate card for current hourly vs committed pricing.

## Get started

OpenAI-style routes, Indian GPUs, INR billing. Pricing: https://www.e2enetworks.com/pricing · Talk to sales: https://www.e2enetworks.com/contact-sales

- [Start Free](https://myaccount.e2enetworks.com/accounts/signup)
- [Talk to an Engineer](https://www.e2enetworks.com/contact-sales)

---

This Markdown is generated from the same data that renders https://www.e2enetworks.com/inference-endpoints. Provider: E2E Networks Limited (NSE: E2E), India. Site index for AI agents: https://www.e2enetworks.com/llms.txt