---
canonical: "https://www.softatlas.io/together-ai/products/serverless-inference"
name: "Serverless Inference"
provider: "Together AI"
category: "Artificial Intelligence / Foundation Models & LLM APIs / LLM Inference & Gateways"
review_count: 0
ai_powered: true
website: "https://together.ai/serverless-inference"
updated: "2026-10-05"
---

# Serverless Inference

By [Together AI](/together-ai.md)

High-performance inference as APIs, allowing users to run open-source models on demand without managing infrastructure.

## Features
- Run open-source models on demand via APIs
- Perform batch inference for large workloads
- Deploy custom models on dedicated hardware
- Utilize token-based capacity with SLAs for throughput
- Access accelerated compute with GPU clusters
- Fine-tune models with custom training data
- Store model weights and data securely
- Measure model quality through evaluations

## Built for
DEVELOPERS, OPERATIONS

Source: https://www.softatlas.io/together-ai/products/serverless-inference