Availability and pricing

Cloud	Version	Software price	Last build
AWS Marketplace EC2 AMI · all commercial regions	4.12.1	$0.05/hr Recommended instance: t3.large · 5-day free trial	2026-10-25	Listing ↗
Azure Marketplace VM image · plan payg-gen2 · Gen2	4.10.0	$0.028/vCPU/hr Recommended VM: Standard_D2s_v3	2026-09-20	Listing ↗

Software price only; cloud infrastructure is billed separately by the provider. Prices in USD.

Image facts

Base OS	Ubuntu 24.04 LTS
Hardening	CIS Level 1, Ubuntu 24.04 LTS (tailored)
License	MIT
Upstream	Ettore Di Giacinto
Machine-readable	product.json · catalog.json

What is LocalAI

LocalAI is an open-source, OpenAI-compatible inference server delivered as a single statically linked Go binary. It exposes the same REST surface as OpenAI - /v1/chat/completions, /v1/embeddings, /v1/audio/transcriptions, /v1/audio/speech, /v1/images/generations, /v1/models, plus a built-in /models gallery API - so any client written for OpenAI (openai-python, openai-node, LangChain OpenAI provider, LlamaIndex, IDE plugins) talks to it unchanged with one base URL swap. Inference runs entirely on CPU using llama.cpp and Whisper.cpp backends; GGUF model files load from local disk under /var/lib/localai/models and persist across restarts - no external database, no Redis, no cloud egress to OpenAI or Anthropic. Bring your own GGUF model (LLaMA family, Mistral, Qwen, Phi, Gemma) or install one in two clicks from the bundled gallery (mudler/LocalAI gallery index). MIT license, no vendor lock-in.

What the Lynxroute image adds

Security hardening:

Per-instance LOCALAI_API_KEY (24-char random) generated at first boot, enforced by LocalAI for every /v1/, /models, /embeddings, /audio, /images call - never baked into the image
The same API key authenticates OpenAI-SDK REST clients (Authorization: Bearer) and the Web UI ("Login with API Token") - one credential, one rotation surface
LocalAI bound to 127.0.0.1:8080 - the API process never listens on a public interface
Host Nginx fronts port 443 with a self-signed certificate; HTTP redirects to HTTPS; security headers (X-Content-Type-Options, X-Frame-Options, Referrer-Policy) applied
UFW firewall pre-configured - only TCP 22, 80, 443 are exposed
fail2ban, AppArmor
CVE scan - every image is scanned for vulnerabilities before release

OS hardening (CIS Level 1):

CIS Ubuntu 24.04 LTS Level 1 benchmark applied via ansible-lockdown
auditd, SSH hardening, kernel hardening, IMDSv2 enforced

Compliance artifacts:

SBOM - CycloneDX 1.6 at /etc/lynxroute/sbom.json
CIS Conformance Report at /etc/lynxroute/cis-report.html
CIS Tailored Profile at /usr/share/doc/lynxroute/CIS_TAILORED_PROFILE.md

Deploy

Launch in one command

Credentials are generated at first boot and written to /root/localai-credentials.txt.

AWS CLIAzure CLI

# subscribe once on the AWS Marketplace listing, then:
aws ec2 run-instances \
  --image-id resolve:ssm:/aws/service/marketplace/prod-lfouziothu6du/latest \
  --instance-type t3.large --key-name my-key --security-group-ids sg-xxxxxxxx

# accept the plan terms once, then:
az vm image terms accept --publisher lynxroute --offer localai --plan payg-gen2
az vm create -g my-rg -n localai --size Standard_D2s_v3 \
  --image lynxroute:localai:payg-gen2:latest --admin-username azureuser --generate-ssh-keys

Release notes

Latest release

The most recent release with notes; the full release history is in product.json.

LocalAI 4.12.1

AWS · 2026-10-25

LocalAI updated 4.12.0 -> 4.12.1, a security-only patch release. MIT unchanged
Security: hardened handling of user-supplied URLs (vision, image and audio endpoints): every redirect hop is validated, carrier-grade NAT and 0.0.0.0/8 ranges are treated as non-public, and the connection goes to the validated address
Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base, picking up every operating-system security update published since the previous build