providers

Tools we use.

Honest reviews of the providers behind self-hosted AI deployments. What we use, what we recommend, what we'd switch to. Affiliate relationships disclosed on every page.

LLM providers

llm★★★★★

Anthropic (Claude API)

The LLM provider we default to for self-hosted agent workloads. Claude 4.5 Sonnet remains the best agentic model in 2026.

$3 / 1M input tokens, $15 / 1M output (Sonnet 4.5)

llm★★★★★

OpenAI (GPT API)

GPT-5 is competitive with Claude on many tasks. The API is the most mature in the market; the agent behaviour is more variable.

$2.50 / 1M input tokens, $10 / 1M output (GPT-5)

llm★★★★★

OpenRouter

LLM gateway with unified API across 100+ providers. Our default for cost-optimisation and provider fallback.

At-cost from upstream provider + small markup* affiliate

Hosting & VPS

hosting★★★★★

Hetzner

German VPS provider. CX22 plan at €5/month is our standard test rig. The cheapest credible EU VPS in 2026.

€5/month (CX22) — €38/month (CCX13 dedicated)* affiliate

hosting★★★★★

Cloudflare Workers

Edge serverless platform. Free tier covers serious traffic. The reference deployment target for Moltworker.

Free tier (100K requests/day) — $5+/month paid tiers

Networking

network★★★★★

Tailscale

Mesh VPN built on WireGuard. The standard 2026 way to keep self-hosted dashboards off the public internet.

Free for personal use (up to 100 devices, 3 users) — $5/user/month for teams

Every affiliate relationship listed at /disclosure. Sponsorship inquiries at /partners.