LLM Providers shortlist: Self-hosted / on-prem + Chat / conversational
Narrow your LLM provider shortlist by deployment model, primary workload, and cost sensitivity. The model that performs best on coding benchmarks is rarely the most cost-efficient choice for high-volume document extraction or chat. Self-hosted models offer cost and data sovereignty advantages but require significant infrastructure to operate reliably. These filters help you skip providers whose deployment model or cost structure don't fit your use case before running detailed evaluations.
2 products match your constraints
Each product below fits the filters you selected. Click through to read the full decision brief — pricing behavior, limits, and what breaks first.
Open-weight model family enabling self-hosting and flexible deployment, often chosen when data control, vendor flexibility, or cost constraints outweigh managed convenience.
Model provider with open-weight and hosted options, often shortlisted for cost efficiency, vendor flexibility, and European alignment while still supporting a managed API route.
Share this shortlist
Send this URL to your team — it preserves your exact filter selections.
Refine your shortlist
Change a filter to see which products match different constraint combinations.