Deployment
Small Models (<10B) providers
Every model provider on LLMAPI tagged “Small Models (<10B)” — 3 of 50 providers. All of them run through one API key and one OpenAI-compatible endpoint.
Providers listed3
Models reachable11
Filters available84
IntegrationOne OpenAI-compatible endpoint
3 providers matching this filter.
| Provider | Models | Regions | Best for | |
|---|---|---|---|---|
Liquid AI Liquid foundation models beyond transformers. |
6 | US | Low-latency inference at the edge and on-device | View → |
Multiverse Computing Compressed models via quantum-inspired techniques. |
3 | EU | Compressed models for on-device and cost-sensitive deployments | View → |
Inco Confidential-computing model inference. |
2 | US | Privacy-sensitive workloads in confidential enclaves | View → |
One key, every provider on this page
Consolidated billing, spend limits and instant fallback between providers.