Compatibility Matrix
Which LibreChat capabilities are supported by each model endpoint type.
LibreChat connects to many AI providers through a small set of endpoint types. This page summarizes which capabilities each endpoint supports. Many capabilities depend on the specific model you select, so those cells are marked as model-dependent rather than a hard yes or no.
- Supported
- Not supported
- Depends on the model
- Via the Agents endpoint
| Capability | OpenAI | Azure OpenAI | Anthropic | AWS Bedrock | Custom (OpenAI-compatible) | Agents | Assistants | |
|---|---|---|---|---|---|---|---|---|
| Streaming responses | Supported | Supported | Supported | Supported | Supported | Supported | Supported | Supported |
| Vision (image input) | Depends on the model | Depends on the model | Depends on the model | Depends on the model | Depends on the model | Depends on the model | Depends on the model | Depends on the model |
| Tools / function calling | Depends on the model | Depends on the model | Depends on the model | Depends on the model | Depends on the model | Depends on the model | Supported | Supported |
| Web Search | Supported | Supported | Supported | Supported | Supported | Supported | Supported | Not supported |
| Code Interpreter | Supported | Supported | Supported | Supported | Supported | Supported | Supported | Supported |
| Artifacts | Supported | Supported | Supported | Supported | Supported | Supported | Supported | Not supported |
| File Search (RAG) | Supported | Supported | Supported | Supported | Supported | Supported | Supported | Supported |
| Image Generation | Via the Agents endpoint | Via the Agents endpoint | Via the Agents endpoint | Via the Agents endpoint | Via the Agents endpoint | Via the Agents endpoint | Supported | Via the Agents endpoint |
| OCR | Supported | Supported | Supported | Supported | Supported | Supported | Supported | Supported |
| Memory | Supported | Supported | Supported | Supported | Supported | Supported | Supported | Not supported |
| MCP | Via the Agents endpoint | Via the Agents endpoint | Via the Agents endpoint | Via the Agents endpoint | Via the Agents endpoint | Via the Agents endpoint | Supported | Not supported |
Quick reference, maintained manually. “Depends on the model” means the capability is available when the selected model supports it. Verify against your deployed version. Last reviewed: 2026-06-18.
Notes
- Custom (OpenAI-compatible) covers any provider configured through custom endpoints, such as OpenRouter, Groq, Mistral, Ollama, DeepSeek, Perplexity, and others. Exact support depends on how closely the provider mirrors the OpenAI API and on the model you pick.
- Agents is the most capable endpoint: it adds tool use, MCP, Code Interpreter, file search, and Image Generation on top of most base models. Reach for it when you need capabilities a plain chat endpoint doesn't expose.
- Vision and tools / function calling are properties of the model, not the endpoint, so a capable model is required regardless of provider.
- Assistants uses OpenAI's Assistants runtime, which provides its own file search and code execution but does not layer on LibreChat features such as Memory or Artifacts.
This is a manually maintained quick reference. If a value looks wrong for your release, please open an issue or PR.
How is this guide?