All comparisons


| Visit LibreChat | Visit vLLM | |
|---|---|---|
| What it costs | ||
| Pricing | Open source | Open source |
| Pricing details | Free and MIT licensed, self-hosted with Docker. No pricing page. The formerly paid Code Interpreter API is being discontinued following the ClickHouse acquisition. You pay the model providers directly. | Free and Apache-2.0. There is no pricing page, no hosted tier and no paid edition; the project is funded by donations through GitHub and OpenCollective, and compute for development and testing is contributed by sponsors. Your cost is the hardware you run it on. |
| Price range | $0/mo | Not published by the vendor |
| Free option | Free tier | No free option |
| What it is | ||
| What it does | Self-hosted, MIT-licensed chat interface for every model provider, with agents, MCP tools, a code interpreter, memory, web search and SSO. Runs in Docker. | The Apache-2.0 serving engine that most self-hosted LLM stacks run on, exposing any of 200+ open-weights architectures behind an OpenAI-compatible API. |
| The details | ||
| GitHub stars | 44,316stars | 90,229stars |
| Language | TypeScript | Python |
| License | MIT License | Apache License 2.0 |
| Last commit | 18 Sept 2026 | 27 Aug 2026 |
What it costs
- Pricing
- Open source
- Pricing details
- Free and MIT licensed, self-hosted with Docker. No pricing page. The formerly paid Code Interpreter API is being discontinued following the ClickHouse acquisition. You pay the model providers directly.
- Price range
- $0/mo
- Free option
- Free tier
What it is
- What it does
- Self-hosted, MIT-licensed chat interface for every model provider, with agents, MCP tools, a code interpreter, memory, web search and SSO. Runs in Docker.
The details
- GitHub stars
- 44,316stars
- Language
- TypeScript
- License
- MIT License
- Last commit
- 18 Sept 2026
What it costs
- Pricing
- Open source
- Pricing details
- Free and Apache-2.0. There is no pricing page, no hosted tier and no paid edition; the project is funded by donations through GitHub and OpenCollective, and compute for development and testing is contributed by sponsors. Your cost is the hardware you run it on.
- Price range
- Not published by the vendor
- Free option
- No free option
What it is
- What it does
- The Apache-2.0 serving engine that most self-hosted LLM stacks run on, exposing any of 200+ open-weights architectures behind an OpenAI-compatible API.
The details
- GitHub stars
- 90,229stars
- Language
- Python
- License
- Apache License 2.0
- Last commit
- 27 Aug 2026
Read the full reviews
What each one is actually like to use, tested by hand rather than summarised from the vendor’s own page.


























