vLLM
A high-throughput open-source framework for LLM inference and OpenAI-compatible serving.
Open source under Apache-2.0; the GPU/cloud resources required to run it may incur costs.
View resource βOfficial resources filtered for AI/API development workflows. Free conditions and limits are governed by each official source.
A high-throughput open-source framework for LLM inference and OpenAI-compatible serving.
Open source under Apache-2.0; the GPU/cloud resources required to run it may incur costs.
View resource βA developer tool for running open models locally with a simple API.
The software is open source and free to run locally; hardware, power and model storage costs are the user's responsibility.
View resource βAn open protocol connecting models with external tools, data sources and workflows.
The specification and SDKs are public; service costs and permissions of individual servers must be checked separately.
View resource βAn open-source platform for machine learning and generative AI lifecycle management.
Open source and self-hostable; hosting and storage costs are billed separately.
View resource βA platform offering open-model inference, fine-tuning and high-performance deployment APIs.
Public documentation allows evaluating the APIs; free credits must be confirmed against the current account and pricing page.
View resource β