> ## Documentation Index > Fetch the complete documentation index at: https://docs.baseten.co/llms.txt > Use this file to discover all available pages before exploring further. # Baseten overview > Run hosted models, deploy custom models, and train models on production GPU infrastructure. Baseten is a platform for model inference and training. You can call hosted models through an OpenAI-compatible API, deploy your own models on dedicated infrastructure, or train models and serve the resulting checkpoints. Baseten manages model containers, GPU capacity across clouds and regions, scaling, and observability. Its inference engines optimize supported model architectures for production traffic. Call a hosted model through Model APIs with an API key and the OpenAI SDK. ## Choose how to start Use Model APIs to call supported language models without deploying them. Package an open-source, fine-tuned, or custom model with Truss and deploy it on dedicated GPUs. Fine-tune with Loops or run your own training code with Training Jobs. To point a coding agent at Model APIs, see [Coding agents](/inference/model-apis/coding-agents). To let an agent operate your workspace, see [Connect your coding agent](/agent-setup). ## Model APIs [Model APIs](/inference/model-apis/overview) expose hosted endpoints for a curated set of models. They support the OpenAI Chat Completions API and the Anthropic Messages API in beta, so you can use familiar client SDKs. Choose Model APIs when a supported model fits your application and you want to start with an API call. Baseten manages the model, engine, hardware, and scaling. ## Dedicated inference Deploy an open-source model, private checkpoint, or custom model on dedicated infrastructure with [Truss](/development/model/overview). Truss packages the model and its dependencies, then Baseten builds and deploys the container. For supported architectures, a `config.yaml` can define the model, hardware, and inference engine without custom serving code. Use a Python model class or a custom Docker server when you need custom preprocessing, postprocessing, dependencies, or server behavior. Dedicated deployments give you control over the model, hardware, autoscaling settings, and release lifecycle. They also support stable environments for development, staging, and production. Deploy a model with a config-only Truss project. Follow the build, routing, autoscaling, cold-start, and promotion lifecycle. ## Inference engines Baseten maintains inference engines for common model architectures: * [Engine-Builder-LLM](/engines/engine-builder-llm/overview) compiles dense text-generation models with TensorRT-LLM. * [BIS-LLM](/engines/bis-llm/overview) serves large mixture-of-experts models with distributed inference and KV-aware routing. * [BEI](/engines/bei/overview) serves embedding, reranking, and classification models. You can select an engine in `config.yaml`, let Baseten select one for a supported architecture, or run a server such as vLLM or SGLang in a [custom Docker container](/development/model/custom-server). ## Training Baseten has two ways to train models: * [Loops](/loops/overview) provides dedicated trainers and samplers for supervised fine-tuning and reinforcement learning on supported base models. * [Training Jobs](/training/overview) runs your framework and training code in your own container on dedicated GPU clusters. Both paths store checkpoints that you can deploy to the Baseten inference stack. See [Training on Baseten](/training) to compare them. ## Production operations Every dedicated deployment includes [logs](/observability/logs), [metrics](/observability/metrics), request traces, [autoscaling](/deployment/autoscaling/overview), and [environment promotion](/deployment/environments). Export observability data to Datadog, Prometheus, Grafana, or New Relic, and store [secrets](/organization/secrets) in the workspace instead of in source control. [Multi-cloud Capacity Management](/concepts/howbasetenworks#multi-cloud-capacity-management-mcm) provisions GPUs across cloud providers and regions. Baseten also supports [multiple hosting options](/hosting-options/overview) for teams that need private networking, workload isolation, infrastructure ownership, or specific data regions. Baseten is [SOC 2 Type II](https://www.baseten.co/blog/soc-2-type-2) and [HIPAA](https://www.baseten.co/blog/baseten-announces-hipaa-compliance) compliant, and supports [regional environments](/deployment/regional-environments) for data-residency requirements. ## Baseten for Model Labs Baseten for Model Labs is how you serve and distribute models to your customers. It is enabled per workspace. To get access, [talk to us](https://www.baseten.co/talk-to-us/). Apply one access and policy layer across Baseten-hosted, third-party, and custom model targets. Sell your model through Baseten. Baseten manages the customer contract and billing. ## Next steps Make your first Model APIs request. Install the Baseten skill and MCP servers so your agent can operate your Baseten workspace and search these docs. Follow end-to-end guides for deploying and optimizing models. Browse the inference, management, training, and gateway APIs.