# Baseten > ## Documentation Index ## Pages - [MARS6](mars6.md): ## Documentation Index - [Access control](access.md): ## Documentation Index - [Activate environment deployment](activates-a-deployment-associated-with-an-environment.md): ## Documentation Index - [Any deployment by ID](activates-a-deployment.md): ## Documentation Index - [Development deployment](activates-a-development-deployment.md): ## Documentation Index - [Gated features for BIS-LLM](advanced-features.md): ## Documentation Index - [All MPNet Base V2](all-mpnet-base-v2.md): ## Documentation Index - [API keys](api-keys.md): ## Documentation Index - [Async inference](async.md): ## Documentation Index - [Auto-Scaling Engines](autoscaling-engines.md): ## Documentation Index - [Autoscaling](autoscaling.md): ## Documentation Index - [b10cache 🆕](b10cache.md): ## Documentation Index - [Base Docker images](base-images.md): ## Documentation Index - [Basics](basics.md): ## Documentation Index - [BEI-Bert](bei-bert.md): ## Documentation Index - [Configuration reference](bei-reference.md): ## Documentation Index - [Embeddings with BEI](bei.md): ## Documentation Index - [Model I/O in binary](binary.md): ## Documentation Index - [Binary IO](binaryio.md): ## Documentation Index - [Reference Config (BIS-LLM)](bis-llm-config.md): ## Documentation Index - [Custom build commands](build-commands.md): ## Documentation Index - [Your first model](build-your-first-model.md): ## Documentation Index - [Cache](cache.md): ## Documentation Index - [Call your model](calling-your-model.md): ## Documentation Index - [Async cancel request](cancel-async-request.md): ## Documentation Index - [Cancel model promotion](cancel-promotion.md): ## Documentation Index - [Transcribe audio with Chains](chains-audio-transcription.md): ## Documentation Index - [RAG pipeline with Chains](chains-build-rag.md): ## Documentation Index - [Chains CLI reference](chains-cli.md): ## Documentation Index - [Chains SDK Reference](chains.md): ## Documentation Index - [Chat Completions](chat-completions.md): ## Documentation Index - [Checkpointing](checkpointing.md): ## Documentation Index - [truss cleanup](cleanup.md): ## Documentation Index - [Python driven configuration for models 🆕](code-first-development.md): ## Documentation Index - [Deploy a ComfyUI project](comfyui.md): ## Documentation Index - [Concepts](concepts.md): ## Documentation Index - [Request concurrency](concurrency.md): ## Documentation Index - [Configuration](configuration.md): ## Documentation Index - [truss configure](configure.md): ## Documentation Index - [truss container](container.md): ## Documentation Index - [Create Chain environment](create-a-chain-environment.md): ## Documentation Index - [Create environment](create-an-environment.md): ## Documentation Index - [Create training project](create-training-project.md): ## Documentation Index - [Create a team API key](creates-a-team-api-key.md): ## Documentation Index - [Create a team training project](creates-a-team-training-project.md): ## Documentation Index - [Create an API key](creates-an-api-key.md): ## Documentation Index - [Custom engine builder](custom-engine-builder.md): ## Documentation Index - [Custom health checks](custom-health-checks.md): ## Documentation Index - [Deploy custom Docker images](custom-server.md): ## Documentation Index - [Data and storage](data-directory.md): ## Documentation Index - [Export to Datadog](datadog.md): ## Documentation Index - [Deactivate environment deployment](deactivates-a-deployment-associated-with-an-environment.md): ## Documentation Index - [Any deployment by ID](deactivates-a-deployment.md): ## Documentation Index - [Development deployment](deactivates-a-development-deployment.md): ## Documentation Index - [DeepSeek-R1 Qwen 7B](deepseek-r1-qwen-7b.md): ## Documentation Index - [Deepseek R1](deepseek-r1.md): ## Documentation Index - [Delete an API key](delete-an-api-key.md): ## Documentation Index - [Delete chains](deletes-a-chain-by-id.md): ## Documentation Index - [Delete chain deployment](deletes-a-chain-deployment-by-id.md): ## Documentation Index - [Delete models](deletes-a-model-by-id.md): ## Documentation Index - [Delete model deployments](deletes-a-models-deployment-by-id.md): ## Documentation Index - [Deploy and iterate](deploy-and-iterate.md): ## Documentation Index - [Deploy your first model](deploy-your-first-model.md): ## Documentation Index - [Deploy](deploy.md): ## Documentation Index - [Async deployment](deployment-async-predict.md): ## Documentation Index - [Async chains deployment](deployment-async-run-remote.md): ## Documentation Index - [Deploy training and S3 checkpoints](deployment-from-training-and-s3.md): ## Documentation Index - [Async deployment](deployment-get-async-queue-status.md): ## Documentation Index - [Deployment](deployment-predict.md): ## Documentation Index - [Chains deployment](deployment-run-remote.md): ## Documentation Index - [Deployment](deployment-wake.md): ## Documentation Index - [Websocket deployment](deployment-websocket.md): ## Documentation Index - [Serving your trained model](deployment.md): ## Documentation Index - [Deployments](deployments.md): ## Documentation Index - [Deprecation](deprecation.md): ## Documentation Index - [Architecture and design](design.md): ## Documentation Index - [Async development](development-async-predict.md): ## Documentation Index - [Async chains development](development-async-run-remote.md): ## Documentation Index - [Async development](development-get-async-queue-status.md): ## Documentation Index - [Development](development-predict.md): ## Documentation Index - [Chains development](development-run-remote.md): ## Documentation Index - [Development](development-wake.md): ## Documentation Index - [Websocket development](development-websocket.md): ## Documentation Index - [Dockerized model](docker.md): ## Documentation Index - [Download training job source code](download-training-job.md): ## Documentation Index - [Reference config (Engine-Builder-LLM)](engine-builder-config.md): ## Documentation Index - [Engine control in Python](engine-builder-customization.md): Use`model.py`to customize engine behavior - [Engine-Builder LLM Models](engine-builder-models.md): ## Documentation Index - [Engine builder overview](engine-builder-overview.md): Deploy optimized model inference servers in minutes - [Async environment](environments-async-predict.md): ## Documentation Index - [Async chains environment](environments-async-run-remote.md): ## Documentation Index - [Async environment](environments-get-async-queue-status.md): ## Documentation Index - [Environment](environments-predict.md): ## Documentation Index - [Chains environment](environments-run-remote.md): ## Documentation Index - [Websocket environment](environments-websocket.md): ## Documentation Index - [Environments](environments.md): ## Documentation Index - [Error Handling](errorhandling.md): ## Documentation Index - [Model I/O with files](files.md): ## Documentation Index - [Flux-Schnell](flux-schnell.md): ## Documentation Index - [Function calling](function-calling.md): ## Documentation Index - [Gemma 3 27B IT](gemma-3-27b-it.md): ## Documentation Index - [Get Chain environment](get-a-chain-environments-details.md): ## Documentation Index - [Get all Chain environments](get-all-chain-environments.md): ## Documentation Index - [Get all environments](get-all-environments.md): ## Documentation Index - [Get environment](get-an-environments-details.md): ## Documentation Index - [Async request](get-async-request-status.md): ## Documentation Index - [Get training job checkpoint files](get-training-job-checkpoint-files.md): ## Documentation Index - [List training job checkpoints](get-training-job-checkpoints.md): ## Documentation Index - [Get training job logs](get-training-job-logs.md): ## Documentation Index - [Get training job metrics](get-training-job-metrics.md): ## Documentation Index - [Get training job](get-training-job.md): ## Documentation Index - [List training projects](get-training-projects.md): ## Documentation Index - [By ID](gets-a-chain-by-id.md): ## Documentation Index - [Any chain deployment by ID](gets-a-chain-deployment-by-id.md): ## Documentation Index - [By ID](gets-a-model-by-id.md): ## Documentation Index - [Any model deployment by ID](gets-a-models-deployment-by-id.md): ## Documentation Index - [Development model deployment](gets-a-models-development-deployment.md): ## Documentation Index - [Production model deployment](gets-a-models-production-deployment.md): ## Documentation Index - [Get all chain deployments](gets-all-chain-deployments.md): ## Documentation Index - [All chains](gets-all-chains.md): ## Documentation Index - [Get all model deployments](gets-all-deployments-of-a-model.md): ## Documentation Index - [All instance types](gets-all-instance-types.md): ## Documentation Index - [All models](gets-all-models.md): ## Documentation Index - [Get all secrets](gets-all-secrets.md): ## Documentation Index - [Get all team secrets](gets-all-team-secrets.md): ## Documentation Index - [Instance type prices](gets-instance-type-prices.md): ## Documentation Index - [Your first Chain](getting-started.md): ## Documentation Index - [Export to Grafana Cloud](grafana.md): ## Documentation Index - [gRPC 🆕](grpc.md): ## Documentation Index - [Status and health](health.md): ## Documentation Index - [How Baseten works](howbasetenworks.md): ## Documentation Index - [Image generation](image-generation.md): ## Documentation Index - [truss image](image.md): ## Documentation Index - [Implementation](implementation.md): ## Documentation Index - [Overview](index.md): ## Documentation Index - [Inference](inference.md): ## Documentation Index - [truss init](init.md): ## Documentation Index - [Integrations](integrations.md): ## Documentation Index - [Invocation](invocation.md): ## Documentation Index - [Kokoro](kokoro.md): ## Documentation Index - [Lifecycle](lifecycle.md): ## Documentation Index - [List training jobs](list-training-jobs.md): ## Documentation Index - [List all teams](lists-all-teams.md): ## Documentation Index - [Get all API keys](lists-the-users-api-keys.md): ## Documentation Index - [Llama 3.3 70B Instruct](llama-33-70b-instruct.md): ## Documentation Index - [Loading Checkpoints](loading.md): ## Documentation Index - [Local Development](localdev.md): ## Documentation Index - [truss login](login.md): ## Documentation Index - [Speculative decoding guide](lookahead-decoding.md): ## Documentation Index - [LoRA support](lora-support.md): ## Documentation Index - [Management](management.md): ## Documentation Index - [Metrics](metrics.md): ## Documentation Index - [Cached weights 🆕](model-cache.md): ## Documentation Index - [truss model-logs](model-logs.md): ## Documentation Index - [Multinode Training](multinode.md): ## Documentation Index - [Export to New Relic](new-relic.md): ## Documentation Index - [Nomic Embed v1.5](nomic-embed-v1-5.md): ## Documentation Index - [Overview](overview.md): ## Documentation Index - [Performance client](performance-client.md): ## Documentation Index - [Performance optimization](performance-optimization.md): ## Documentation Index - [truss predict](predict.md): ## Documentation Index - [Private Docker registries](private-registries.md): ## Documentation Index - [Production](production-wake.md): ## Documentation Index - [Export to Prometheus](prometheus.md): ## Documentation Index - [Promote to chain environment](promotes-a-chain-deployment-to-an-environment.md): ## Documentation Index - [Promote to model environment](promotes-a-deployment-to-an-environment.md): ## Documentation Index - [Any model deployment by ID](promotes-a-deployment-to-production.md): ## Documentation Index - [Development model deployment](promotes-a-development-deployment-to-production.md): ## Documentation Index - [truss push](push.md): ## Documentation Index - [Quantization guide](quantization-guide.md): ## Documentation Index - [Quick start](quickstart.md): ## Documentation Index - [Qwen-2-5-32B-Coder-Instruct](qwen-2-5-32b-coder-instruct.md): ## Documentation Index - [Rate limits and budgets](rate-limits-and-budgets.md): ## Documentation Index - [Reasoning](reasoning.md): ## Documentation Index - [Recreate training job](recreate-training-job.md): ## Documentation Index - [Using request objects / cancellation](requests.md): ## Documentation Index - [Resources](resources.md): ## Documentation Index - [Custom responses](responses.md): ## Documentation Index - [Restricted environments](restricted-environments.md): ## Documentation Index - [truss run-python](run-python.md): ## Documentation Index - [SDXL Lightning](sdxl-lightning.md): ## Documentation Index - [Search training jobs](search-training-jobs.md): ## Documentation Index - [Secrets](secrets.md): ## Documentation Index - [Secure model inference](security.md): ## Documentation Index - [Deploy LLMs with SGLang](sglang.md): ## Documentation Index - [Speculative Decoding Examples](speculative-decoding.md): ## Documentation Index - [Baseten platform status](status.md): ## Documentation Index - [Stop training job](stop-training-job.md): ## Documentation Index - [Streaming](streaming.md): ## Documentation Index - [Structured output (JSON mode)](structured-output.md): Enforce an output schema on LLM inference - [Structured outputs](structured-outputs.md): ## Documentation Index - [Truss Integration](stub.md): ## Documentation Index - [Subclassing](subclassing.md): ## Documentation Index - [Metrics support matrix](supported-metrics.md): ## Documentation Index - [Teams 🆕](teams.md): ## Documentation Index - [Fast LLMs with TensorRT-LLM](tensorrt-llm.md): ## Documentation Index - [Text to speech](text-to-speech.md): ## Documentation Index - [Torch compile caching 🆕](torch-compile-cache.md): ## Documentation Index - [Tracing](tracing.md): ## Documentation Index - [Training CLI reference](training-cli.md): ## Documentation Index - [Training SDK](training.md): ## Documentation Index - [Truss configuration](truss-configuration.md): ## Documentation Index - [Truss SDK Reference](truss.md): ## Documentation Index - [Update Chain environment](update-a-chain-environments-settings.md): ## Documentation Index - [Update chainlet environment's autoscaling settings](update-a-chainlet-environments-autoscaling-settings.md): ## Documentation Index - [Update chainlet environment's instance type](update-a-chainlet-environments-instance-type-settings.md): ## Documentation Index - [Update model environment](update-an-environments-settings.md): ## Documentation Index - [Any model deployment by ID](updates-a-deployments-autoscaling-settings.md): ## Documentation Index - [Development model deployment](updates-a-development-deployments-autoscaling-settings.md): ## Documentation Index - [Upsert a secret](upserts-a-secret.md): ## Documentation Index - [Upsert a team secret](upserts-a-team-secret.md): ## Documentation Index - [Billing and usage](usage.md): ## Documentation Index - [Run any LLM with vLLM](vllm.md): ## Documentation Index - [Watch](watch.md): ## Documentation Index - [WebSockets 🆕](websockets.md): ## Documentation Index - [Whisper V3](whisper-v3-fastest.md): ## Documentation Index - [truss whoami](whoami.md): ## Documentation Index - [Why Baseten](whybaseten.md): ## Documentation Index