Baseten llms.txt · AI Docs Browser · mdream [llms.txt Tools](https://mdream.dev/llms-txt/baseten/llms-txt) # Baseten llms.txt docs.baseten.co/llms.txt [Raw llms.txt](https://docs.baseten.co/llms.txt) [Raw llms-full.txt](https://docs.baseten.co/llms-full.txt) Copy Markdown [](https://docs.baseten.co/llms.txt) llms.txt Docs AI tools Cancel a queued async request. Get the status of an async request. Asynchronously call a named environment of a chain. Asynchronously call a named environment of a model. Asynchronously call a specific deployment of a chain. Asynchronously call a specific deployment of a model. Asynchronously call the development deployment of a chain. Asynchronously call the development deployment of a model. Asynchronously call the production environment of a chain. Asynchronously call the production environment of a model. Call a specific chain deployment by deployment ID. Call a specific deployment of a model by deployment ID. Call the chain deployment associated with a specified environment. Call the development deployment of a chain. Call the development deployment of a model. Call the model deployment associated with a specified environment. Call the production environment of a chain. Call the production environment of a model. Get async queue status for a named environment. Get async queue status for a specific deployment. Get async queue status for the development deployment. Get async queue status for the production environment. Wake a named environment of a model. Wake a specific deployment of a model by deployment ID. Wake the development deployment of a model. Wake the production environment of a model. Asynchronously call a regional environment of a chain. Asynchronously call a regional environment of a model. Call a regional environment of a chain. Call a regional environment of a model. Get async queue status for a regional environment. Wake a regional environment of a model. How Baseten works Why Baseten Cold starts Autoscaling Request lifecycle Traffic patterns CI/CD Concepts Deployments Environments Manage the deployment lifecycle Pull logs and metrics Manage deployments Scale a deployment Regional environments Resources Rolling deployments Binary I/O Concepts Deploy Architecture and design Engine Builder LLM models Error handling Your first Chain Invocation Local development Overview Streaming Truss integration Subclassing Watch Baseten Delivery Network Build your model Configuration Custom Docker containers Dependencies Deploy and iterate Access model environments gRPC Health checks Cached weights The Model class Develop a model on Baseten Performance optimization Runtime caching Secrets Streaming and endpoints WebSockets BEI-Bert Configuration reference Named entity recognition Overview Advanced features for BIS-LLM Configuration reference Migrate from Engine-Builder-LLM Overview Custom engine builder Configuration reference Speculative decoding LoRA support Overview Overview Autoscaling engines Deploy from cloud storage Quantization guide Serve embeddings with BEI Transcribe audio with Chains Build a RAG pipeline with Chains Create a model with the REST API Customize a model Deploy a Hugging Face model Build and deploy an LLM Deploy your first model Deploy a Dockerized model Generate images with Flux Nemotron 3 Embed Qwen3 Embedding Qwen3 Reranker FLUX.1 Krea 2 Turbo DiffusionGemma Gemma 4 GLM-4.7 GLM-5 GPT-OSS Holo 3.1 Laguna Llama 3.1 Llama 3.2 Llama 3.3 Llama 4 Mellum2 MiniMax M2.5 Nemotron 3 Qwen3 Qwen3-VL Qwen3.5 Qwen3.6 Qwen3-ASR VibeVoice Voxtral Deploy LLMs with Ollama Build with Baseten Deploy LLMs with SGLang Deploy a model with Eagle speculative decoding Stream LLM responses Add system packages Deploy LLMs with TensorRT-LLM Generate speech with Kokoro Deploy LLMs with vLLM Manage groups and API keys Billing webhooks Call your model Manage endpoints Get started Baseten Frontier Gateway Rate and usage limits Async inference Call your model Inference errors Function calling Configure HTTP clients Integrations JSON mode Audio Deprecation Model APIs Rate limits and budgets Reasoning Vision Model I/O in binary Model I/O with files Overview Performance client SSH access Streaming Structured outputs Concepts Deploy a checkpoint Loss functions Loops Quickstart Supported base models Tinker compatibility Train on a dataset Export to Datadog Export to Grafana Cloud Export to New Relic Overview Export to Prometheus Metrics support matrix Status and health Logs Metrics Secure model inference Tracing Access control API keys Audit logs Billing and usage OpenID Connect (OIDC) authentication Organization settings Restricted environments Secrets SSO and SCIM Teams Baseten overview Quickstart Truss Push GitHub Action baseten api baseten auth baseten model baseten model-api baseten model deployment baseten model deployment replica baseten model environment baseten org api-key baseten org billing baseten org secret baseten org team baseten org user Baseten CLI overview baseten ssh baseten truss baseten version baseten whoami Chains CLI reference Baseten command-line tools Loops CLI reference Training CLI reference truss auth truss cleanup truss configure truss container truss download truss image truss init truss login truss migrate truss model-config truss model-logs Truss CLI reference truss push truss run-python truss ssh truss upgrade truss watch truss whoami Create an API key Get an API key List API keys for a group Register an API key Revoke an API key Billing webhooks Create an endpoint Delete an endpoint Get an endpoint List endpoints Update an endpoint Create a group Delete a group Get a group Get group usage List groups Update a group Overview Chat Completions Messages Overview Websocket deployment Websocket development Websocket environment Transcribe streaming audio Transcribe Pre-Recorded Audio Get checkpoint files List checkpoints Validate a checkpoint Deactivate a deployment Get a deployment Get deployment logs Get deployment metrics List deployments Loops API reference Create a run Get a run List runs Create a sampler Get a sampler List samplers Get server capabilities Create a session Get a session Create an API key Delete an API key Get all API keys Get billing usage summary Delete chains Get chainlet logs By ID All chains Any deployment by ID Activate environment deployment Development deployment Activate production deployment Add a deployment to a model Update chainlet environment's autoscaling settings Any model deployment by ID Development model deployment Update production deployment autoscaling settings Chain deployment Any deployment by ID Deactivate environment deployment Development deployment Deactivate production deployment Delete chain deployment Delete model deployments Get model deployment config Get model deployment download URL Get model deployment logs Get model deployment metrics Any chain deployment by ID Any model deployment by ID Development model deployment Production model deployment Get all chain deployments Get all model deployments Cancel model promotion Force cancel rolling deployment Force roll forward promotion Pause rolling deployment Promote to chain environment Promote to model environment Any model deployment by ID Development model deployment Resume rolling deployment Any deployment by ID Development deployment Production deployment Terminate deployment replica Get a team's environment group Get an environment group List environment groups List a team's environment groups Update a team's environment group Update an environment group Create Chain environment Create environment Get Chain environment Get all Chain environments Get all environments Get environment Get environment logs Get environment metrics Update Chain environment Update chainlet environment's instance type Update model environment All instance types Instance type prices By name All Model APIs Create a model from a source Delete models By ID All models Prepare a model upload Overview Rate limits Get all secrets Upsert a secret Create a team API key Create a team training project Get a team by ID Get all team secrets List all teams Upsert a team secret Get a user Get the current user List users Reference documentation Chains SDK Reference Errors Helpers Loops SDK reference SamplingClient ServiceClient TrainingClient Types Training SDK truss.load truss.login ModelDeployment Truss SDK Reference truss.push truss.whoami Create training job Create training project Delete training job Delete training project Download training job source code Get auth codes for training job Get training job Get training job checkpoint files List training job checkpoints Get training job logs Get training job metrics Get training job queue context Get training project Get training project cache summary List training projects List training jobs Overview Recreate training job Search training jobs Stop training job Truss configuration Baseten platform status Building blocks Cache Checkpoints Multinode training Storage and data ingestion Deploy with optimized inference engines Serve your trained model Get started VS Code and Cursor remote tunnels Lifecycle Load checkpoints Management Training on Baseten Remote access Slurm workstations SSH access Train on your own data Deployments Inference OpenAPI Specs management-api-spec messages-openapi-spec llm-openapi-spec inference-api-spec meta Very Uncomparables Typography Spelling Skunked RASSyndrome P-Value Oxymorons Nonwords Needless Malapropisms LGBTTerms LGBTOffensive Jargon Hyperbole Hedging GroupTerms GenderBias Diacritical DenizenLabels DateSpacing DateRedundancy DateMidnight DateCase Cursing Currency CorporateSpeak Cliches But Archaisms Apologizing Annotations AnimalLabels Airlinese WordList Will We Units Spacing Slang Semicolons Ranges Quotes Periods Passive Parens OxfordComma Ordinal OptionalPlurals LyHyphens Latin Headings HeadingPunctuation Gender FirstPerson Exclamation EmDash Ellipses DateFormat Contractions Colons Acronyms AMPM package package-lock settings spec ## What is Baseten's llms.txt? Baseten publishes an `/llms.txt` file that provides AI systems with a structured index of its documentation. It follows the [llms.txt specification](https://llmstxt.org), organizing links to guides, API references, and tutorials under section headings so that LLMs like ChatGPT, Claude, and Gemini can quickly understand what Baseten offers and where to find details. Pass Spec 2 Sections 500 Links 76.2 KB Size ~19.5k Tokens Sections: Docs · OpenAPI Specs ## Add Baseten Docs to Your AI Assistant Select your tool to see how to add Baseten's llms.txt as a documentation source. Cursor Windsurf Claude Code ChatGPT Zed Copilot 1. 1 Open any chat or composer panel 2. 2 Type @Docs and select "Add new doc" 3. 3 Paste the URL: https://docs.baseten.co/llms.txt 4. 4 Wait for the green dot (indexing complete) 5. 5 Reference @Docs in chat when asking about Baseten Cursor crawls the URL and indexes all subpages. Add a trailing slash to index child pages too. ## Spec Compliance 4 notes ## Frequently Asked Questions Where is Baseten's llms.txt file? Baseten publishes its llms.txt at https://docs.baseten.co/llms.txt. This file provides a structured, markdown-formatted index of Baseten's documentation that AI systems can consume to understand the project's APIs, guides, and references. How do I use Baseten's llms.txt with AI coding assistants? Copy the llms.txt content and paste it into your AI assistant (Cursor, Windsurf, Claude, ChatGPT) as context. This gives the AI an accurate map of Baseten's documentation so it can provide better code suggestions and answers about Baseten. What does Baseten's llms.txt contain? Baseten's llms.txt contains 2 sections and 500 documentation links in 76.2 KB (~19.5k tokens). Key sections include Docs, OpenAPI Specs. How many tokens does Baseten's llms.txt use? The concise llms.txt index is approximately 19.5k tokens (76.2 KB). Most AI assistants can fit this within their context window. For the full expanded documentation, look for an llms-full.txt variant which embeds all content inline. Can I generate an llms.txt for my own project? Yes. Use the free llms.txt generator at mdream.dev/tools/llms-txt/generator to crawl your site and produce a spec-compliant llms.txt file. You can also validate existing files with the llms.txt validator. ## Browse More llms.txt Files [Rolldown Fast Rust-based bundler for JavaScript with Rollup-compatible API](https://mdream.dev/llms-txt/baseten/llms-txt/rolldown) [Klavis AI Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale](https://mdream.dev/llms-txt/baseten/llms-txt/klavis) [Fireworks AI Docs](https://mdream.dev/llms-txt/baseten/llms-txt/fireworks) [Promptfoo Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.](https://mdream.dev/llms-txt/baseten/llms-txt/promptfoo) [Convex Documentation For general information about Convex, read \[https://www.convex.dev/llms.txt\](https://www.convex.dev/llms.txt).](https://mdream.dev/llms-txt/baseten/llms-txt/convex-backend) [Courier](https://mdream.dev/llms-txt/baseten/llms-txt/courier) [Directus Documentation Directus is a real-time API and no-code Data Studio for managing any SQL database. It provides REST and GraphQL APIs, granular access control, authentication, file storage, automations, realtime via WebSockets, analytics dashboards, AI integration, and a full extension system. The Data Studio is a web application for non-technical users to browse, manage, and visualize data without writing code.](https://mdream.dev/llms-txt/baseten/llms-txt/directus) [Pinecone Docs](https://mdream.dev/llms-txt/baseten/llms-txt/pinecone) [View all 99 projects ](https://mdream.dev/llms-txt/baseten/llms-txt) ## Related Tools [

llms.txt Generator

Generate an llms.txt for your own project.](https://mdream.dev/llms-txt/baseten/tools/llms-txt/generator) [

llms.txt Validator

Validate your llms.txt against the official spec.](https://mdream.dev/llms-txt/baseten/tools/llms-txt/validator) © 2026 [Harlan Wilton](https://github.com/harlan-zw) · [MIT](https://github.com/harlan-zw/mdream/blob/main/license) [GitHub](https://github.com/harlan-zw/mdream) [Discord](https://discord.com/invite/275MBUBvgP)