# Vultr Inference API > Public customer API. Private Vultr integration routes that require the platform key are not included. Every page below is also Markdown at its own URL with .md added. ## Get started - [Quickstart](/docs/get-started/quickstart.md): Your first request in a minute, with curl or the OpenAI SDK you may already use. - [Authentication](/docs/get-started/authentication.md): One API key per request, as a bearer token or as Anthropic's x-api-key header. - [SDKs and compatibility](/docs/get-started/sdks.md): Use the OpenAI, Anthropic or OpenRouter SDK you already have; change the base URL and the key. ## Concepts - [Errors](/docs/concepts/errors.md): A request that fails answers with an HTTP status and a JSON error body. Every route uses OpenRouter's error shape, except /v1/messages, which uses Anthropic's so their SDKs and Claude Code can read it. - [Limits](/docs/concepts/limits.md): How many requests a minute, how many at once, how much a model reads and writes, and how large a body can be. - [Streaming](/docs/concepts/streaming.md): Read the answer as it is written, on chat completions, responses and messages, and what a stream looks like when it fails. - [Async jobs](/docs/concepts/async-jobs.md): A video or a song takes seconds to minutes to render, so creating one answers 202 at once with a job. Poll the job, listen to a song as it renders, or have a webhook tell you when it is done. - [Webhooks](/docs/concepts/webhooks.md): Have a finished video or song call your server, signed so you know it came from us. - [Reasoning](/docs/concepts/reasoning.md): Models that think before they answer: how much they think, how to cap it, and where the thinking comes back. - [Documents and media](/docs/concepts/documents.md): Send PDFs, Office files, images, audio and video in a conversation; what each becomes, and what it costs. ## Workflows - [Chat over your files](/docs/workflows/chat-over-files.md): Ask questions about your documents: upload them once and send them whole, or store them in a vector store and let the API find the passages that matter. - [Render a video with webhooks](/docs/workflows/video-webhooks.md): Start a render, have it call your server when it is done, and download the video, without polling. - [Write songs for MiniMax Music 3](/docs/workflows/music-minimax-music3.md): How to write the caption and lyrics MiniMax Music 3 sings best from, cast singers, control a song's length, and hear it as it renders. - [Claude Code](/docs/workflows/claude-code.md): Run Claude Code on open models: point it at the API with your key, and pick a model in /model. ## Integrations - [Coding agents](/docs/integrations/coding-agents.md): Use Vultr Serverless Inference in Codex CLI, OpenCode, OpenClaw, pi and Hermes Agent, with the live model list, context windows and reasoning levels. - [Codex CLI](/docs/integrations/codex.md): Run OpenAI's Codex CLI on Vultr Serverless Inference: one install writes a vultr profile and a live model list, and codex -p vultr uses them. - [OpenCode](/docs/integrations/opencode.md): Give OpenCode's vultr provider the live model list: context windows, output limits, prices and reasoning variants, from one plugin entry. - [OpenClaw](/docs/integrations/openclaw.md): Add Vultr Serverless Inference to OpenClaw from ClawHub: the live model list with context windows, prices, input types and thinking levels. - [pi](/docs/integrations/pi.md): Use Vultr Serverless Inference in the pi coding agent: one package install, and the live model list with context windows, prices and thinking levels. - [Hermes Agent](/docs/integrations/hermes.md): Add Vultr Serverless Inference to Nous Research's Hermes Agent: a provider plugin with the live model list, context windows and reasoning efforts. - [Model catalog libraries](/docs/integrations/model-catalog.md): Read the live model list from TypeScript or Python: context windows, output limits, exact prices, modalities and reasoning levels, with an offline cache. ## Models - [Models](/docs/models.md): every model the API serves with its price, read from the live catalog ## API reference The OpenAPI document: /docs/openapi.json ### Messages - [POST /v1/messages](/docs/reference/create-message.md): Create Message ### Chat - [POST /v1/chat/completions](/docs/reference/create-chat-completion.md): Create Chat Completion - [POST /v1/chat/completions/RAG](/docs/reference/rag-chat-completion.md): RAG Chat Completion ### Responses - [POST /v1/responses](/docs/reference/create-response.md): Create Response - [GET /v1/responses/{id}](/docs/reference/get-response.md): Get Response - [DELETE /v1/responses/{id}](/docs/reference/delete-response.md): Delete Response ### Embeddings - [POST /v1/embeddings](/docs/reference/create-embeddings.md): Create Embeddings - [GET /v1/embeddings/models](/docs/reference/list-embedding-models.md): List Embedding Models ### Decisions - [POST /v1/systemone](/docs/reference/create-systemone.md): Create Decision ### Rerank - [POST /v1/rerank](/docs/reference/create-rerank.md): Rerank Documents ### Audio - [GET /v1/audio/models](/docs/reference/list-audio-models.md): List Audio Models (deprecated) - [POST /v1/audio/speech](/docs/reference/create-speech.md): Create Speech - [POST /v1/audio/transcriptions](/docs/reference/create-transcription.md): Create Transcription - [GET /v1/audio/voices](/docs/reference/list-audio-voices.md): List Audio Voices ### Files - [GET /v1/files](/docs/reference/list-files.md): List Files - [POST /v1/files](/docs/reference/create-file.md): Upload File - [GET /v1/files/{id}](/docs/reference/get-file.md): Get File - [DELETE /v1/files/{id}](/docs/reference/delete-file.md): Delete File ### Vector Store - [GET /v1/vector_store](/docs/reference/list-vector-stores.md): List Collections - [POST /v1/vector_store](/docs/reference/create-vector-store.md): Create Collection - [GET /v1/vector_store/{id}](/docs/reference/get-vector-store.md): Get Collection - [DELETE /v1/vector_store/{id}](/docs/reference/delete-vector-store.md): Delete Collection - [PATCH /v1/vector_store/{id}](/docs/reference/update-vector-store.md): Update Collection - [POST /v1/vector_store/{id}/search](/docs/reference/search-vector-store.md): Search Collection - [GET /v1/vector_store/{id}/items](/docs/reference/list-vector-store-items.md): List Collection Items - [POST /v1/vector_store/{id}/items](/docs/reference/add-vector-store-item.md): Add Collection Item - [GET /v1/vector_store/{id}/items/{itemid}](/docs/reference/get-vector-store-item.md): Get Collection Item - [DELETE /v1/vector_store/{id}/items/{itemid}](/docs/reference/delete-vector-store-item.md): Delete Collection Item - [PATCH /v1/vector_store/{id}/items/{itemid}](/docs/reference/update-vector-store-item.md): Update Collection Item - [GET /v1/vector_store/{id}/files](/docs/reference/list-vector-store-files.md): List Collection Files - [POST /v1/vector_store/{id}/files](/docs/reference/add-vector-store-file.md): Add Collection File - [GET /v1/vector_store/{id}/files/{fileid}](/docs/reference/get-vector-store-file.md): Get Collection File - [DELETE /v1/vector_store/{id}/files/{fileid}](/docs/reference/delete-vector-store-file.md): Delete Collection File ### Images - [GET /v1/images/models](/docs/reference/list-image-models.md): List Image Models - [GET /v1/images/models/{author}/{slug}/endpoints](/docs/reference/list-image-model-endpoints.md): List Image Model Endpoints - [POST /v1/images](/docs/reference/create-image-openrouter.md): Generate Image (OpenRouter) - [POST /v1/images/generations](/docs/reference/create-image.md): Create Image - [POST /v1/images/edits](/docs/reference/create-image-edit.md): Edit Image ### Videos - [GET /v1/videos](/docs/reference/list-videos.md): List Videos - [POST /v1/videos](/docs/reference/create-video.md): Create Video - [GET /v1/videos/models](/docs/reference/list-video-models.md): List Video Models - [GET /v1/videos/{id}](/docs/reference/get-video.md): Get Video - [DELETE /v1/videos/{id}](/docs/reference/delete-video.md): Cancel or Delete Video - [GET /v1/videos/{id}/content](/docs/reference/get-video-content.md): Download Video ### Music - [GET /v1/music](/docs/reference/list-music.md): List Music - [POST /v1/music](/docs/reference/create-music.md): Create Music - [GET /v1/music/models](/docs/reference/list-music-models.md): List Music Models - [GET /v1/music/{id}](/docs/reference/get-music.md): Get Music - [DELETE /v1/music/{id}](/docs/reference/delete-music.md): Cancel or Delete Music - [GET /v1/music/{id}/content](/docs/reference/get-music-content.md): Download Music - [GET /v1/music/{id}/stream](/docs/reference/get-music-stream.md): Stream Music ### Webhooks - [GET /v1/webhooks/secret](/docs/reference/get-webhook-secret.md): Get Webhook Secret - [POST /v1/webhooks/secret/rotate](/docs/reference/rotate-webhook-secret.md): Rotate Webhook Secret ### Models - [GET /v1/models](/docs/reference/list-models.md): List Models - [GET /v1/models/count](/docs/reference/count-models.md): Count Models - [GET /v1/models/{id}](/docs/reference/get-model.md): Get Model - [GET /v1/model/{author}/{slug}](/docs/reference/get-model-by-author-and-slug.md): Get Model By Author And Slug - [GET /v1/models/all](/docs/reference/list-all-models.md): List All Models (deprecated) ### Usage - [GET /v1/usage](/docs/reference/get-usage.md): Get Usage ### Health Check - [GET /v1/health](/docs/reference/get-cluster-status.md): Get Cluster Status