{"slug": "rubyllm-what-s-new-in-2-0", "title": "RubyLLM: What's New in 2.0", "summary": "RubyLLM 2.0 adds video, speech, OCR, reranking, files, batches, and a shared API for provider-hosted tools to the Ruby framework, expanding on the chat, tools, agents, structured output, thinking, embeddings, images, transcription, and moderation support already present in version 1.16. The release also introduces tool approvals, citations, thinking, caching, and fallbacks, plus new APIs for media, documents, and search, with usage tracking and workflows for larger applications and Rails integration. The 40 shared features are documented in a provider coverage matrix spanning OpenAI, Anthropic, Gemini, Vertex AI, Amazon Bedrock, Azure OpenAI/Foundry, xAI, DeepSeek, Cohere, Mistral, OpenRouter, Perplexity, Deepgram, ElevenLabs, Ollama, Ollama Cloud, and GPUStack.", "body_md": "Skip to content\nSearch\n⌘\nCtrl\nK\nMain Navigation\nGuides\nAPI\nWhat's New in 2.0\nModels\nBlog\n2.0.0 (stable)\n2.0.0 (stable)\n1.16.0\nChangelog\nAppearance\nStar\n...\nSupport\nStar\n...\nSupport\nGuides\nAPI\nWhat's New in 2.0\nModels\nBlog\n2.0.0 (stable)\n2.0.0 (stable)\n1.16.0\nChangelog\nAppearance\nStar\n...\nSupport\nSearch documentation\nEsc\nMenu\nOn this page\nReturn to top\nOn this page\nCopy page\nCopy page\nCopy page as Markdown for LLMs\nView as Markdown\nView this page as plain text\n# What's New in 2.0 Explore the expanded provider coverage, new AI operations, conversation controls, and Rails integration in RubyLLM 2.0. {: .fs-6 .fw-300 } After reading this guide, you will know: * How much more of each provider's API you can use in 2.0. * How to use tool approvals, citations, thinking, caching, and fallbacks. * Which new APIs you can use for media, documents, and search. * How batches, usage tracking, and workflows support larger applications. * How these features fit into Rails. RubyLLM 2.0 expands the framework across conversations, agents, media, documents, and Rails. You can use much more of each provider's API through Ruby methods, with consistent results, streaming, and usage tracking. You also get more control over how conversations run and persist. The examples assume you have [configured the providers you use](https://rubyllm.com/configuration/). For an existing application, the [upgrade guide](https://rubyllm.com/upgrading/) covers API changes and database migrations. ## Provider API Coverage 1.16 already supported chat, tools, agents, structured output, thinking, embeddings, images, transcription, and moderation. 2.0 adds video, speech, OCR, reranking, files, batches, and a shared API for provider-hosted tools. It also extends the existing APIs with more controls and richer results. Red cells show built-in support added in 2.0. Gray cells were already supported in 1.16. Outlined cells with a × mark missing integrations; use “Missing in 2.0” to find them. Select a cell for its sources and implementation notes.

The 40 shared features appear below. Additional provider APIs (55 rows) open on a separate page.

Red cells mark built-in support added in 2.0, including features previously available through raw options or partial integration. Select a cell for evidence.

Provider features. Red: built-in support added in 2.0. Gray: already built in to 1.16. Lighter red with braces: usable through raw options. Outlined cross: missing. Red stripes: partial. Dash: not documented in this API. Diagonal stroke: outside scope. Question mark: unverified.
FeatureOpenAIAnthropicGeminiVertex AIAmazon BedrockAzure OpenAI / FoundryxAIDeepSeekCohereMistralOpenRouterPerplexityDeepgramElevenLabsOllamaOllama CloudGPUStack
Conversations
Chat ╱ ╱
Chat streaming ╱ ╱
Structured output – – –
Image input – ╱
PDF input – – – ╱ – – –
Audio input – ╱ – – ╱ ╱ –
Video input – – – – – – – – – – – –
Thinking results – ╱
Thinking controls ╱ ╱
Citations – – ╱ – – –
Tools
Function tools ╱ ╱
Tool choice – – – –
Multiple tool calls ╱ ╱
Limit parallel calls – – – – – – –
Web search tool – – – ╱ – –
Web fetch tool – – ╱ – – – –
Code execution tool – – – ╱ – ╱ – –
File search tool – ╱ – – ? – – ╱ – – –
Remote MCP tools – – ╱ – ╱ – –
Caching and Context
Prompt caching – ╱ ?
Cache boundaries – – – – – – – – – –
Managed cache resources – – – – – – – – – – – – – – –
Context compaction ╱ – – – – – ╱ ? – –
Token counting – – – – ? – – – –
Media
Image generation – – – – – – –
Image editing – – – – – – – –
Video generation – – – – – – – – –
Speech generation – ╱ – – – – –
Transcription – – – –
Streaming transcription – – – – – – –
Speaker identification – – – – – – –
Moderation – – – – – – – – – – – – – –
Documents and Search
OCR / document parsing – – – – – – – – – – – – – – ?
Text embeddings – – – – – ?
Multimodal embeddings – – – – – – – – – –
Reranking – – – – – – – – – – –
Files and Batches
File upload – – – – –
File download – – – – –
Chat batches – – – – – – –
Embedding batches – ? – – – – – – – –