--- title: Vani Studio is open, plus Docs, Slides and Designs,... description: AhuraSense's Vani assistant adds a large batch of features: Vani Studio for AI image/video generation (camera moves, effects, looks, reusable characters),... canonical: https://daily.dev/posts/vani-studio-is-open-plus-docs-slides-and-designs-learning-mode-and-scheduled-tasks-d6jfuzzps twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Vani Studio is open, plus Docs, Slides and Designs, Learning mode and scheduled tasks | daily.dev og:description: AhuraSense's Vani assistant adds a large batch of features: Vani Studio for AI image/video generation (camera moves, effects, looks, reusable characters),... og:url: https://daily.dev/posts/vani-studio-is-open-plus-docs-slides-and-designs-learning-mode-and-scheduled-tasks-d6jfuzzps og:image: https://api.daily.dev/og/posts/d6jfuZZps.png og:image:alt: Vani Studio is open, plus Docs, Slides and Designs, Learning mode and scheduled tasks og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Vani Studio is open, plus Docs, Slides and Designs, Learning mode and scheduled tasks **[Ahurasense](https://daily.dev/sources/ahurasense)** · 5 min read · 1 upvotes · 0 comments ## Summary AhuraSense's Vani assistant adds a large batch of features: Vani Studio for AI image/video generation (camera moves, effects, looks, reusable characters), Docs/Slides/Designs creation and editing, richer chat replies with charts and diagrams, a Learning mode that tutors instead of answering directly, and scheduled recurring tasks. Also new: project knowledge files, community-shared skills, a connectors directory (Notion, Linear, Sentry), message actions, cache-based usage reductions on long chats with several Claude/Fable/Kimi/MiMo models, and a monthly recap. For developers, every chat image/video model is now available via the API (including GPT Image 2 variants and Grok Imagine), cached token reporting, context length fields on the models endpoint, a learning mode API flag, new SDK guides, and restored Codex CLI compatibility with /v1/responses. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I enable learning mode in the Vani API instead of getting a direct answer? Add "vani_mode": "learning" to a Chat Completions, Responses, or Messages API request. This makes the model ask what you already know, give one hint at a time, check understanding, and still provide the full solution if explicitly requested, mirroring the Learning toggle available in the chat interface's model menu. _Developers tracking new API parameters for AI assistants can follow releases like this on daily.dev._ ### Which image and video generation models are available through the Vani API? Every image and video model available in chat is now exposed on the API, including GPT Image 2, GPT Image 2.5 Flare and Sunburst, and Grok Imagine Image and Grok Imagine Video, alongside existing models. Each is priced per image or per video according to the published pricing page. _Those comparing generative media APIs can keep up with newly released models via daily.dev._ ### How can I see cached token usage when calling the Vani or Claude API? The field prompt_tokens_details.cached_tokens (with equivalents in the Responses and Messages APIs) reports how many tokens were billed at the cheaper cached-input price. Claude cache_control hints passed in a request are also forwarded where the underlying provider supports them, letting developers verify caching savings on long conversations. _Developers optimizing LLM API costs can track usage-reporting changes like this on daily.dev._ ## Similar posts on daily.dev - [Google AI Studio is the best-kept secret in vibe coding](https://daily.dev/posts/google-ai-studio-is-the-best-kept-secret-in-vibe-coding-vsft4yozq) · XDA Developers · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#genai](https://daily.dev/tags/genai), [#ai-image-generation](https://daily.dev/tags/ai-image-generation) [View this post on daily.dev](https://daily.dev/posts/vani-studio-is-open-plus-docs-slides-and-designs-learning-mode-and-scheduled-tasks-d6jfuzzps) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Vani Studio is open, plus Docs, Slides and Designs, Learning mode and scheduled tasks","url":"https://daily.dev/posts/vani-studio-is-open-plus-docs-slides-and-designs-learning-mode-and-scheduled-tasks-d6jfuzzps","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/vani-studio-is-open-plus-docs-slides-and-designs-learning-mode-and-scheduled-tasks-d6jfuzzps"},"datePublished":"2026-10-03T13:55:53.094Z","dateModified":"2026-10-03T13:56:18.357Z","description":"AhuraSense's Vani assistant adds a large batch of features: Vani Studio for AI image/video generation (camera moves, effects, looks, reusable characters),...","image":"https://media.daily.dev/image/upload/s--ZrL_HSsR--/f_auto/v1722860399/public/Placeholder%2006","thumbnailUrl":"https://media.daily.dev/image/upload/s--ZrL_HSsR--/f_auto/v1722860399/public/Placeholder%2006","isAccessibleForFree":true,"articleSection":"Ahurasense","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Ahurasense","logo":"https://media.daily.dev/image/upload/s--WNYcnrr7--/f_auto/v1790970263/squads/b4b1b632-59d4-4ff2-95a4-bf38f90e102d?_a=BAMAMicg0","url":"https://daily.dev/squads/ahurasense"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/vani-studio-is-open-plus-docs-slides-and-designs-learning-mode-and-scheduled-tasks-d6jfuzzps","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,genai,ai-image-generation","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Ahurasense","item":"https://daily.dev/squads/ahurasense"},{"@type":"ListItem","position":3,"name":"Vani Studio is open, plus Docs, Slides and Designs, Learning mode and scheduled tasks"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/vani-studio-is-open-plus-docs-slides-and-designs-learning-mode-and-scheduled-tasks-d6jfuzzps#faq","mainEntity":[{"@type":"Question","name":"How do I enable learning mode in the Vani API instead of getting a direct answer?","acceptedAnswer":{"@type":"Answer","text":"Add \"vani_mode\": \"learning\" to a Chat Completions, Responses, or Messages API request. This makes the model ask what you already know, give one hint at a time, check understanding, and still provide the full solution if explicitly requested, mirroring the Learning toggle available in the chat interface's model menu. Developers tracking new API parameters for AI assistants can follow releases like this on daily.dev."}},{"@type":"Question","name":"Which image and video generation models are available through the Vani API?","acceptedAnswer":{"@type":"Answer","text":"Every image and video model available in chat is now exposed on the API, including GPT Image 2, GPT Image 2.5 Flare and Sunburst, and Grok Imagine Image and Grok Imagine Video, alongside existing models. Each is priced per image or per video according to the published pricing page. Those comparing generative media APIs can keep up with newly released models via daily.dev."}},{"@type":"Question","name":"How can I see cached token usage when calling the Vani or Claude API?","acceptedAnswer":{"@type":"Answer","text":"The field prompt_tokens_details.cached_tokens (with equivalents in the Responses and Messages APIs) reports how many tokens were billed at the cheaper cached-input price. Claude cache_control hints passed in a request are also forwarded where the underlying provider supports them, letting developers verify caching savings on long conversations. Developers optimizing LLM API costs can track usage-reporting changes like this on daily.dev."}}]} ```