{"slug":"2026-11-19-2000","scheduled_at":"2026-11-19T19:00:00.000Z","published_at":"2026-11-19T18:58:22.740Z","updated_at":"2026-11-21T20:59:15.357Z","is_no_updates":false,"tagline":"Google opens Genie 4 real-time world generation in the Gemini API, plus 5 more updates","cover_url":"https://ai24updates.com/api/covers/2026-11-19-2000","cover_alt":"Abstract editorial illustration on a dark canvas: a glowing interactive 3D landscape forming from light, captioned Genie 4","cover_credit":null,"correction_note":null,"update_count":6,"updates":[{"id":"google-genie-4-gemini-api","title":"Google Genie 4 — real-time world model now available in the Gemini API and AI Studio, with pricing","summary":"Google made Genie 4 (models/genie-4), its real-time interactive world generation model, available on the paid tier of the Gemini API and in Google AI Studio.","facts":["Genie 4 seeds a world from a text prompt, a 16:9 reference image, or both, then streams steerable 24 fps 16:9 video with synchronized 48 kHz stereo audio over WebRTC and WebSockets.","Users steer the live stream with keyboard movement controls (WASD and arrow keys) and mid-session text events, such as changing the weather or summoning characters.","It runs on the Interactions API (v1beta) and requires a paid-tier Gemini API key; it does not support the Free tier, Batch API, Flex or Priority inference.","Pricing is $1.50 per 1M input tokens (text or reference image) and $17.50 per 1M video output tokens (audio included), about $0.10 per second or ~$6.05 per minute of streamed output.","Google points users to Gemini Omni 1.2 Flash for offline fixed-length clips, multi-turn video editing and upsampling to 4K."],"announced_at":null,"announced_at_precision":null,"company":"google","change_type":null,"importance":null,"importance_reason":null,"action_required":null,"deadline":null,"story_id":null,"sources":[{"label":"Gemini API docs: Genie 4","url":"https://ai.google.dev/gemini-api/docs/models/genie-4","type":"docs","official":true},{"label":"Gemini API pricing","url":"https://ai.google.dev/gemini-api/docs/pricing","type":"docs","official":true},{"label":"Google AI Studio on X","url":"https://x.com/GoogleAIStudio/status/2123479057996116143","type":"social","official":true}],"primary_source_available":true,"detected_at":null,"what_changed":null,"previous_state":null,"availability_status":null,"products":null,"affected_roles":null,"usage_modes":null,"role_notes":null,"deadline_quote":null,"what_to_watch":null,"claims":[],"evidence_level":"legacy","action_base":null,"action_deadline":null,"event_version":1,"url":"https://ai24updates.com/updates/2026-11-19-2000#event-google-genie-4-gemini-api"},{"id":"ideogram-4-6","title":"Ideogram 4.6 — new image model with native 4K output and more precise editing","summary":"Ideogram released Ideogram 4.6, a new image model focused on precise editing, generating images in native 4K.","facts":["Ideogram 4.6 generates images in native 4K with no upscaling.","Ideogram says realism and texture detail are much better, with work to remove the 'AI look' and waxy skin.","Edits show significantly less pixel drift outside the edited area and better color and material accuracy.","Ideogram highlights sketch-to-image, saying the model stays as faithful as possible to the input sketch.","Ideogram also said it will skip an open 4.5 release and go directly to an open 4.6."],"announced_at":null,"announced_at_precision":null,"company":"ideogram","change_type":null,"importance":null,"importance_reason":null,"action_required":null,"deadline":null,"story_id":null,"sources":[{"label":"Ideogram on X","url":"https://x.com/ideogram_ai/status/2123461101224624402","type":"social","official":true},{"label":"Ideogram on X: open 4.6","url":"https://x.com/ideogram_ai/status/2123483923632025908","type":"social","official":true}],"primary_source_available":true,"detected_at":null,"what_changed":null,"previous_state":null,"availability_status":null,"products":null,"affected_roles":null,"usage_modes":null,"role_notes":null,"deadline_quote":null,"what_to_watch":null,"claims":[],"evidence_level":"legacy","action_base":null,"action_deadline":null,"event_version":1,"url":"https://ai24updates.com/updates/2026-11-19-2000#event-ideogram-4-6"},{"id":"kling-4-0-native-4k-hdr","title":"Kling 4.0 — native 4K resolution and 10-bit HDR output","summary":"Kuaishou's video model Kling 4.0 now supports native 4K resolution and 10-bit HDR output.","facts":["Kling 4.0 now generates video in native 4K resolution.","10-bit HDR output is available in both 4K and 1080p.","Kling says the update brings greater detail and richer colors to every frame.","The upgrade is available on kling.ai."],"announced_at":null,"announced_at_precision":null,"company":"kling","change_type":null,"importance":null,"importance_reason":null,"action_required":null,"deadline":null,"story_id":null,"sources":[{"label":"Kling AI on X","url":"https://x.com/Kling_ai/status/2123431119903461709","type":"social","official":true}],"primary_source_available":true,"detected_at":null,"what_changed":null,"previous_state":null,"availability_status":null,"products":null,"affected_roles":null,"usage_modes":null,"role_notes":null,"deadline_quote":null,"what_to_watch":null,"claims":[],"evidence_level":"legacy","action_base":null,"action_deadline":null,"event_version":1,"url":"https://ai24updates.com/updates/2026-11-19-2000#event-kling-4-0-native-4k-hdr"},{"id":"perplexity-agent-api-xhigh-gpt-6-2-sol","title":"Perplexity Agent API — xhigh effort level switches to GPT-6.2 Sol","summary":"Perplexity's Agent API xhigh effort level now runs on OpenAI's GPT-6.2 Sol with no fallback model.","facts":["The xhigh effort level now selects xhigh@2026-11-18.0, which uses openai/gpt-6.2-sol without a fallback model.","It replaces the previous configuration of Claude Opus 5.5 with a GPT-6.1 Sol fallback.","Tools, high reasoning effort, the 300-step limit and context compaction settings are unchanged.","Earlier pinned versions are unchanged; pinning xhigh@2026-11-11.0 keeps the previous model configuration."],"announced_at":null,"announced_at_precision":null,"company":"perplexity","change_type":null,"importance":null,"importance_reason":null,"action_required":null,"deadline":null,"story_id":null,"sources":[{"label":"Perplexity API changelog","url":"https://docs.perplexity.ai/changelog/changelog","type":"changelog","official":true}],"primary_source_available":true,"detected_at":null,"what_changed":null,"previous_state":null,"availability_status":null,"products":null,"affected_roles":null,"usage_modes":null,"role_notes":null,"deadline_quote":null,"what_to_watch":null,"claims":[],"evidence_level":"legacy","action_base":null,"action_deadline":null,"event_version":1,"url":"https://ai24updates.com/updates/2026-11-19-2000#event-perplexity-agent-api-xhigh-gpt-6-2-sol"},{"id":"microsoft-canvas-mai-image-2-7-flash","title":"Microsoft AI Canvas — interactive image workspace powered by MAI Image 2.7 Flash","summary":"Microsoft AI launched Canvas, an interactive image workspace on MAI Labs powered by its MAI Image 2.7 Flash model.","facts":["Canvas turns sketches into polished diagrams and supports precise edits without starting over.","Users describe an image in a panel or start from a photo; each run makes one image in about 10 to 20 seconds.","Parts of an image can be changed by editing a word in the prompt or selecting an object in the image.","Canvas is available to try now on Microsoft AI's MAI Labs site."],"announced_at":null,"announced_at_precision":null,"company":"microsoft","change_type":null,"importance":null,"importance_reason":null,"action_required":null,"deadline":null,"story_id":null,"sources":[{"label":"MAI Labs Canvas","url":"https://labs.microsoft.ai/?model=canvas","type":"other","official":true},{"label":"Microsoft AI on X","url":"https://x.com/MicrosoftAI/status/2123462465740533910","type":"social","official":true}],"primary_source_available":true,"detected_at":null,"what_changed":null,"previous_state":null,"availability_status":null,"products":null,"affected_roles":null,"usage_modes":null,"role_notes":null,"deadline_quote":null,"what_to_watch":null,"claims":[],"evidence_level":"legacy","action_base":null,"action_deadline":null,"event_version":1,"url":"https://ai24updates.com/updates/2026-11-19-2000#event-microsoft-canvas-mai-image-2-7-flash"},{"id":"ai2-theorizer-asta","title":"Ai2 Theorizer — research-theory agent launches in Asta and goes open source","summary":"Ai2 launched Theorizer, an AI agent that combines findings from scientific papers into testable theories, in its Asta research platform and open-sourced the code.","facts":["Theorizer proposes explanations for scientific observations and links each one to evidence from published studies, describing where it might apply.","It is available in Asta, Ai2's platform of AI agents for scientific research, where Ai2 covers token costs up to a limit.","The code is open source, so researchers can run the library locally and pay for tokens as needed.","Scientists have tested it in their own research for nearly a year; Ai2 hosts a webinar on December 10 at 10am PT."],"announced_at":null,"announced_at_precision":null,"company":"ai2","change_type":null,"importance":null,"importance_reason":null,"action_required":null,"deadline":null,"story_id":null,"sources":[{"label":"Ai2 blog","url":"https://allenai.org/blog/theorizer-in-asta","type":"official_blog","official":true},{"label":"Ai2 on X","url":"https://x.com/allen_ai/status/2123451767648125042","type":"social","official":true}],"primary_source_available":true,"detected_at":null,"what_changed":null,"previous_state":null,"availability_status":null,"products":null,"affected_roles":null,"usage_modes":null,"role_notes":null,"deadline_quote":null,"what_to_watch":null,"claims":[],"evidence_level":"legacy","action_base":null,"action_deadline":null,"event_version":1,"url":"https://ai24updates.com/updates/2026-11-19-2000#event-ai2-theorizer-asta"}],"kind":"regular","slot":"20:00","punctuality":"on_time","delay_minutes":0,"submission_punctuality":null,"submission_delay_minutes":null,"version":1,"submitted_at":null,"approved_at":null,"period_start":null,"period_end":null,"review":"editor","review_note":null}