{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-10-05-reka-rho-1-omni-model/","md":"https://postcutoff.com/e/2026-10-05-reka-rho-1-omni-model/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-05-reka-rho-1-omni-model","date":"2026-10-05","date_precision":"day","short_title":"Reka unveils Rho-1, a 19B 'omni' model that reads and generates text, images, streaming video and robot actions in one context","deck":null,"takeaway":null,"category":"research","category_label":"Research","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Reka: Rho-1: Collapsing the multimodal stack","url":"https://reka.ai/labs/research/rho-1-collapsing-the-multimodal-stack","type":"official","group":"primary","domain":"reka.ai"},{"n":2,"title":"Reka: inverse dynamics model for interactive world models","url":"https://reka.ai/labs/research/reka-inverse-dynamics-model-for-interactive-world-models","type":"official","group":"primary","domain":"reka.ai"},{"n":3,"title":"AlphaSignal: Reka's Rho-1 merges reasoning, video, and robot control into one model","url":"https://alphasignal.ai/news/reka-s-rho-1-merges-reasoning-video-and-robot-control-into-one-model","type":"press","group":"press","domain":"alphasignal.ai"}],"official":2,"filed":"2026-10-05","updated":"2026-10-05","orgs":["Reka AI"],"title":"Reka unveils Rho-1, a 19B 'omni' model that reads and generates text, images, streaming video and robot actions in one context","summary":"On Oct 5, 2026 Reka published Rho-1, a 19B-parameter model trained from scratch that puts text, vision, video and robot actions as tokens in a single context, streaming steerable video at about 0.79x real time; a distilled Flash variant makes a 5.3-second clip in about one second. It is a research preview only: no public weights or API.","key_facts":["19B parameters, 'symmetric two-stream transformer with shared attention', trained from scratch on 320 H100 GPUs for three months (Reka)","Streams video at a median 0.79x real time (99 denoising steps); a distilled 8-step variant (Rho-1 Flash) renders a 5.3-second clip in ~1 second","Native video resolution 672x384; continuous video can be steered mid-rollout without cuts","Robot actions: demo episode on LIBERO simulation tasks (seven action channels); no quantitative LIBERO scores published. Companion inverse-dynamics model derives robot controls from ordinary internet video","Known limits stated: long-horizon drift in 30-second streams, unreliable object tracking, brittle editing","Availability: research preview through collaboration on Reka Cloud; no public weights or public API (contact@reka.ai)"],"key_numbers":[],"tags":["multimodal","video-generation","world-model","robotics","research-preview"],"science":null,"body_md":"## What happened\n\nReka, the small multimodal lab behind the Reka Core/Flash/Edge models, published a research post on Rho-1. It is a single 19B\ntransformer that handles text, images, video and robot actions as tokens in one context window, instead of chaining a language\nmodel with a separate video diffusion model. Reka says it is \"among the fastest models in the world in every modality\" and\n\"faster than any other video model we timed\" for 5.3-second clips, but it names no competing models. Every result comes from a\ncheckpoint trained on \"just 320 H100 GPUs for three months\".\n\n## Why it matters\n\nThis is a compute-light attempt at the unified \"omni\" world-model and robotics stack that larger labs pursue with far more compute.\nThe speed claims are Reka's own. No independent benchmarks, weights or API exist yet.","disputed":[],"related":[],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-05","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-05","run":null,"sources_read":null,"updated":"2026-10-05","human_review":null,"version":{"date":"2026-10-06"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":127,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":97,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":188,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":127,"in_training_data":false}],"short_url":null}