Research, with limits. These attributed findings were checked against search excerpts, not hands-on tests. Identity is linked to a primary reference; aliases and renames may still need resolution. Availability and usefulness are not independently assessed. The observed date is not a launch date.
What the sources describe
What it is
Reka describes Rho-1 as a 19B omni-reasoning model trained from scratch that generates text, images, and video and takes actions in one network. Source ↗
The announcement states Rho-1 base video generation runs at 0.79x real-time median, with a watchable stream beginning in about six seconds. Source ↗
This is a short discovery note. The available evidence does not yet support a complete practical guide.
Research history
Dated observations, not a claim that the product changed each time. Identical evidence does not create a new entry. Later checks can update the last-checked date.
View this observation
Reka describes Rho-1 as a 19B omni-reasoning model trained from scratch that generates text, images, and video and takes actions in one network. Source ↗
The announcement states Rho-1 base video generation runs at 0.79x real-time median, with a watchable stream beginning in about six seconds. Source ↗
How this was found
Initial broad query: new language reasoning multimodal AI model releases evaluations announcements and updates since 2026-10-03
Model: deepseek/deepseek-v4.1-flash · Policy: web-exploration-v2. Search excerpts are held privately for seven days; source links, evidence hashes and our reviewed paraphrases remain. Linked pages may change.