Omni 1.2 Flash puts free AI video inside Google Vids
Omni 1.2 Flash, and The Deploy Log for this week. Every price and claim read off the publisher's own page, with a call on each.
Omni 1.2 Flash
DEPLOYif you make product promos or social clips
WHAT SHIPPEDGoogle Vids now runs on Omni 1.2 Flash, and anyone with a Google account or Workspace subscription can generate up to three 15-second videos per month at no cost.
THE CATCHThe free tier is three videos per month, so it is a trial loop, not a production pipeline.
IF YOU RUNa marketing team that needs quick-turn social content without a video editor
SOURCEGoogle, Generate longer AI videos with Omni 1.2 Flash in Google Vids at no cost
The Deploy Log
Tools and products
| WATCHif you run local coding agents MiMo V2.6. Ollama v0.40.15 adds support for Xiaomi MiMo's mimo-v2.6, a 9B model built for code and agent workflows. Ollama |
| DEPLOYif you debug slow Next.js functions Vercel Tracing. Vercel Tracing is generally available on all plans, with a new Traces page, CLI search, automatic tracing for new Next.js projects, and retention of 3 days on Hobby, 14 days on Pro and Enterprise. Vercel |
| WATCHif you run recurring background tasks Vercel Schedules. Vercel Schedules is in public beta on all plans, running tasks on a recurring cadence or at a single point in time, billed at $5 per 1M runs and $10 per 1M creations on Pro and Enterprise. Vercel |
| DEPLOYif you add web search to agents DeepSeek Search and Fetch. DeepSeek Search and DeepSeek Fetch are available through AI Gateway, each costing $0.75 per 1,000 billable requests, with no separate DeepSeek account required. Vercel |
| WATCHif you manage repository secrets Secret scanning. GitHub secret scanning adds SpaceX as a partner, detects starlink_public_api_v2_secret, and upgrades Alibaba, AWS, Google, OpenVSX, Pydantic Services, and Tencent detectors with additional false-positive filtering. GitHub |
| WATCHif you run Claude Code behind a gateway Claude Code v2.1.319. Claude Code v2.1.319 changes auto mode behavior with telemetry or feature flags off, adds MCP task backgrounding, and adds a /claude-api latency-optimize command. Anthropic |
| WATCHif you use Codex in the terminal Codex rust-v0.167.0. Codex rust-v0.167.0 opens the agent command center with codex agents --no-daemon, marks unread results, and adds Google Cloud Vertex AI setup with Application Default Credentials or a credential file. OpenAI |
| WATCHif you use LangChain middleware langchain-typesafe 0.0.2. langchain-typesafe 0.0.2 accepts a classifier in experimental middleware. LangChain |
| WATCHif you stream LangChain output langchain-core 1.7.6. langchain-core 1.7.6 merges streamed AIMessageChunks once when accumulating runnable streams and stops parse_partial_json from retrying one character at a time. LangChain |
Robotics, hardware and chips
| WATCHif you stream games on GeForce NOW Hogwarts Legacy DLSS 5. Hogwarts Legacy receives an NVIDIA DLSS 5 upgrade with 3D-Guided Neural Rendering on GeForce NOW, and 24 games join the library in November, including eight this week. NVIDIA |
Left out
- Copilot weekly releases: edition 53 already carried it
- Copilot impact dashboard: it did not carry a number that moved
- Pull request overview: it did not carry a number that moved
- json-render: it did not carry a number that moved
- Policy-Based Enforcement: it did not carry a number that moved
- Gemini in Google Forms: it did not carry a number that moved
- SageMaker GPU partitioning: it did not carry a number that moved
- Mistral Studio: it did not carry a number that moved
- @GitHub in Slack and Teams: it did not carry a number that moved
The pattern
The same week that Google gives away three 15-second Omni 1.2 Flash videos per account, Vercel prices DeepSeek Search and Fetch at $0.75 per 1,000 billable requests and Schedules at $5 per 1M runs. Free video is a trial loop, while the paid tools are metered infrastructure. One says content creation is now a consumer feature; the other says agent workflows are a billing unit.
Claude Code v2.1.319, Codex rust-v0.167.0, Ollama v0.40.15 with MiMo V2.6, and langchain-typesafe 0.0.2 all ship in the same window. Each release tightens control over agents: backgrounding MCP tasks, opening a command center, accepting a classifier in middleware. The pattern is not new model capability but operational discipline. Meanwhile GitHub secret scanning adds SpaceX and upgrades Alibaba, AWS, Google, OpenVSX, Pydantic Services, and Tencent detectors, because every one of those agent surfaces is now a credential boundary.